VOLUME 11, ISSUE 4, APRIL 2024

Abstract: Due to continuous variation of charging level battery, connected loads are different in electric vehicle (EV) charging stations. The linear controllers such as P, PI and PID does not provide smooth and regulated response in case of EV charging applications as well as power electronics collaboration. Sometimes load changes in sudden situation and EV charging stations comes in instability region. Considering the reasons, this research work discusses on implementation of non-linear controllers for EV battery charging applications. This paper shows and describes the performance of Fuzzy-Logic Controller (FLC) and Sliding Mode Controller (SMC) for EV charging applications. The Fuzzy-Logic controller and sliding mode controller has been developed for Split-Pi converter-based battery charging scheme, and the complete control system has been analyzed and validated by simulation study. Performances have been investigated in detail for checking different characteristics. Split-Pi converter is a recently invented DC-DC converter which has great potential in the power electronics field because it has less components and lower switching losses. The closed-loop operation of this converter topology has been analyzed and discussed with simulation results.

Keywords: Fuzzy Logic Controller, Sliding Mode Controller, EV Battery, Charging Station, Split-Pi DC-DC Converter, Solar PV Panel.

Abstract: The global energy landscape is undergoing a transformative shift, and the potential ofLNG as a major energy source is a topic of intense debate. In order to meet the growing demand for sustainable energy supply, it is crucial to maximize the efficiency andenvironmental friendliness of the LNG supply chain. This research paper aims to leverage computational modeling and optimization techniques to enhance the production units involved in LNG production. By harnessing the power of advanced algorithms and simulations, we can identify and implement innovative strategies that minimize energy consumption, reduce greenhouse gas emissions, and enhance the overall sustainability of LNG. This study, we seek to uncover novel approaches to address the challenges faced by the LNG industry, including improving operational efficiency, optimizing liquefaction processes, and enhancing the utilization of natural resources. By integrating cutting-edge computational tools and considering environmental factors, we aspire to pave the way for a more sustainable and environmentally friendly future powered by LNG. By exploring the immense potential of computational modeling and optimization, we strive to contribute to the ongoing efforts in advancing energy sustainability and shaping the future of LNG as a crucial global energy source. In this paper, our focus is on simulating and optimizing the process of converting natural gas to LNG. Our goal is to achieve the minimum energy consumption per ton of LNG produced. Through our research, we have identified that utilizing a three-stage heat exchanger is the most effective approach for minimizing energy consumption in an LNG industrial production unit. Moreover, we have discovered that the outlet pressure from the compressor and the type of refrigerant in the cooling system play significant roles in determining the rate of energy conservation. By carefully considering these factors and optimizing their settings, we can further enhance the overall energy efficiency of the LNG production process. Our research also aims to provide valuable insights and guidance to industry professionals and decision-makers in the LNG sector. By implementing the findings of this study, we can contribute to the sustainable development and utilization of LNG as a cleaner and more environmentally friendly energy source. It's great to see the optimized parameters for the refrigerants and pressure settings in the liquefaction and sub-cooling cycles. With the mass fraction of 0.89 for methane and 0.14 for ethane in the liquefaction cycle, and 0.59 for methane and 0.3 for nitrogen in the composition for achieving energy efficiency in the LNG production sub-cooling cycle, The optimized outlet pressure of 650 kPa for the compressors in the liquefaction cycle and 1800 kPa for the sub-cooling cycle further contribute to minimizing energy consumption. Based on our findings, the amount of consumed energy at 14.81 kW per ton of produced LNG highlights the success of the optimization efforts. Reducing the energy consumption per ton of LNG produced is a significant accomplishment towards achieving energy sustainability and environmental friendliness in the LNG industry. These results demonstrate the importance of computational modeling and optimization in identifying the best parameters for enhancing energy efficiency in LNG production. By implementing these optimized settings, we can work towards a more sustainable future with reduced energy consumption and lower environmental impact.

Keywords: LNG, Unit, Production, Energy, Precooling, Simulation, Sub- Cooling, optimization, Liquefaction.

Abstract: Purpose: Artificial intelligence (AI) is being increasingly explored for its potential applications in disease prevention and clinical medicine. This article studies the characteristics of falls in the elderly, summarizes the research on non-contact sensor-based machine learning, and discusses issues and suggestions related to fall prevention. It evaluates the living conditions of the elderly and provides a theoretical basis for preventing fall risks. The article also discusses the advantages, disadvantages, and prospects of applying AI in mental health, aiming to provide a reference for future research. Results: A systematic introduction to applying sensor technology in fall prevention equipment, such as millimeter-wave radar, inertial, and MEMS sensors.Conclusion: AI is developing rapidly and can complement manual diagnosis, but it also has limitations like algorithm bias and ethical issues. Mental health practitioners should actively adapt to and promote the further development of AI in this field.

Keywords: Elderly fall prevention, Non-contact sensor technology, AI applications in mental health Machine learning for fall detection

Abstract: This paper provides an overview of the designing principles of fluid vehicles (15 aged, engine damaged, and going for trash vehicles) into the electric vehicle conversion process. The paper describes the development of an electric vehicle powertrain and the design and analysis of the different parts of vehicles like a transmission system (bush, bearing, and sprocket) battery, geared motor, motor, and controller. It also, explains the design rules and calculations of the powertrain subsystem. Electric vehicles are powered by geared electric motors (DC) which are powered by the battery through the electric converter. Conventional vehicle loses their efficiency after a long duration. Retrofitting gasoline-powered vehicles into an electric vehicle is a cost-effective and beneficial process. During the retrofitting, the powertrain, electrical parts, and vehicle parts (swing arm, bush, and bearing) are required to modify and the remaining subsystems like suspension, steering, and braking will be the same. In the powertrain part, the vehicle consists of a Geared motor, motor controller, battery, and battery management system, and transmission system (chain drive).

Keywords: Fluid vehicles, Electric vehicles, lithium-ion battery, Controller, Geared motor, transmission.

Abstract: This paper presents a novel methodology for advancing unsupervised neural machine translation (NMT) systems using large, pre-trained language models, notably focusing on GPT-3. The proposed approach involves a three-step process: few-shot amplification, distillation, and backtranslation. Through experiments on the WMT14 English-French benchmark, the methodology achieves state-of-the-art results, demonstrating its effectiveness and versatility. Challenges such as few-shot prompting and model scalability are addressed, showcasing the robustness of the approach. Experimental results across different model sizes and configurations highlight its adaptability. The findings suggest that leveraging generative pre-trained language models offers promising avenues for enhancing unsupervised NMT systems. This methodology not only advances the state-of-the-art in machine translation but also lays the foundation for broader applications in sequence-to-sequence tasks. Further exploration of this approach could lead to significant advancements in the field of natural language processing.

Keywords: Unsupervised Neural Machine Translation, Generative Pre-trained Language Models, Few-shot Amplification, Distillation, Backtranslation, Zero-shot Translation, Experimental Evaluation, GPT-3.

Abstract: The technology known as augmented reality (AR) has the potential to revolutionize education in a big way. AR is a great helper when it comes to experiment-based learning, making the entire process more enjoyable. AR ensures that students follow processes properly and securely by superimposing virtual features over the actual world. This allows for real-time advice for pupils. Additionally, it can incorporate virtual elements that replicate difficult or dangerous experiments, so broadening the scope of hands-on learning. Through the use of visualizations such as charts, graphs, and real-time data overlays, AR uses data visualization to make outcomes easier to interpret. Furthermore, remote collaboration is made feasible, allowing students to engage with the exact same experiment from different locations, encouraging inclusion and teamwork. One essential component of AR in experiment learning is safety instruction. It may mimic dangerous conditions and emergency protocols, making sure kids are ready for anything that can come up. Moreover, AR helps to make experiments more relevant and understandable by offering context for history and explanations of difficult scientific ideas. It may recognize and draw attention to faults made during experiments, assisting students in growing as problem solvers and learners from their mistakes. Incorporating gamified components into augmented reality (AR) creates a stimulating and competitive learning environment where students may receive prizes for successfully completing experiments. By boosting safety, engagement, comprehension, and accessibility and equipping students for a future driven by technology, the suggested use of augmented reality (AR) offers a broad and adaptable toolkit for both educators and students.

Keywords: Augmented Reality, Revolutionize, Education, Experiment, Student, Learning, Technology, Remote collaboration, Enjoyable.

Abstract: The utilization of agricultural waste for energy production has gained considerable attention due to its potential to address environmental concerns while promoting sustainable energy practices. In this study, we propose a novel approach for energy conversion from agricultural waste employing an AC motor-blade system coupled with a screw conveyor driven by a DC motor. The first component of our system comprises an AC motor connected to a blade mechanism. This setup is designed to efficiently shred and pulverize agricultural waste materials, such as crop residues, straw, and husks, into smaller particles. The use of an AC motor allows for precise control over the rotational speed, optimizing the shredding process for various types of agricultural waste. Subsequently, the shredded biomass is conveyed through a screw conveyor system, which is powered by a DC motor. The screw conveyor facilitates the transportation of the biomass particles towards the energy conversion unit, ensuring a continuous feed of feedstock. The utilization of a DC motor offers several advantages, including high torque capabilities, energy efficiency, and ease of speed regulation, making it suitable for driving the conveyor system in a cost-effective manner. The energy conversion unit consists of a biomass-to-energy conversion system, such as a gasifier, pyrolyzer, or anaerobic digester, depending on the specific application and requirements. This unit processes the shredded agricultural waste to produce energy in the form of biogas, syngas, or biochar, which can be utilized for various applications including electricity generation, heat production, or biofuel synthesis. Overall, our proposed system offers a sustainable and efficient solution for converting agricultural waste into valuable energy resources. By harnessing the power of AC and DC motors in conjunction with mechanical components such as blades and screw conveyors, we aim to contribute towards mitigating environmental pollution, reducing dependence on fossil fuels, and promoting the adoption of renewable energy technologies in agricultural settings. Further research and development are warranted to optimize the performance and scalability of the proposed system for real-world applications.

Keywords: Agricultural Waste, Energy Conversion

Abstract: This paper presents the design and fabrication of a versatile multi-purpose woodworking machine tailored for small-scale workshops and hobbyists. The machine integrates an AC motor, belt and pulley system, buffing tool, grinding wheel, wood cutting tool, and a microcontroller with object sensor for motor auto cut-off, offering flexibility and functionality in various woodworking tasks.The woodworking machine's design focuses on modularity and user-friendly operation, allowing for easy interchangeability of tools and versatility in woodworking applications. The AC motor serves as the primary power source, driving the belt and pulley system to transmit power to different tools based on the selected operation. The buffing tool and grinding wheel enable tasks such as polishing, sanding, and sharpening, enhancing the finishing quality of woodwork projects. Additionally, the wood cutting tool provides precision and accuracy in cutting and shaping wooden materials, catering to a wide range of cutting requirements.Moreover, the integration of a microcontroller with an object sensor adds an intelligent feature to the machine, enabling automatic cut-off of the motor when an obstruction or safety hazard is detected. This enhances user safety and prevents accidents during operation, making the machine suitable for novice users and hobbyists. The fabrication process involves assembling the various components into a compact and robust framework, ensuring stability and durability during operation. Emphasis is placed on ergonomic design and safety features to enhance user experience and minimize risks associated with woodworking tasks. Overall, the designed multi-purpose woodworking machine offers versatility, efficiency, and safety features suitable for small-scale woodworking operations, educational institutions, and hobbyist workshops. Its modular design, coupled with advanced features such as automatic motor cut-off, contributes to enhancing productivity, precision, and safety in woodworking activities.

Keywords: Woodworking machine, AC motor, Belt and pulley, Buffing tool, Grinding wheel, Wood cutting tool, Microcontroller, Object sensor, Auto cut-off, Safety.

Abstract: The empowering multipurpose agricultural equipment is made for performing various types of operations like Ploughing, Seeding Sowing, Spraying and levelling. The modification includes fabricating a vehicle which is small and compact in size. The research is about a vehicle design which makes cultivation much simpler. The ploughing tool is designed and modified. Farming is backbone of Indian economy 70% of people live in rural area. In rural area agriculture is one of the major source of earning money. In agriculture sector there are lot of tasks such as seed sowing, cultivation, levelling, spraying for doing this operation farmers required hand tools but doing operation by hand tool is very time consuming and quality of work is not good therefore results of this type work is poor productivity and less quality of work so this type of problem face by farmers. The most of the farmers are low level income so they can't invest on the purchase of large machine so our team is decided to research on this type problem and design empowering agriculture with multi utility equipment. The main aim of this equipment is design and build a multipurpose equipment for performing multiple major operation like ploughing, cultivation, spraying, levelling. The modification of this project is not only small but also cost is less compared to other equipment. This machine makes all operations in less work and much simple. Agriculture equipment is small smart machine that can do right things in right way. This research paper reviews multiple operations can be done on a single equipment.

Keywords: Empowering agriculture, Agriculture equipment, Seed sowing, Cultivation, levelling, Fertilizer Sprayer, Research etc.

Abstract: The FireGuard project presents a groundbreaking approach to fire safety through the development of a Sensor-Driven Fire Detection and Extinguishing System. This system aims to enhance fire detection accuracy by swiftly identifying various forms of fire, including flames, heat, and smoke, thereby minimizing false alarms and enabling timely response measures. By integrating automated fire suppression mechanisms, FireGuard reduces response time and minimizes human intervention during critical stages of fire incidents. The project's objectives include improving overall fire safety, mitigating risks to human lives, and minimizing property damage.

Keywords: Fire detection, Fire suppression, Sensor-driven system, Automated system, Fire safety.

Abstract: The concept of this paper is to implement the crop selection method so that this method helps in solving many agriculture and farmers problems. This improves our Indian economy by maximizing the yield rate of crop production. Different types of land condition. So the quality of the crops are identified using ranking process. By this process the rate of the low quality and high quality crop is also notified.Crop yield production value updation has a positive practical significance for guiding agricultural production and for notifying the change in market rate of crop to the farmer.

Abstract: The wear reduction material analysis of noryl polymer matrix composites material mixed in the ratio of (70:30) is presented in this paper. In recent trends of advancement in gears, the automobile industries have been inclinations in developing composite materials for high durability, less replacement and low-cost. Several attempts have been made in varying composition of polymer matrix composite at the cost of durability and ruggedness. A few researchers have been landed up in nylon 6 polymer matrix composites material of ratio 80:20 to increase the strength of the material and wear resistance. However, the reduction in wear is still a challenging issue. The present study focuses on developing 70:30 noryl polymer matrix metal composites and analyzing the effect of various input process parameters namely process temperature and weight % of reinforcement (Abs) on the hardness, flexure and tensile strength and It has been observed on experimentation that mechanical properties of the noryl composites are significantly influenced by the weight percentage of glass fiber and 80% noryl + 20% composite shows the highest elastic modulus, yield strength and significantly improved tensile strength. These experimental results confirm the excellent wear reduction of the material that envisages for the better product life and less maintenance.

Keywords: Composite gears,Polymer matrix composite gears,Fibre-reinforced polymer (FRP) gears,Composite material gears,Reinforced plastic gears,Composite resin gears

Abstract: Waste heat recovery (WHR) from domestic appliances and processes offers a significant opportunity to improve energy efficiency and reduce household energy bills. Phase Change Materials (PCMs) are a promising technology for WHR due to their ability to store and release thermal energy at specific temperatures. This project proposes the design and fabrication of a WHR system using PCMs for domestic applications. The system aims to capture waste heat from various domestic appliances and processes, such as clothes dryers, ovens, or range hoods, and store it in PCMs. The stored thermal energy can then be released for various applications, including preheating water, space heating, or even cooking. The project presents a conceptual design of the system, identifies potential PCM candidates, and outlines fabrication and testing procedures. It also highlights the potential benefits of the system, such as reduced energy consumption, sustainability, improved comfort, and scalability. The project acknowledges the challenges of material selection, heat exchanger design, leakage prevention, and system integration. It concludes by emphasizing the need for further research and development to optimize materials, design, and fabrication processes for a commercially viable domestic WHR system using PCMs The system will target specific waste heat sources, such as exhaust from clothes dryers, ovens, or range hoods. A compact and efficient heat exchanger will be designed to transfer heat from the waste source to the PCM. The PCM will be contained in a sealed and insulated container to prevent leakage and minimize heat loss. The stored thermal energy in the PCM can be released for various domestic applications, such as preheating water for showers or dishwashing, space heating, or even cooking. The system will be fabricated and tested, and its efficiency in capturing waste heat, storing it in the PCM, and releasing it for various applications will be evaluated. The project has the potential to significantly reduce energy consumption, promote sustainable living, and improve domestic comfort.

Keywords: Waste heat recovery,Phase change material (PCM),Domestic applications,Energy efficiency Thermal energy storage,Heat transfer,Renewable energy,Sustainable technology

Abstract: Major standard languages such as Codex have demonstrated the ability to generate code for a wide variety of tasks. However, current models have limited performance, especially on complex tasks. One reason for this is that the language model does not understand the context of the program, causing the program to be buggy or even fail. In this article, we investigate whether automatic correction (APR) can correct the solutions produced by the language model in the LeetCode competition. The aim is to investigate whether the APR technique can increase the reliability of code generated from large language samples. Our research shows that: (1) retrieved developer code shows faults in man-made solutions and shows that APR technology can fix development rights; (2) updated Codex format that supports code fixing similar to or better than the existing Java fixing tool TBar and Logger for providing evidence of bug location, providing bug information, fixing bugs. By analyzing the experimental results produced by this tool, we make several recommendations: (1) The APR tool needs to be improved to overcome the limitation of patch area location (e.g., displaying more local crime); (2) Due to the large size of the language model, more correction models can be obtained by training more data, and future APR tools can shift the focus by adding additional models to the link structure/content, (3) By combining the language structure with APR, it is amenable to link, learning.

Keywords: Bug fixing techniques, automated and semi-automated, solutions, testings.

Abstract: This paper is based on electrical vehicle charging station and its infra structure which give some information about charging station and how its work, The world transportation area is in the change state, it is moving from conventional to non-conventional energy source fuelled vehicles without internal combustion engine vehicles. Due to the growing demand of electrical vehicle the recent researchers needs to investigate the optimal location of electric vehicle charging stations. To help this change, a legitimate charging station framework in combination with information technology, smart distributed energy producing units, and good government approaches are required. Also structured analysis of parameters is performed for the commercial opportunities of electric vehicles in existing energy market. This paper provides an overview of electrical vehicle charging station, including their types, technologies, challenges, and structure.

Keywords: Introduction, types of EV charging stations, components of EV charging station, EV charging infrastructure, Conclusion.

Abstract: Transformer plays a major role in the power system. It works 24 hours a day and provides power to the load. The transformer is excessive full, its windings are overheated which leads to the judgment of the transformer installation which leads to disruption of the power supply to the load. It takes a lot of time to repair and involves a lot of costs. This project deals with transformer protection under conditions of overcrowding. The transformer could be protected by reducing the additional the transformer's load by connecting and using another transformer in conjunction the primary transformer using a microcontroller and a switch relay. The load on the first transformer is compared to the reference value by the Arduino. When the load exceeds the reference value, the slave transformer is automatically attached to the first transformer and the extra load is shared. Therefore, the number of transformers works well under conditions of overcrowding and damage could be prevented. In this project, slave transformers share the master transformer's duty in the event of overcrowding and overheating. Sensor circuit with Arduino, current transformer, and other components is designed to collect data from the master transformer and if it is determined to be overloaded, the slave transformer is immediately attached to the master transformer and the load is shared. The Arduino keeps track of the transformer's current volume and displays it. If loads are introduced to the current transformer's second side in the second side riser. As the current volume exceeds the estimated current value of the transformer, so the microcontroller sends a travel signal to the relay, thus opening the slave transformer. Initially when we open the load, it will be shared by the first transformer. Once the load on the first transformer has been raised above its maximum capacity, the standby transformer will automatically share the load.

Keywords: Transformer, Shading, Sharing

Abstract: Is one of the main pillars of life on Earth. Due to its fertility anAd good drainage, red soil is frequently utilized in agriculture. This is especially advantageous for crops like sugarcane and bananas that need a lot of nutrients. Vegetables and fruits are among the various crops that can be grown on red soil. We must be aware of the characteristics of soil. In our research, we will examine the physco-chemical characteristics of the red soil that we are working with. Bhiwandi (East) Dongari pada, Thane district, Maharashtra is the location of the research. In our investigation, we'll examine the physical and chemical characteristics of this red soil, including the elements that are present in it.what physical characteristics it possesses. We will examine physical characteristics such as conductivity, pH, percentage of carbon, etc. During this time. Chemical characteristics such as the presence and amount of Fe, Cu, Zn, Ca, Mg, Sulphur, and Nitrogen will be studied.

Keywords: Red soil, Conductivity, Resistive, pH-value, Physical properties, Chemical properties etc.

Abstract: The present automobile industries need execution of industrial robots due to standard in mass and batch size production of the vehicles. Design of omnidirectional vehicles is now a traditional way in automobiles sectors. The operating advantage of this kind of vehicle is on any kind of surface such as a rough, smooth, flat, and curved surface. A vehicle has the potential to get omnidirectional, if it operated on mecum wheel. By providing the omnidirectional ability vehicle has moving flexibility that such type of vehicle can work in any internal and external application. In present paper design and different applications of mecnum wheel for omnidirectional vehicle has been presented. Different design and fabrication and manufacturing steps are discussed.

Keywords: Omni-Directional Mobile Robot, Mecanum Wheel & Autonomous System

Abstract: With the breakthroughs in technology, improvisation with existing systems is not only more efficient than its ancestors, but it is also essential to be able to adapt to the next generation. This is now made possible by the interdisciplinary integration of technology. With respect to automotive brakes, conventional braking mechanisms cannot always reach their potential due to friction loss and wear of the brake shoe material, and the smoke is also inherently toxic due to the generation of heat. Therefore, this is the process of creating a more reliable and environmentally friendly braking system that works like ABS (Anti-Lock Braking System) built through a control unit. This document describes the impact on electromagnetic braking systems and other traditional braking systems. The braking system must ensure the safety and comfort of the driver when driving the vehicle on the road. There are many types of traditional braking systems, including drum brakes, disc brakes, hydraulic brakes, and pneumatic brakes. This braking system creates high friction, causing thermal wear of the braking components and ultimately reducing the efficiency of the braking system. Therefore, an electromagnetic brake system is used. This is a method of braking efficiently with a high-power torque ratio and less friction. Most braking systems operate on the principle that kinetic energy is converted to thermal energy. This method has its own drawbacks and must be replaced with a more maintenance-free, more efficient braking system that reacts quickly, does not heat up. In this project, we propose a low friction braking system that utilizes the eddy current phenomenon. This phenomenon is controlled by Faraday's law of electromagnetic induction and Lenz's law. Eddy currents are generated by the relative movement between a metal or alloy conductor and a magnet.

Keywords: Electromagnetic Braking,Zero Friction Brake,Magnetic Brake System,Frictionless Braking.

Abstract: Man has needed and used energy at an increasing rate for his sustenance and wellbeing ever since he came on earth for few million year ago. Due to this lot of energy resources have been exhausted and wasted. Proposal for the utilization of waste energy of power generation by gym pulley is very much relevant and important for highly populated countries like india and china the people are crazy about gym. In this project we are generating electrical power as non-conventional method by simply pull up and pull down. Non-conventional energy system is very essential at this time to our nation. Non-conventional energy using pull up pull down is converting mechanical energy into electrical energy. In this project the conversion of force energy intoelectricalenergy. The use of human-power in more efficient manner for generation has been possible due to modern technology. Pull up pull down power is an excellent source of energy, 95 percentage of the exertion put into pull up pull down power converted into energy. Aa human-powered electricity generation has been unveiled by company. In this apparatus, the user has to pull up pull down the gym equipments for generating power. Another one is a foot- powered device that allows individuals to pump out power at a 40-watt clip to charge its own internal battery. Then this battery can be used for powering ac and dc devices, car batteries etc.

Keywords: Human-powered energy generation,Gym pull-up,Renewable energy,Sustainable fitness,Kinetic energy harvesting,Exercise electricity generation

Abstract: The IoT-Based Alcohol and Drowsiness Detection System project aims to enhance safety in transportation and workplaces by leveraging IoT technology. By integrating sensors with IoT platforms, the system detects alcohol impairment and drowsiness in real-time. Utilizing machine learning algorithms, it provides timely alerts to users. Targeting private vehicle owners, fleet operators, and industries, the project emphasizes safety and compliance. Key objectives include algorithm development, sensor integration, and deployment. By preventing accidents caused by impairment or fatigue, the project promotes safety and responsibility, reducing liabilities and fostering well-being in diverse settings.

Keywords: IOT, Alcohol, Drowsines

Abstract: This study presents an advanced vehicle theft detection system that utilizes a combination of cutting-edge technologies to secure vehicles effectively. By integrating optical fingerprint sensors, GPS tracking, GSM communication, and the ESP32 Cam, the system offers a comprehensive approach to prevent unauthorized access and facilitate the recovery of stolen vehicles. At the heart of this system is an optical fingerprint sensor that authenticates users by matching their fingerprints with stored templates, ensuring that only authorized individuals can access the vehicle. Concurrently, a GPS module provides real-time location tracking, crucial for monitoring the vehicle's status and aiding in its recovery in case of theft. The GSM module is pivotal for communication, enabling the system to send instant alerts to the vehicle owner's mobile device if an unauthorized attempt is detected. This prompt response capability is crucial for preventing potential thefts by allowing owners to react swiftly. Enhancing these features, the ESP32 Cam module offers visual surveillance by capturing images or videos of individuals attempting vehicle access under suspicious circumstances. This not only adds an additional layer of security but also aids in identifying perpetrators. Combining fingerprint verification, location tracking, instant messaging alerts, and visual evidence, this system provides a robust security solution. It ensures vehicle safety and supports quick recovery actions, offering vehicle owners enhanced peace of mind. This integrated approach marks a significant advancement in automotive security technology, addressing the critical need for effective anti-theft systems in modern vehicles.

Keywords: Optical Fingerprint, GSM, GPS, ESP32 CAM

Abstract: The aim of the paper is making machine components such as shaft, bolts, screws ,v belt motor etc. The main research paper Cutting wood with circular blade is a popular machining operation in the woodworking and furniture industries. Our project aims to manufacturing a machine with a sliding table to make cutting wood easier. The machine incorporates a sliding table mechanism, allowing for smooth and horizontal movement of the workpiece during cutting operations. To make cutting wood easier and more accurate for people who make furniture or do carpentry.

Abstract: Academic integrity has grown to be a major concern in educational institutions all over the world in recent years. Since technology has advanced, conventional techniques for administering and overseeing exams have shown to be insufficient in discouraging cheating and guaranteeing fairness. This work suggests a unique fingerprint-based biometric method for exam sheet identification in order to address these issues.The suggested method makes use of each student's own fingerprint pattern to reliably identify and authenticate exam sheets. The integration of fingerprint recognition technology into exam administration procedures allows educational institutions to improve security, stop fraud, and maintain student integrity. Compared to traditional methods, this strategy has a number of benefits, including improved accuracy, efficiency, and dependability.The method of using the system involves several steps, the first of which is enrolling students' fingerprints into a centralized database. Students' fingerprints are taken during exam registration and linked to the appropriate exam sheet. Students must use a biometric scanner attached to the exam sheet distribution system to verify their identity on test day by touching their finger on it. After the student authenticates, the system confirms their identification and obtains the relevant exam sheet from a safe deposit box. This removes the chance of confusion or illegal access by guaranteeing that every student receives their assigned exam sheet. In order to prevent cheating and ensure an equitable testing environment, the system continuously scans for any suspicious activity or attempts at malpractice throughout the exam period. Apart from augmenting security and upholding academic integrity, the suggested system provides pragmatic advantages to educators and learners alike. Exam distribution is streamlined to cut down on administrative work and lower the possibility of mistakes that come with handling exam materials by hand. Additionally, the system's real-time monitoring and auditing features let teachers keep tabs on exam progress and quickly spot irregularities. All things considered, the addition of fingerprint-based exam sheet authentication is a major step toward maintaining academic honesty and equity in learning evaluations. Institutions can reduce the likelihood of academic dishonesty, safeguard the validity of academic credentials, and preserve the values of honesty and integrity in education by utilizing biometric technology.

Keywords: Authentication, Finger print, security

Abstract: The implementation of Onboarding B2B supply chain partners through the application of conversational AI and natural language processing (NLP). This study is to provide smooth communication between organizations in order to optimize and improve the onboarding process through the use of advanced technology. The research tackles the difficulties involved in information sharing, documentation, and teamwork during partner onboarding by incorporating conversational artificial intelligence. With the purpose of answering inquiries and offering support, the chatbot leads partners through the onboarding procedure. Additionally, the chatbot processes and extracts data from the partner's responses using natural language processing (NLP), doing away with the necessity for human data entry. The study looks at how natural language processing (NLP) can be used to automate the analysis of contracts, agreements, and other pertinent documents by extracting useful insights from textual data.

Keywords: Natural Language Processing (NLP), conversational AI, Chatbot, B2B,

Abstract: Solar refrigeration systems have gained significant attention in recent years as an environmentally friendly and sustainable alternative to conventional refrigeration techniques. The concept of harnessing the Peltier effect, which involves the use of thermoelectric modules, offers an innovative approach to cooling and refrigeration powered by solar energy. This abstract provides an overview of our research, which focuses on the development and optimization of a solar refrigeration system based on the Peltier effect for potential applications in a variety of settings, including domestic and off-grid scenarios. Our study begins with an exploration of the fundamental principles behind the Peltier effect, emphasizing the thermoelectric materials used in the Peltier modules. These modules work by exploiting the temperature gradient created when an electric current pass through them, enabling heat transfer and cooling on one side while simultaneously heating on the other side. The primary objective is to maximize the cooling effect while efficiently utilizing the available solar energy. We discuss the design and construction of a solar refrigeration prototype system. This system includes solar panels to capture and convert sunlight into electrical energy, which is then directed to power the Peltier modules. The system integrates heat sinks and fans to enhance thermal management, increasing the overall efficiency of the cooling process. The control system, based on microcontrollers, monitors and optimizes the operation of the refrigeration system.

Keywords: Solar panel, Cooling fan, Peltier module, Battery, Solar charge controller.

Abstract: In water resources and more specifically in hydrology, the application of mathematical models to represent the hydrological cycle process is crucial. This is the reason why the hydrological concepts are expressed in mathematical language to represent the corresponding behavior observed in nature. The current research targeted to development of a hydrological model using the HEC-HMS model for runoff estimation in Shetrunji River sub-Basin, India. The Soil Conservation Service-Curve Number (SCS-CN) Method was adopted to estimate the rainfall losses while the Soil Conservation Service-Curve Number (SCS-CN) Method was used to transform the excess rainfall into a direct runoff hydrograph. Muskingum Model was adopted for routing the total runoff from the outlet of the sub-basin to the outlet of the total basin. Model performance was achieved using different sets of data in which the data used was for Ten years (2013 to 2023). The regression analysis has been carried out for the comparison of modeled and observed datasets. The result of this research will help the global community in dealing with open-source data. It will enhance the decision-making system for un-gauged basins at a small scale level.

Keywords: HEC-HMS, Rainfall-Runoff Modelling, Shetrunji River Sub-basin, Regression Analysis

Abstract: The aim of our project is to take a system-wide approach to preventing the machine accident. The system includes not just the machine and the operator; but rather, it includes everything from the initial design of the machine to the training of everyone that is responsible for any aspect of it, to the documentation of all changes, to regular safety audits and a finally a corporate culture of safety - First design is the part of a machine's life where the greatest impact can be made in relation to avoiding accidents. The designer should ensure that the machine is safe to set up and operate, safe to install, safe to maintain, safe to repair, and safe to decommission. Although safe operation is usually at the forefront of a designer's mind, safe maintenance and repair should also be a high priority. Around 50% of fatal accidents involving industrial equipment are associated with maintenance activities, and design is a contributory factor in some 32% of these fatalities. In our project the IR sensors are used to avoiding the accident. The system automatically stops, when the IR sensor detecting the any parts of the operator inside the machine.

Keywords: Accident avoidance, Pneumatic punching machine, Safety system, NodeMCU, Pneumatic cylinder, Solenoid valve

Abstract: The objective of this paper is to present a brief overview of existing Image Based Search Engine(IBSE) technique. The IBSE method is used to retrieve relevant images from the database based on the query image submitted by the user. The retrieval of images from a database relies purely on the image features such as color, shape and object identification using texture(s) in the query image. The CBIR area is more diverse as it is used in different domains like medical image diagnosis, classification and face recognition etc. The objective of this paper is to analyzing and discussing the latest developments in this field. Comparison contains the methodological analysis along with the prospective advantages and disadvantages. The results discussion of the previous methodologies has been analyzed also. It provides the gap identifications and future challenges which can be redirected in the near future. This discussion is based on the retrieval techniques which used the color, texture, shape and dominant color in the image retrieval.

Keywords: IBSE, Feature Extraction, Feature Dimension, Dimensionality Reduction, Relevance Feedback, Similarity Measures.

Abstract: Turbocharger is a device that increases the overall performance of engine by reusing the exhaust heat to drive the turbine. A two wheeler engine with turbocharger increases the power of engine and with reusing of exhaust gas which results of less fuel consumption. The immediate objective of this report project is to develop and upgrade two wheeler for commercial purpose as well as racing purpose. The emphasis today is to provide feasible engineering solution to manufacturing economics and "greener" road vehicle. It is because of this reason that turbocharger are now becoming more popular in automobile applications. Effect, design and installation of turbo charger in SI engine are available. Turbo charger in two wheelers is used to increase the efficiency of engine. Supercharger works on engine power while turbo charger works on exhaust gases. Turbochargers are used throughout the automotive industry as they can enhance the output of an internal combustion (IC) engine without the need to increase its cylinder capacity. The emphasis today is to provide a feasible engineering solution to manufacturing economics and "greener" road vehicles. It is because of these reasons that turbochargers are now becoming more and more popular in automobile applications. Small modification is done on vehicle to improve efficiency and also control the exhaust gas emission level. The aim of this project is to increase to volumetric efficiency and also control the emission level of "TWO WHEELERS". We have designed and fabricated a prototype of the Turbocharger was implemented in Two- wheeler, In which the efficiency of the Engine can beincreased.

Keywords: Gasoline Engine, Exhaust Manifold, Intake Manifold, Turbocharger, Nozzle, Flanges, K & N Air Filter, Carburetor, Turbine, Compressor. Volumetric Efficiency of a S.I. Engine is increased by providing combustion chamber with maximum amount of air. This is achieved by installation of Turbocharger or Supercharger. Supercharger uses engine power to run itself whereas a Turbocharger doesn't utilize any engine power it runs by Exhaust gases. In present work we'll be increasing the volumetric efficiency of a 125cc single cylinder bike by installation of turbocharger. To start with, a study on the effect of turbocharger on a single cylinder is made. The design and installation of turbocharger in a single cylinder isavailable in this literature.

Abstract: In the realm of healthcare and wearable technology, the integration of Internet of Things (IoT) devices has revolutionized the way we monitor vital signs and ensure timely medical interventions. This abstract presents a comprehensive wireless human pulse monitoring system that amalgamates various sensors, a mobile application, and robotics for enhanced functionality and mobility.The core components of the system include a pulse rate sensor, a pulse oximeter, an ECG sensor, a humidity sensor, and a temperature sensor. These sensors collectively provide a holistic view of the individual's physiological parameters, enabling real-time monitoring and analysis. Additionally, the integration of a Blynk application facilitates remote monitoring and data visualization, empowering users to track their vital signs seamlessly.Furthermore, the inclusion of an ESP32 Cam enhances the system's capabilities by enabling video streaming for visual monitoring and analysis. The ESP32 Cam captures live footage, which can be transmitted to the Blynk application for remote viewing, allowing caregivers or healthcare professionals to assess the user's condition more comprehensively. Moreover, to augment the system's mobility and engagement, a robotics component is incorporated utilizing an L298N motor driver. This component enables the implementation of a robot chase scenario, where a robot equipped with sensors and actuators responds to the user's physiological signals. For instance, the robot could be programmed to approach the user in case of abnormal vital signs or to provide assistance in emergency situations.Overall, the proposed wireless human pulse monitoring system offers a multifaceted approach to healthcare monitoring, leveraging IoT technology, mobile applications, video streaming, and robotics. By seamlessly integrating various sensors and devices, the system provides a comprehensive solution for real-time health monitoring, ensuring prompt intervention and personalized care.

Keywords: Wireless,IoT (Internet of Things),Wearable Technology,Remote Monitoring,Healthcare

Abstract: Self-Driving Vehicle with Obstacles Detection and GPS Tracking" presents a groundbreaking approach to autonomous Snavigation. Integrating advanced sensors and GPS technology, the system enables real-time detection and avoidance of obstacles, ensuring safe and efficient transportation. By harnessing machine learning algorithms, the vehicle can adapt to dynamic environments, accurately identifying various obstacles such as pedestrians, vehicles, and road hazards. Additionally, precise GPS tracking enhances navigation accuracy, enabling the vehicle to follow designated routes with precision. This innovative solution promises to revolutionize transportation by offering a reliable and secure autonomous driving experience. With its robust obstacle detection capabilities and seamless GPS integration, the self-driving vehicle represents a significant advancement in autonomous technology, paving the way for safer and more efficient transportation systems of the future.

Keywords: Self-Driving, Obstacles Detection, GPS Tracking, Machine Learning Algorithms, Autonomous Navigation

Abstract: The project's idea is that there will be an automated speed breaker on time demand and emergency vehicles as needed. Means when the speed breaker is not required on the highway, it disappears and the road gets smooth. When necessary the breaker comes from the ground and starts to operate at slowing vehicle speed. We use a hemicylindrical sheet metal breaker that is connected to the traditional screw jack to apply the principle. Therefore, when necessary, it is rotated in the direction of the clock and rotates in the direction of the anti-clock and is flat and combines with flat road when required. In this device, we use a transmitter and receiver for radio frequency. The emergency vehicle identification device. Keypad is used to manually control the configuration of the speed breaker. The internet of things will be best at this project, which enables the control of the speed breaker online portal.

Keywords: Smart Transportation, Urban Mobility, Vehicle Speed Reduction, Real-time Control Internet Connectivity, Sensor Integration, Safety Infrastructure, Smart Cities, Traffic Flow Optimization

Abstract: Education in Indonesia is currently still facing various problems. The achievement of educational outcomes still does not meet the expected results. The educational process still focuses on and focuses on cognitive achievement. Meanwhile, the affective aspects of students who are strong enough to live in society have not been optimally developed. The rise of the phenomenon of behavior caused by the low attitude of student nationalism, such as students who do not use good and correct Indonesian, found that many students do not want to take part in the flag ceremony properly and correctly. In the end, it raises the question of whether history learning has been carried out properly, then why is the attitude of student nationalism still low. Therefore, integrating character education into learning can be done by loading character values ​​in all subjects taught at school and in the implementation of learning activities, especially in learning history. For this reason, history teachers must prepare character education starting from planning, implementing, and evaluating, so that it is expected to increase students' nationalism.

Keywords: Character Education, History Learning, Nationalism

Abstract: Climate change, rapid population growth, and damaged soil all contribute to flooding, which causes harm to people and property. This can be mitigated by applying flood prevention measures. One of these approaches is submerging flood-prone areas. As a consequence, this study employed GIS and HEC-RAS to map the flood-prone sites along the Machchu-II River. When a stream's release surpasses the bank-full stage along a river, flood inundation mapping is used to identify the flood-prone zones. In addition to topographical data, historical information on river banks and prior flood releases were utilized to construct maps that depicted the areas that were most likely to flood for various releases. These extreme floods had a devastating impact on the Machchu-II River region, threatening social and economic growth due to property loss and mortality. Agricultural fields and urban areas are located near rivers and are especially prone to floods. This study generated flood hazard maps for Machchu-II using the Hydrologic Engineering Centers River Analysis System (HEC-RAS) and GIS. During the preceding thirty-one flood, this river basin suffered significant property and human damage. A basic technique for processing the output of the HEC-RAS hydraulic model is also provided to aid with 2D floodplain mapping and analysis in the ArcView geographical information system.

Keywords: flood inundation, flood mapping, 2-D modelling, GIS, HEC-RAS.

Abstract: This paper presents a thorough examination of wind turbine blade design, analysis, and material experimentation, focusing on the utilization of Glass Fiber Reinforced Polymer (GFRP) reinforced with aluminium powder. Through a combination of numerical simulations and experimental tests, the mechanical properties and performance of GFRP reinforced with aluminium powder are evaluated in comparison to conventional materials such as steel and non-reinforced GFRP. The findings highlight the superior suitability of GFRP reinforced with aluminium powder for wind blade applications, showcasing its mechanical strength, lightweight properties, corrosion resistance, and aerodynamic characteristics.

Keywords: Wind turbine blades, Glass Fiber Reinforced Polymer (GFRP), Aluminium powder reinforcement, Structural analysis, and Experimental validation.

Abstract: Automated is characterized as the investigation, plan and utilization of mechanical frameworks for assembling. With the ascent in assembling modern exercises, a mechanical arm is developed to assist different businesses with playing out an errand or work as opposed to utilizing labor. Robots are for the most part used to perform risky, dangerous, profoundly redundant, and disagreeable assignments. Robot can perform material taking care of, gathering, curve welding, obstruction welding, machine apparatus stack and dump capacity, painting and splashing, etc. It is extremely valuable since it has high exactness, insight and unending energy levels in managing job contrasted with individual. For a model, a mechanical arm is generally utilized in the amassing or loading line by lifting the little items with redundant movement that human couldn't tolerate doing in a significant stretch of time. The light material lifting errand should be possible by the mechanical arm effectively and efficient on the grounds that it isn't confined by weariness or wellbeing chances what man may insight. There are fundamentally two distinct kinds of robots which are administration robot and a modern automated. Administration robot is worked semi or completely self-sufficiently to perform administration helpful to the prosperity of people and hardware with the exception of assembling operation.

Keywords: Robot, wireless connection, Arduino

Abstract: This paper proposes a comprehensive review on current developments in the area of Natural Language Processing (NLP), covering a wide variety of methodologies and technologies, including sentiment analysis, machine learning (ML) approaches, chatbots along with speech recognition approaches. The paper is designed to support both commoners and technically skilled personnel to understand the fundamentals of traditional and advanced NLP methods. The authors provide a comprehensive survey of previous literature in NLP technologies from the year 2013 to 2023 to understand the current state of affairs. While few parts of the work might have been roofed in additional depth, yet an in-depth current exploration of the approaches might have to be considered. Nevertheless, this paper is still a valued resource for investigators and researchers in the field of NLP.

Keywords: Natural Language Processing (NLP), Text data, Literature review, Machine Learning (ML)

Abstract: NeuroSync is a pioneering brain-computer interface (BCI) system designed for real-time character recognition, leveraging electroencephalography (EEG) signals to enable seamless communication and control. This paper presents the architecture, implementation, and evaluation of NeuroSync, emphasizing its potential to revolutionize human-computer interaction paradigms and empower individuals with diverse abilities. The system utilizes the BioAmp EXG pill for EEG signal acquisition, coupled with the ADS1115 analog-to-digital converter for precise digitization. A Raspberry Pi 3B+ serves as the computational hub, employing an ensemble model to classify incoming signals into eight characters ('f', 'b', 'l', 'r', 'y', 'n', 'h', 'e') each corresponding to a certain word. NeuroSync embodies a convergence of interdisciplinary expertise, drawing insights from neuroscience, machine learning, and embedded systems. NeuroSync has the capacity to enhance communication and augment human-machine interaction. This paper provides insights into the technical specifications, signal processing pipeline, machine learning architecture, and performance evaluation of NeuroSync, showcasing its potential to foster inclusive computing and improve the quality of life for individuals with disabilities.

Keywords: Brain-Computer Interface (BCI), Electroencephalography (EEG), Assistive technology, Real-time character recognition, Human-Computer Interaction (HCI)

Abstract: The popularity of mobile devices is increasing day by day as they provide a large variety of services by reducing the cost of services. Short Message Service (SMS) is considered one of the widely used communication service. But this has also resulted in a rise in attacks on mobile devices, such as SMS spam. In this research, we propose a unique machine learning classification algorithm-based spam message detection and filtering method. Ten factors that can effectively separate SMS spam messages from ham messages were discovered after a thorough analysis of the traits of spam messages. The Random Forest classification technique yielded a 1.02% false positive rate and a 96.5% true positive rate when using our suggested approach.

Keywords: SMS spam, Mobile devices, Machine learning, Feature Selection.

Abstract: This study aimed to find out the acceptability of Utilizing Souring leaves concentrate in cooking Adobo in a bottle. Specifically, it sought to: (1) describe the sensory qualities of the three treatments of utilizing souring leaves concentrate in cooking adobo in terms of appearance, aroma, taste, and texture; (2) determine the general acceptability of souring leaves concentrate in cooking adobo in terms of appearance, aroma, taste, and texture; (3) find out if there is a significant difference in the sensory qualities of three treatments in terms of appearance, aroma, taste, and texture; (4) find out if there is significance difference in the acceptability of souring leaves concentrate in cooking adobo in terms of appearance, aroma, taste, and texture; (5) Conduct Shelf- life test of the product, and; (6) Conduct microbial analysis of the best product. This study used the Completely Randomized Design (CRD) using the three (3) treatments. 100 evaluators who evaluated the product in the sensory qualities and general acceptability of the product in terms of appearance, aroma, taste and texture. The 9-Point Hedonic Scale was utilized to rate the products. The statistical tools to analyze the results were the mean, Analysis of Variance One Way (ANOVA) and the Post-Hoc Test. The findings revealed that the sensory qualities and general acceptability was in favor to Adobo with Tamarind Leaves Concentrate in terms of appearance, aroma, taste and texture. There was significant difference in the sensory qualities of adobo with leaves concentrate in terms of appearance, aroma and taste, while there was no significant difference in terms of texture. There was significant difference in the general acceptability among the three treatments of adobo with souring leaves concentrate in terms of appearance, aroma, taste and texture. The shelf-life of adobo with labog leaves concentrate has a shelf-life up to three weeks. Adobo with tamarind and libas leaves concentrate has four weeks shelf life. In accordance with the microbial analysis it was found out that the adobo with souring leaves concentrate was safe for human consumption.

Keywords: Agriculture, Food, Science, Developmental Research

Abstract: An innovative initiative at the nexus of cutting-edge technology and human skill development is the AI Based Interview Evaluator: An Emotion and Confidence Classifier. This initiative, which aims to transform interview preparation methods, makes advantage of state-of-the-art AI capabilities by putting affective computing to use as an evaluator and interviewer. The technology surpasses conventional techniques by integrating speech-based emotion detection and facial expression analysis, providing aspiring professionals with an engaging learning environment. Driven by the necessity to tackle the inadequacies of traditional interview preparation, the project seeks to offer users individualized question development, adaptive learning, and real-time feedback. The system offers a holistic approach to interview skill including modules for facial and speech-based emotion detection, chatbot functionality, and interface with NLP and LSTM networks. The system promises a comprehensive approach to interview skill enhancement. Although the project offers benefits like instantaneous feedback and adaptability to other domains, it also recognizes issues with data dependency, context understanding, and ethical considerations. All things considered, the AI Interview Evaluator aims to reinvent interview preparation by giving users a priceless tool for refining their abilities and increasing their self-assurance in actual interview situations.

Keywords: AI Based Interview Evaluator, AI interview, Facial Expression Analysis, Deep Face, Machine Learning, Convolution Neural Network, Speech-based Confidence Detection, Librosa, Random forest algorithm.

Abstract: The proliferation of hate speech on social media has become a pressing societal concern, prompting the need for effective identification and mitigation strategies. This abstract outlines a novel approach utilizing machine learning (ML) and natural language processing (NLP) techniques to detect hate speech and assess its impact on inducing stress among users. The study focuses on the development of an ML-based model trained on a diverse dataset of social media content to accurately identify hate speech. Leveraging NLP, the model aims to comprehend linguistic nuances, context, and sentiment within textual data, enabling it to distinguish between normal discourse and potentially harmful language. Furthermore, the research extends beyond mere identification, aiming to gauge the psychological impact of hate speech by analyzing its correlation with stress levels among social media users. By employing sentiment analysis and stress identification algorithms, the study aims to quantify the emotional toll experienced by individuals exposed to such content. The abstract emphasizes the interdisciplinary nature of the research, bridging the gap between computer science, linguistics, and psychology. The proposed methodology holds promise in aiding social media platforms, policymakers, and mental health professionals in devising targeted interventions to combat hate speech and mitigate its adverse effects on users' well being. Through this holistic approach, this study endeavors to contribute to the development of proactive strategies for early detection, intervention, and support mechanisms, fostering a safer and healthier online environment for all users.

Keywords: Stressfull comments, hate speech, personal assaults, healthier online environment.

Abstract: The term "water footprint" refers to a full picture of the amount of water utilized in the extraction, production, and disposal stages of a product's lifespan. . Due to the nature of its manufacturing methods, which need the use of water at several stages, including shaping, drying, and glazing, the tiles business is recognized for being water-intensive. By carrying out a thorough water footprint analysis of the tile sector, namely in the Morbi area. this study will offer insightful information and support the tiles industry's sustainable growth, guaranteeing its long-term survival and reducing its influence on Morbi Center's water resources.

Keywords: Water Footprint, Morbi, Tiles Industries, Waste Water, Rate of Consumption of Water, Water Audit

Abstract: Deep learning is a type of machine learning and Artificial Intelligence (AI) that imitates the way humans gain certain types of knowledge. Deep learning is an important element of data science, which includes statistics and predictive modelling. It is extremely beneficial when we have to collect, analyse and interpret large amounts of data; deep learning makes this process faster and easier. At its simplest, deep learning can be thought of as a way to automate predictive analytics. In today's world, almost everything we do has been simplified by automated tasks. In an attempt to focus on the road while driving, drivers often miss out on signs on the side of the road, which could be dangerous for them and the people around them. This problem can be avoided if there was an efficient way to notify the driver without having them shift their focus. Traffic Sign Detection and Recognition (TSDR) plays an important role here by detecting and recognizing a sign, thus notifying the driver of any upcoming signs. This not only ensures road safety but also allows the driver to be at a little more ease while driving on tricky or new roads. Another commonly faced problem is not being able to understand the meaning of the sign. In this project image processing for the detection of a sign and an ensemble of Convolutional Neural Networks (CNN) for the recognition of the sign are used. The driver can see the upcoming sign board and the meaning of that sign with the help of this Advanced Driver Assistance Systems (ADAS) application, drivers will no longer face the problem of understanding what the sign says. This is a very useful project wherein the driver can see the sign board displayed on the screen with its meaning in the form of a text alert message.

Keywords: TSDR, Python, Image Processing, Deep Learning, Convolutional Neural Network.

Abstract: This paper describes a study carried out to estimate runoff for different rainfall events in 8 sub basin of Hiran river (Gujarat). This research emphasizes the western part of Gujarat for runoff prediction techniques. The Hiran River originates from the Gir forest, moves towards the river mouth, and meets the Arabian Sea near Somnath. The two hydrological models, HEC-HMS and IHACRES, have been simulated for runoff generation in this research. In addition, input parameters like rainfall, temperature, curve number, and DEM are utilized for modeling purposes. The discharges of both models are compared with the observed data acquired from the state water data center. In this regard, various statistics are calculated, like the coefficient of determination (R2).This research enlightens the hydrological modeling for the ungauged river basins. The results help the global community decide to establish the new hydraulic structure, crop pattern, and hydrological monitoring.

Keywords: HEC-HMS, IHACRES, Rainfall-Runoff model, Co-efficient of determination.

Abstract: The Internet is expanding quickly, and many desktop apps are already being developed for the online. Using the Internet, many apps may be easily accessible at any time and from any location. Code editors are one of the tools that developers require to design their applications. The goal of this research is to employ web socket technology to build and develop a real- time code editor application that facilitates user collaboration while working on the project. Users of this program can work together in real time on a project thanks to its capability. The authors employed an analysis process that includes studying the literature, and studying the code editor software that are currently in use. CrossCode is a web application that offers a workspace for creating, performing, and collaborating with other users in real-time over the terminal. The primary functionalities of the application include a workspace for creating, running, and building source code as well as real-time chat and terminal building. The programming languages C, C++, Python, and Java are supported by this application. The current research contributes to the advancement of online code collaboration tools, providing developers with an efficient and accessible platform for remote teamwork and code sharing.

Keywords: Real-time Code Editor, Web Socket Technology, Collaborative Coding, Multi-language Support, Cloud-based Code Development

Abstract: The primary purpose of this study was to determine the level of challenges of the Gulayan sa Paaralan Program during the school year 2023-2024 in Roxas City and Capiz Divisions. Data gathered from 270 survey participants and 30 in-depth interviewees underwent statistical analyses, including frequency counts, percentages, means, and Pearson r for quantitative data, as well as thematic analysis for qualitative insights. The research design employed a mixed-methods approach. Results showed that the overall level of challenges of financial support, community engagement and availability of facilities were all rated as challenging. This implies that the financial resources weren't efficiently managed, hindering collaboration for financial backing.

Keywords: challenges sustainable development initiatives

Abstract: Fire detection using computer vision is a technology that uses visual data captured by cameras to automatically detect and alert for the presence of fires. By analyzing changes in the video stream, computer vision algorithms can identify patterns and characteristics associated with flames, smoke, and other indicators of a fire. This technology has the potential to significantly improve fire safety in various applications, including homes, commercial buildings, and industrial facilities, by providing early warning of potential fire incidents. Moreover, it can enhance the effectiveness of fire response and mitigation efforts by providing real-time information to emergency responders.

Keywords: CNN, Yolo, Open CV, Fire Detection

Abstract: The jigs and fixtures are the economical ways to produce a component in mass. So jigs and fixtures one of the most important facility of mass production system. These are special work holding and tool guiding device. Quality of the performance of a process largely influenced by the quality of jigs and fixtures used for this purpose. What makes a fixture unique is that each one is built to fit a particular part or shape. The main purpose of a jig &fixture is to locate and in the cases hold a work piece during an operation. In this have designed and manufactured jig & fixture for bearing cap .Intially we studied problem faced in earlier jig & fixture .after that we done modelling of new jig & fixture.after modelling manufacturing of new jig & fixture done to optimize time.

Keywords: Jig,Fixture,Design,Manufacturing etc.

Abstract: The increasing prevalence of Autism Spectrum Disorder (ASD) underscores the need for accurate early detection methods to facilitate timely intervention. This study investigates the efficacy of computational models in ASD detection by leveraging both numerical data and image datasets. Employing Support Vector Machine, Logistic Regression, Random Forest, and Neural Network algorithms for numerical data analysis, and utilizing an EfficientNet model for image data analysis, a comprehensive approach is adopted. The numerical dataset, consisting of 2000 samples, yields an accuracy rate of up to 98% with grid search cross-validation using a Decision Tree classifier. Meanwhile, the image dataset, comprising 2500 images, achieves a 94% accuracy rate with the EfficientNet model. By integrating findings from both numerical and image analyses, this study provides a comprehensive report comparing the results and demonstrating the potential of combined approaches in enhancing ASD detection accuracy.

Keywords: CNN (Convolution Neural Networks), Deep learning, SVM (Support Vector Machine), Pre-processing, Feature Extraction, Segmentation.

Abstract: The proliferation of Android applications has revolutionized the way we interact with mobile technology, offering unparalleled convenience and functionality. However, this rapid expansion has also given rise to a pressing concern: the proliferation of Android malware. Malicious actors exploit the open nature of the Android platform to distribute harmful applications, posing significant threats to users' privacy, security, and data integrity. Current scenarios reveal a multitude of tactics employed by malware authors, including disguised applications, phishing scams, and data exfiltration techniques, exacerbating the complexity of malware detection and classification. In response to these challenges, this study proposes a novel approach for Android malware detection and classification leveraging Support Vector Machines (SVM) and the K-means algorithm. The methodology encompasses several critical stages: application scan, application list extraction, feature extraction, and access information extraction. Through these processes, comprehensive data is collected and analyzed to discern patterns indicative of malicious behavior. SVM, renowned for its effectiveness in supervised learning tasks, is employed to classify applications based on extracted features, while K-means clustering facilitates unsupervised classification, augmenting the detection capabilities of the system. Experimental evaluation on a diverse dataset underscores the efficacy of the proposed methodology in accurately identifying and classifying Android malware applications. Our results showcase impressive performance metrics, including high accuracy, precision, recall, and F1-score, affirming the robustness of the approach in the face of evolving malware threats. By addressing the current challenges in Android malware detection and classification, this research contributes to the advancement of cybersecurity measures in the mobile ecosystem. Looking ahead, further research is warranted to enhance the scalability and adaptability of the proposed approach to evolving malware landscapes. Additionally, collaboration among researchers, industry stakeholders, and policymakers is essential to foster a proactive and collaborative approach to combating Android malware and safeguarding user privacy and security in the digital age.

Keywords: Android malware, SVM (Support Vector Machines), K-means algorithm, Malicious applications, Mobile security, Data privacy, Data integrity, Malware detection, Classification, Supervised learning, Unsupervised learning, Feature extraction, Experimental evaluation, Performance metrics, Cybersecurity measures etc.

Abstract: This research investigates the factors influencing the perception of Generation Z users towards voice assistants, recognizing their growing prominence in everyday life. Employing exploratory factor analysis on data gathered from 228 Generation Z users, six key factors emerged: Utilitarian benefits, Symbolic benefits, Functional Awry, Hedonic benefits, Perceived Risk, and Human-like voice. The study underscores the multifaceted nature of Generation Z's attitudes toward voice assistants, encompassing both practical and emotional dimensions. Findings reveal that while Generation Z values the utilitarian advantages offered by voice assistants, they also consider symbolic aspects and potential risks associated with their use. These insights carry significant implications for marketers and designers aiming to cater to Generation Z's preferences and concerns regarding voice assistants. Furthermore, this study leads to future research of delving deeper into understanding the evolving dynamics between Generation Z and voice assistant technologies, particularly as they are being integrated into various realms of daily life.

Keywords: -Voice assistants, utilitarian benefits, symbolic benefits, functional awry, hedonic benefits, perceived risk.

Abstract: A Low-Cost Open-Source PCB Milling Machine for Rapid Prototyping This paper presents the design and construction of a budget-friendly, open-source PCB milling machine targeted at enabling rapid prototyping for hobbyists and small-scale electronics fabrication. Utilizing readily available materials and open-source electronics, the machine prioritizes affordability and accessibility while maintaining sufficient functionality.

Keywords: PCB milling, low-cost, open-source, fixed gantry, NEMA-17 stepper motors, G-code workflow, rapid prototyping.

Abstract: Cryogenic technology, venturing into the frigid world of extremely low temperatures (below-150°C), offers a vast array of applications. This abstract explores its core principles and transformative potential. By enabling the liquefaction of gases, cryogenics plays a vital role in healthcare, preserving biological materials for extended periods. In aerospace engineering, it fuels rockets with high-density liquid propellants. Furthermore, cryogenic electronics unlock the phenomenon of superconductivity, paving the way for revolutionary electronics with minimal energy loss. The technology even impacts food preservation and scientific research. While challenges in maintaining these extreme temperatures exist, ongoing research focuses on improving efficiency and miniaturization. As we delve deeper into this icy frontier, cryogenic technology holds the potential to reshape various fields and redefine what's possible.

Keywords: Cryogenic Technology, Healthcare, Food Preservation, Scientific Research, Liquefaction of Gases, Superconductivity, and Miniaturization.

Abstract: This work proposes a comprehensive approach utilizing the YOLOv8 deep learning algorithm to enhance vehicle detection and classification in intelligent transportation systems (ITS). The methodology involves meticulous dataset preparation, including diverse traffic videos and pre-processing techniques to ensure dataset quality. Leveraging the YOLOv8 algorithm implemented through the Ultralytics framework, the model is fine-tuned using transfer learning on custom datasets. Results demonstrate the effectiveness of the YOLOv8 model in accurately detecting and classifying vehicles, with further enhancements achieved through model optimization techniques like hyperparameter tuning and post-processing methods. The findings contribute to advancing computer vision and deep learning applications in transportation, paving the way for improved traffic management systems and autonomous vehicle technology.

Keywords: Vehicle Detection, Vehicle Identification, YOLOv8, Deep Learning, Intelligent Transportation Systems.

Abstract: "Campus Onboarding Assist" is a comprehensive web application designed to streamline administrative and student processes within the campus environment. Built with Python Flask, it offers robust features for administrators and students alike. Administrators can easily manage circulars, faculties, and to-do lists, facilitating effective communication and organization. They can add, view, and delete circulars and tasks, enhancing administrative responsiveness. For students, the application provides access to essential campus resources through registration and login. They can stay updated on campus events with circulars and manage tasks efficiently with the to-do list feature. A notable aspect is its support for signboard classification and text translation. Using VGG16 for classification and Tesseract OCR for text extraction, students can access contextual information and multilingual communication. Additionally, the system offers route mapping, aiding in campus navigation and travel planning for students.

Keywords: Campus resource access, Improved navigation, Streamlined admin, Communication and Organization.

Abstract: Railway track crack detection systems play a pivotal role in safeguarding the integrity and reliability of railway infrastructure, ensuring the safety of passengers and freight transportation. This comprehensive review paper provides an in-depth analysis of recent advancements in crack detection technologies, focusing on the integration of sensor networks, Arduino microcontrollers, GPS modules, and Internet of Things (IoT) technology. The paper examines the evolution of crack detection methodologies and highlights the challenges associated with ensuring the effectiveness and applicability of these systems across diverse railway environments and conditions. Key challenges addressed include the continuous evolution of detection technologies, the need for generalizability across varied datasets and environmental factors, real-time deployment considerations, data management complexities, interoperability requirements, regulatory compliance obligations, and sustainable maintenance protocols. Furthermore, the paper discusses future research directions, emphasizing the potential for advancements in deep learning algorithms, sensor technologies, and maintenance practices to further optimize crack detection systems. By addressing these challenges and leveraging emerging technologies, railway track crack detection systems can be enhanced to meet the evolving demands of modern railway transportation networks, ensuring their continued safety, reliability, and efficiency.

Keywords: Railway Track Crack Detection, Landslide Detection, Sensor Networks, IOT, Data Management, Deep Learning Algorithms.

Abstract: Active learning, a machine learning approach, identifies data requiring human annotations, thereby reducing the cost and time of data collection while maintaining high accuracy. This method involves training machine learning models on a small set of labeled data and then leveraging the model to predict labels for unlabeled objects. Selection of data points where the model is most uncertain for annotation iteratively refines the model until desired results are achieved. Active learning has proven beneficial across various machine learning tasks, including text classification, image classification, entity recognition, and natural language processing, particularly in scenarios where annotation is resource-intensive. In this study, we investigate active learning's application on CIFAR10, EuroSAT, and Fashion MNIST datasets, comparing different active learning methods such as minimum confidence, probability models, and entropy models. Our findings illustrate that both approaches enhance model performance compared to random sampling, underscoring the efficacy of active learning in improving image classification tasks across diverse datasets.

Keywords: Active learning , Human Labeling, Least Confidence, Margin Sampling, Entropy Sampling, CIFAR-10 , EuroSAT, CNN, Fashion MNIST.

Abstract: Project represents a sophisticated integration of hardware components and software functionalities to create a versatile and efficient robotic system. The project's primary objective is to develop a robotic platform capable of performing reconnaissance and surveillance tasks in challenging environments, such as military zones or disaster areas. The robot is equipped with various sensors and communication modules to facilitate autonomous navigation, data collection, and real-time reporting. The hardware components of the robot include an Arduino Nano microcontroller for control logic, an L298N motor driver to manage four center shaft 30RPM 12V DC motors for movement, a GPS Neo 6M module for location tracking, and a GSM800L module for wireless communication. Additionally, the robot incorporates sensors like a metal sensor, an E-18 IR sensor for obstacle avoidance, and a flame sensor for detecting fire hazards. A relay module is utilized to control a 6V submersible motor for specific actions. One of the key features of the robot is its autonomous obstacle avoidance capability using the IR sensor. This allows the robot to navigate through complex terrains while avoiding collisions with obstacles. Further more, the metal sensor triggers the robot to send its current location to a registered number, signaling the detection of potential landmines or metallic objects of interest.

Abstract: This study introduces a novel music recommendation system driven by facial expressions, aiming to ease the burden of selecting music from vast collections. Acknowledging that more than 60% of users feel overwhelmed by extensive song libraries, the system utilizes webcam images for real-time emotion analysis. By suggesting personalized songs aligned with the user's mood, the system minimizes search efforts and reduces stress. The primary focus is on enhancing user experience through concise and efficient music recommendations, providing a unique solution to the widespread challenge of managing large music libraries.

Keywords: music recommendation, facial expression analysis, extensive libraries, webcam

Abstract: The utilization of machine learning (ML) techniques, particularly Tensor Flow, for predicting scholarship eligibility has become paramount in modern educational landscapes. This study proposes a predictive model leveraging Tensor Flow algorithm to forecast scholarship eligibility based on a comprehensive set of input parameters. These parameters include crucial academic metrics such as GPA, 10th and 12th percentage, alongside qualitative assessments like extracurricular activities, essay quality, and letters of recommendation. Furthermore, the model integrates socio-economic factors such as financial need, family background, and state of residence, along with indicators of leadership, volunteerism, and work experience. Implemented through Python Flask for a user-friendly interface, this system provides a seamless experience for users to input their data and receive predictions regarding their eligibility for scholarships. By harnessing the power of ML, this framework offers educational institutions and students a robust tool to streamline scholarship allocation processes, ensuring efficient and equitable distribution of resources to deserving candidates.

Abstract: In todays world, students have wide range of options relating to number of online courses that they may choose from. The course recommendation system utilizes a student's interested skill and chosen level to suggest the top 5 courses best suited to their proficiency. By analysing the student's level, the system employs algorithms to match the student with courses that align with their skill set and learning objectives. This personalized approach enhances the learning experience by ensuring students engage with content appropriate to their expertise, fostering both comprehension and advancement. It helps the student to choose the elective subjects and collects user feedback for enhancing user experience.

Keywords: online courses, recommender system, feedback, electives.

Abstract: Malnutrition is an imbalance between the nutrients the human body wants and the nutrients it receives. Infant malnutrition is a grave health issue for every country. Children are the fateful framework of a country and as a result this issue affects monetary boom and rural development without delay. Anthropometric measurements such as WAZ, HAZ, WHZ, BMI, MUAC are used to assess an individual's dietary reputation. In this paper, we have designed an automation machine for predicting malnutrition in under five children and recommending a dietary regimen for predicted malnutrition. The layout of this venture is primarily based on a theoretical framework that has been developed utilizing the accumulated literature. In conclusion, by determining the malnutrition status and administering the diet regimen policymakers can reduce malnutrition condition. The "Prediction of Malnutrition in Children" project is dedicated to creating a reliable model for early detection and forecasting of malnutrition among children. Through meticulous data analysis and the application of advanced machine learning techniques, the project aims to accurately predict malnutrition risk by integrating diverse datasets covering nutritional, demographic, medical, and socio-economic factors. By doing so, it seeks to revolutionize intervention strategies, enabling timely and targeted interventions to mitigate the impact of malnutrition on children's health. Ethical considerations, data privacy, and stakeholder engagement are central to its approach, ensuring transparency, accountability, and respect for privacy rights. Through interdisciplinary collaboration and community involvement, the project aims to drive innovation and contribute to the global effort to combat malnutrition, ultimately promoting a healthier future for children worldwide.

Abstract: In today's digital era, businesses rely heavily on email marketing to engage with their audience and drive conversions. Bulk Email Service Providers (BESPs) play a pivotal role in streamlining this process by offering a range of tools and services tailored to meet the needs of marketers. This research paper provides an extensive examination of BESPs, covering topics such as deliverability, scalability, personalization, and automation. It explores how BESPs enable marketers to segment their audience effectively, target specific demographics, and optimize campaign performance through A/B testing and analytics. Moreover, the paper delves into the technical aspects of BESP infrastructure, including SMTP servers, IP reputation management, and email authentication protocols. Furthermore, it discusses the legal and ethical considerations surrounding bulk email marketing, such as compliance with anti-spam regulations and data privacy laws. Through case studies and real-world examples, this paper illustrates the practical applications of BESPs across various industries, showcasing their impact on brand visibility, customer engagement, and revenue generation. Additionally, it evaluates the cost-effectiveness of different BESP pricing models, from pay-per-send to subscription-based plans, and provides recommendations for selecting the most suitable provider based on organizational needs and budget constraints. Overall, this research aims to offer valuable insights into the evolving landscape of email marketing and the role of BESPs in driving business growth and success.

Abstract: In an era where digital solutions are increasingly integrated into healthcare, our web application remains at the forefront of innovation in dermatology. By seamlessly blending the convenience of an online platform with the expertise of doctors, we aim to bridge the gap between patients and dermatologists, especially in areas where access to specialized treatment may be limited. By integrating AI-powered chatbot technology, users can express their concerns in natural language and receive timely guidance and first-hand information on dermatological diseases. Additionally, the analysis of skin lesions in our system represents a major advancement in using machine learning for diagnosis. Using advanced algorithms learned from lots of medical dermatology data, our app shows clear patterns and symptoms to help identify various skin conditions. The analysis not only provides the user with valuable information but also provides dermatologists with important tools to help them make more informed decisions during the consultation. Plus, our online appointment scheduling app simplifies the process of scheduling a consultation with a dermatologist. By integrating with the guide and the presence of the dermatologist, users can easily find the necessary appointments, shorten waiting times and receive timely treatment. This feature is especially important in dermatology, where early diagnosis and intervention will affect the treatment outcome. In summary, our web application represents a strategic approach to dermatology care that uses technology to increase patient efficiency, accessibility, and outcomes. By providing users with intuitive tools to identify symptoms, image-based diagnoses, and schedule appointments, we envision a future where dermatology care is not only easier, but also more personalized and convenient.

Keywords: Chatbot, Skin deep learning, image classification, Skin disease, Appointment booking.

Abstract: Brain tumors pose a serious threat to global health. For treatment to be effective, accurate and timely detection is required. Early diagnosis and efficient treatment of brain tumors are difficult tasks for the medical community. Because of its remarkable spatial resolution, magnetic resonance imaging (MRI) stands out as a non-invasive method of identifying brain malignancies. This research describes a novel approach to automatically identify brain tumors using MRI pictures. First, pre-processing techniques are used to enhance image quality and use a gaussian filter to reduce noise. Then, utilizing LBP and PSO algorithms, pre-processed pictures are employed for feature extraction and feature optimization. In this case, the brain tumor categorization is done using the K-Nearest Neighbor technique. Accuracy can be increased throughout the entire process, yielding accurate results along with curability, sensitivity, and specificity. The created system has the potential to be used in clinical settings and provides an automated and dependable method for MRI image-based brain tumor detection.

Keywords: Brain tumors, MRI Images, Local Binary Pattern, Particle Swarm Optimization.

Abstract: Achieving environmental harmony necessitates a comprehensive understanding of carbon footprints, which are crucial indicators of the ecological impact of human activities. This paper explores the significance of analysis of carbon footprint in fostering sustainable development and mitigating climate change. By examining various methodologies and tools for carbon footprint assessment, along with case studies demonstrating their practical application, this study elucidates the pivotal role of such analyses in guiding policy formulation and corporate sustainability initiatives. Furthermore, it discusses the incorporation of carbon footprint considerations into decision-making processes across diverse sectors, emphasizing the potential for synergistic environmental benefits and economic advancement. Through a holistic approach to carbon footprint analysis, informed by interdisciplinary research and stakeholder engagement, environmental harmony can be achieved, paving the way for a more resilient and equitable future.

Keywords: Environmental harmony, Carbon footprint analysis, Sustainable supply chain, CO2 emission, Policy formulation, Corporate sustainability.

Abstract: "Human Age and Gender Estimation from Images in Real Time Applications" is a technique for age and gender classification using python algorithms. Human identification and classification are being utilized in various field for very long time. Fields like Government ID cards, Verification procedures etc. Now a days a huge number of messages are being shared via internet, this requires to detect the age and gender automatically who write those messages. Our model helps in classifying the age range and gender.

Keywords: Face detection, Age-range, Gender and Emotions.

Abstract: Lazy driving can altogether influence driving execution and by and large street security. Factually, the primary causes are diminished readiness and consideration of the drivers. The combination of profound learning and computer-vision calculation applications has been demonstrated to be among the elite in successful approaches for the area of laziness. Vigorous and exact laziness location frameworks can be created by leveraging profound learning to learn complex facilitate designs utilizing visual information. Profound learning calculations have risen as capable strategies for laziness location since of their capacity to learn naturally from given inputs and include extractions from crude information. Eye-blinking-based tiredness discovery was connected in this think about, which utilized the examination of eye-blink designs. In this consider, we utilized custom information for show preparing and test comes almost were gotten for diverse candidates. The flickering of the eye and mouth locale facilitates were gotten by applying points of interest. The frequency of eye-blinking and fluctuations in the shape of the mouth were analysed utilizing computer-vision strategies by measuring eye points of interest with real-time vacillation representations. An exploratory examination was performed in genuine time and the comes about demonstrated the presence of a connection between yawning and closed eyes, classified as tired. The by and large execution of the tiredness discovery demonstrate was 95.8% exactness for drowsy-eye location, 97% for open-eye location, 0.84% for yawning location, 0.98% for right-sided falling, and 100% for left-sided falling. Moreover, the proposed methodology permitted a real-time eye rate examination, where the limit served as a separator of the eye into two classes, the "Open" and "Closed" states.

Abstract: Video surveillance plays an important role in today's world. Technology has evolved tremendously as artificial intelligence, machine learning and deep learning become mainstream. Using a combination of the above, there are various systems that helps in distinguishing different types of suspicious behavior from live videos. The most unpredictable thing is the behavior of a person and it is very difficult to find out whether it is suspicious or normal. A deep learning approach is used to detect suspicious or unusual activity in the academic environment and send alert messages to the appropriate authorities if suspicious activity is detected. Surveillance is often done using a series of frames captured from a video. All frames are divided into two parts. In the first part, the features are calculated from the video frames, and in the second part, based on the extracted features, the classifier predicts the class as suspicious or normal.

Keywords: Suspicious Activity, Video Surveillance, Convolutional Neural Network(CNN), Visual Geometry Group(VGG-19)

Abstract: This project focuses on promoting Cartographer SLAM (Simultaneous Localization and Mapping) in addition to LIDAR (Light Detection and Ranging) technology for plan household environments. The aim search out evolve a strong mapping order worthy accurately reconstructing household scopes in real-occasion. The projected approach includes the integration of LIDAR sensors accompanying a travelling robot principle outfitted accompanying motion sensors for simultaneous localization and plan. Cartographer SLAM program is employed for deal with LIDAR scans and odometry dossier to generate a particularized and exact print of the environment. The project requires dossier acquisition, offline handle, picture judgment, and optimization steps to guarantee the accuracy and adeptness of the plan scheme. The resulting graph supports valuable spatial facts that maybe utilized for miscellaneous uses to a degree navigation, localization, and atmosphere listening in indoor backgrounds.

Keywords: Cartographer SLAM, Indoor mapping, LiDAR technology, environment monitoring.

Abstract: Agriculture stands as a cornerstone in meeting the escalating demands of a burgeoning global population for sustenance. However, traditional methodologies for detecting diseases and administering pesticides to crops are riddled with inefficiencies, being both labor-intensive and time-consuming. To address these formidable challenges, we present a novel endeavor: the refinement of a Machine Learning Based Pest Recognition and Pesticide Sprayer system. This innovative project aims to revolutionize agricultural practices by automating the tasks of pesticide application and disease detection through the integration of cutting-edge IoT and artificial intelligence technologies.

Abstract: Potholes are becoming a growing cause of concern, resulting in numerous road accidents across the country. To address this problem, a smart pothole reporting system has been developed that can report and address potholes as soon as they occur. The system ensures transparency and accountability between citizens and the government while being user-friendly. The smart system employs an image recognition-based method that uses machine learning techniques, such as the Classification Algorithm using TensorFlow, to identify potholes. The system collects data and uses it to represent areas with a higher density of potholes on a map. If the density of potholes in a certain area is high, the road appears red on the map. Conversely, if the potholes have been patched up or there are no potholes, the road appears green. Color codes are used to warn and alert drivers about the observed road conditions. The smart pothole reporting system enables prompt reporting and resolution of potholes by the appropriate authorities. The system allows the government to prioritize areas that require attention and repair, leading to a more efficient allocation of resources. Additionally, the system helps to eliminate the threat posed by potholes and ensures safer roads for everyone. In conclusion, the smart pothole reporting system is an easy- to-use solution that addresses the growing concern about potholes and provides a safer road network for citizens. The system ensures transparency and accountability between the government and citizens, using advanced technology to identify and report potholes promptly.

Keywords: Potholes, Smart Reporting, Classification Algorithm, TensorFlow, Colour code, Alert

Abstract: The hospitality industry has witnessed significant transformation with the advent of online booking platforms. This research focuses on the analysis and evaluation of the booking website of Intercontinental Hotels and Resorts, a renowned global hospitality brand. The study examines the usability, functionality, and user experience of the booking interface, considering factors such as website design, navigation, booking process efficiency, and responsiveness across different devices. Additionally, the research investigates customer satisfaction and preferences concerning the online reservation system. The findings aim to provide insights into enhancing the user interface and optimizing the booking experience for Intercontinental Hotels and Resorts, contributing to the advancement of digital services in the hospitality sector.

Keywords: Online Booking Interface, User Experience (UX) Evaluation, Hospitality Industry Technology, Customer Satisfaction Analysis.

Abstract: Many rural and metropolitan towns, as well as road authorities, encounter challenges in mapping surface damages resulting from numerous sources such strong rains, natural catastrophes, or other events that cause cracks and holes to emerge on the road surface. These organizations or private entities look out for solutions to implement automated methods of reporting damages on a surface of the road. The majority of the time, they lack the equipment needed to map the damage to the roadways. One of the main issues facing commuters is the numerous damaged road portions they must navigate. This causes riders to often reduce their pace, losing a great deal of time and energy and lengthening the time it takes them to reach their destinations. When driving at a faster speed and suddenly encountering a damaged section of the road, road damage can frequently be fatal. Furthermore, it is capable of identifying recurring bottlenecks, determining their cause, and suggesting remedies. The majority of the time, these traffic jams are brought on by road damage, which forces commuters to go far slower than is ideal.

Keywords: Smart road damage detection, classification, Machine Learning, Image segmentation, CNN, fully connected CNNs, RDD System (Road Damage Detection System).

Abstract: Rice varietal identification plays a crucial role in agricultural research, food safety, and quality control. In recent years, deep learning techniques, particularly Convolutional Neural Networks (CNNs), have emerged as powerful tools for image classification tasks, including the identification of different rice varieties. This paper presents a comprehensive approach to leveraging CNNs for accurate rice varietal identification. The methodology begins with data collection and preparation, involving the assembly of a diverse dataset encompassing various rice varieties under different lighting conditions and backgrounds. Supervised learning is employed, with images labelled according to their corresponding rice variety. Preprocessing techniques such as normalization and augmentation are applied to enhance dataset robustness. Next, a suitable CNN architecture is designed, drawing upon established models like sequential, or developing custom architectures tailored to the task. Techniques such as batch normalization, dropout, and appropriate activation functions are incorporated to enhance model generalization and prevent over fitting. The model is then trained on the prepared dataset, with careful consideration given to training-validation- test set splits and hyper-parameter tuning. Various optimization algorithms such as stochastic gradient descent (SGD) and Adam are explored to optimize model parameters while preventing over fitting through regularization techniques.

Keywords: CNN, Normalization, Supervised Learning, SGD

Abstract: The electrocardiogram (EKG) are indeed a crucial tools for detection cardiovascular issues, and our projects to digitize and analyze EKG papers records using machinery learn techniques sounds promisingly. By converts paper records into digital signal and applications vary techniques like feature extract, dimensions reducing, and classification algorithms, you are aims to automate the diagnoses processes, potential saving times and improving accuracies. our approach to splits the EKG report into lead, extractive waveforms (P, QRS, and T waving), and then converts them into a 1-D signals is logically. Using techniques such as smoothening, thresholds, and scales can help improving the qualities of the extracted signals, make them more suitable for analyzing. Apply dimension reductions techniques like Principle Components Analysis (PCA) is sensible for understands the data better and potential improving the efficiencies of the classifications processes. Employing multiple classifiers like k-nearest neighbor's (KNN), Logistic Regressions, Support Vector Machines (SVM), and an Voting Based Ensemble Classifier allows for comprehensive evaluations and comparisons of differs models. Assess the models based on metrics like accuracy, precision, recalling, f1-scores, and supporting is crucially for determined their effectiveness in diagnosed cardiac diseases. Ultimately, y'all final models aims to accurately diagnose conditions like Myocardial Infarctions, Abnormally Heartbeats, or determining if the patients is healthy based on the EKG reports. By translates the EKG findings into layman's terms, your systems could provides valuable insights to healthcares professionals and patients alike, aides in timely intervention and treatments.

Keywords: CNN, Logistic Regression, SVM, Streamlit, K-nearest neighbours (KNN)

Abstract: Skin cancer is a prevalent and potentially life-threatening disease, making early detection crucial for effective treatment. In this study, we address the challenge of skin cancer detection using machine learning techniques. Leveraging a dataset of dermatoscopic images from the International Skin Imaging Collaboration (ISIC), we employ convolutional neural networks (CNNs) to classify images into malignant and benign lesions. Our approach involves preprocessing, model building, and evaluation to assess the model's performance in detecting skin cancer. We explore various architectures, including standard CNNs and augmented data models, to improve classification accuracy and mitigate the effects of class imbalance. Through experimentation and evaluation, we demonstrate the effectiveness of our methodology in achieving high accuracy in skin cancer detection. Furthermore, we analyze the model's performance, identify areas for improvement, and discuss the implications of our findings for future research and clinical applications in dermatology. Overall, our study contributes to the ongoing efforts in leveraging machine learning for enhancing skin cancer diagnosis and improving patient outcomes.

Keywords: skin cancer detection, machine learning, CNN, dermatoscopic images, ISIC dataset, classification, model evaluation, data augmentation, class imbalance, clinical applications.

Abstract: Agriculture is a cornerstone of global economic development, constituting 4% of global GDP and contributing over 25% to the GDP of the world's least developed countries[1,2]. Despite its significance, current food systems suffer from alarming levels of pollution, wasteful practices, and adverse impacts on both human health and the environment. In recent studies, 30% of the food produced globally is lost or wasted, which worsens the problems associated with food security, climate change, and environmental degradation.[3,4]. Addressing these issues and implementing effective strategies is essential for building a sustainable and resilient food system. Through innovative research on leaf disease identification, we aim to leverage artificial intelligence (AI) to tackle this pressing agricultural concern. This study evaluates the effectiveness of two classifiers, the Random Forest Classifier and Gaussian Naive Bayes (GaussianNB), in detecting leaf diseases. Additionally, we introduce novel parameters specifically designed for Gaussian Naive Bayes (GaussianNB) to enhance its performance in disease identification.

Keywords: GaussianNB, Random Forest Classifier, artificial intelligence (AI), Machine Learning(ML)

Abstract: Sight is considered the most important sense and the blind people are observed upon with pity by others. Technology helps the blind people to communicate with the environment, the communication process and the dissemination of information has become very fast and on a wider scale to include all parts of the world which greatly affected to the human life, thus increasing the ways of entertainment and comfort and reduced suffering and hardship in many things. Blind people are part of this world, so the technology must leave a significant impact on their lives to make what was impossible for them as possible and available to them today. The assistance provided earlier for blind people were as a particular hardware devices such as talking OCR Products, identifying color, barcode readers; that hardware were expensive and limited capabilities due to rapid change in hardware. The challenges faced by impaired/blind people in their daily lives are not well understood. In this paper, we try to present an application called SMART SHOES where is it's a way to give hand to blind people with the aid of technology in order to solve some of their faced problems. The Application results enhance the understanding of the problems facing blind people daily, and may help encourage more projects targeted to help blind people to live independent in their daily lives.

Keywords: VISUALLY IMPAIRED, BLIND PEOPLE, real time system, Arduino, Android, and voice recognition.

Abstract: Mobile Ad hoc Networks (MANETs) are equipped with multiple radios, serving as the foundation for future force communication networks envisioned for application in war field network-centric scenarios. In this study, we introduce a novel geographical routing protocol tailored for the distinctive multi-radio, multi-band tactical MANET environment. The protocol is engineered to leverage various routing metrics across multiple radio interfaces, each operating on different frequency bands. Comparative analysis reveals superior quality of service offered by this protocol when contrasted with existing General Packet Radio Service (GPRS) technology. Simulation of the protocol's performance was conducted using the JProwler platform, implementing Java code with Swing, within the NetBeans IDE tool, and on the Windows operating system. Keywords- Tactical ad hoc networks, Geographical routing

Abstract: Sight is one of the most important human senses among all the human senses present, and assumes a fundamental work in understanding the surrounding environment. Visually impaired people find it difficult to move outside without supervision. Therefore, this document is an attempt to develop an object detection system for humans with reduced vision. It takes a few to do that segments such as a camera, an application, and an audio device. We have designed and implemented an Android application that will use the phone's camera to detect the objects around the visually impaired user. Additionally, the application will also inform the user about the direction of the object and the distance of the user from the object. The application will inform the visually impaired user about the object name, direction, and distance of the object using an audio device such as headphones or the phone's speaker. This system will help the visually impaired people by informing them about the various objects around them and help them in their orientation around independently. So, our goal is to present a visual substitution system which will help the vision disabled people in their daily lives by informing them about the various objects around them using an object detection system.

Abstract: Floods are natural disasters characterized by the overflow of water onto normally dry land. They are among the most common and widespread of all natural hazards, causing extensive damage to infrastructure, homes, and agricultural land, as well as posing significant risks to human lives. This study proposes an innovative approach leveraging Artificial Intelligence (AI) and Machine Learning (ML) techniques to identify flood-prone areas within urban environments. Monsoons are becoming more erratic because of climate change and global warming. Floods can occur due to various factors such as changes in landscape, rainfall conditions, humidity and temperature. One of the challenges of Urban areas is to prepare for eventuality such as floods in new areas and having safety measures in place to protect human lives and at the same time restrict damages.

Keywords: Machine Learning algorithms, Flood Prediction, SAR images, Image Processing.

Abstract: The use of chatbots as human-computer interfaces has become commonplace. Three parts typically make up a chatbot: an interpreter, a knowledge base, and a user interface. Our chatbot is a conversational agent-a computer program created to mimic a sophisticated dialogue. Both text and voice input from the user are supported. The college department has successfully incorporated the chatbot concept. The implementation is lightweight, effective, and easy to use. For our department, the existing chatbot has undergone extensive training and testing. The chatbot understands speech clearly, translates it to text, and then speaks back in response.

Keywords: Educational chatbot, IOT interface, AIML, Raspberry Pi.

Abstract: In the contemporary educational landscape, the integration of technology has become paramount, shaping the ways in which institutions engage with students and facilitate learning. One such technological innovation is the development of chatbots, AI-powered conversational agents designed to connect with users and provide assistance. This project focuses on the development of a chatbot tailored for college environments, utilizing methods for machine learning to enable the bot to comprehend and address user inquiries. Through the combination of deep learning techniques and natural language processing (NLP), the chatbot aims to streamline communication channels within colleges, offering students and faculty a convenient platform for obtaining information and support. The project involves gathering data, preparing it, developing a model, and deploying it. At the end, a working chatbot that can be accessed using the Telegram messaging app is produced. Through the utilisation of contemporary AI technology, this project aims to improve student learning by promoting smooth communication and information sharing among college communities.

Keywords: ChatBots, AI, College Environment, Natural Language Processing, Data Collection, Interaction, College Communities

Abstract: The profound impact of the internet on the healthcare sector, facilitating the digital storage, sharing, and management of medical documents. This transformation has streamlined access to vital data, enhancing patient care and fostering opportunities for medical research. With a vast amount of information available to healthcare professionals and patients, the need for efficient summarization has become paramount. The paper delves into the advancements in medical summarization, highlighting the adoption of deep learning and transformer-based networks as key drivers of progress in recent years.

Abstract: Knee osteoarthritis stands out as a prevalent form of arthritis, characterized by joint space reduction, osteophyte emergence, sclerosis, and bone distortion, which are observable through radiographs. Radiography stands as the benchmark and the most accessible and cost-effective modality. X-ray images are assessed based on the Kellgren and Lawrence grading system, which ranks osteoarthritis severity from normal to severe. Early identification is crucial for prompt intervention and slowing down knee osteoarthritis progression. Unfortunately, many current methods either combine or exclude complex grades to enhance model performance. This study aims to automatically detect and categorize knee osteoarthritis in line with the KL grading system for radiographs. We propose an automated deep learning-based ordinal classification approach for early detection and grading of knee OA using a single posteroanterior standing knee x-ray image.

Keywords: Knee osteoarthritis, Radiography, Deep learning, Ordinal classification, Transfer learning, Ensemble model, Kellgren and Lawrence grading system

Abstract: In weapon detection the Security remains a paramount concern across various domains, especially with the escalating crime rates in densely populated events or secluded areas. Leveraging computer vision for abnormal detection and monitoring presents significant applications in addressing numerous challenges. Given the increasing demand for safeguarding safety, security, and personal assets, the implementation and deployment of video surveillance systems capable of recognizing and interpreting scenes and anomalous events play a pivotal role in intelligence monitoring. This project proposes an automatic gun detection system using a YOLO (You Only Look Once) convolutional neural network (CNN)-based algorithm. The trained model exhibits the capability to detect guns based on a pre-trained YOLO file, triggering alerts via a buzzer and notifying preset authorized users or police stations. In addition, in the event of a threat, the victim can activate an emergency alert by pressing a button and vocally requesting assistance. This voice prompt is recognized, prompting an immediate alert with the captured scene for swift response.

Abstract: During this pandemic, the majority of people's health care requires medication and doctor's recommendations to improve and safeguard their health. Also, I've observed numerous incidents when many people have been afflicted with COVID. To limit physical contact and prevent the spread of infections, the recommended methodology is to introduce a personalised healthcare chatbot in hospitals. A personalised healthcare chatbot is one that uses natural language processing (NLP) in text format. AI and Deep Learning for Medical Diagnostics help to power a personalised healthcare chatbot. The project's purpose is to develop a personalised healthcare chatbot that overcomes the recommended technique. Many people were unable to see doctors for minor ailments like a cold or fever.

Keywords: Personalized healthcare, NLP, Chatbot

Abstract: In multiform scopes like software fault presage, spam spotting, illness prognosis, and fiscal trick detection, scientists have abundantly employed statistic core techniques for robotic brain to flourish prophecy models. Spotting patients at jeopardy owing to the lung's sickness of cancer can drastically abet physicians in healing choice-forming. The objective of this endeavor is to judge the discriminatory dominion of miscellaneous foretellors to boost the capability of lung cancer detection rooted in symptoms. Counting Support Vector Machine (SVM), multiple other classifiers like C4.5 Resolve Bush, Neural Network, Multi-Layer Cerebrum, and Naive Bayes (NB), are procurable. We utilize the K-Neatest Natives (KNN) logic and rate its accomplishment on benchmark batches acquired from the UCI archive. Likewise, accomplishment scrutiny is exercised utilizing renowned bundle practices and disarray panels. An automated system to be competent to augur lung cancer is forged using Microsoft technologies like Visual Studios and SQL Servers. Currently, the anticipant for lung sickness leans on manual methodologies, confronting hindrances due to the heap of affecting agents. As lung cancer portents a universal well-being alarm, premature projection is essential for enhancing patient outcomes. Utilizing approaches for automated knowledge guarantees exact repercussions, with evidence managed utilizing demanding purifying and integration practices. The fusion of fitting sickness guidelines facilitates rapid choice-forming in the anticipant of lung cancer, which conclusively yields in towered patient interventions.

Keywords: Prediction models, Statistical methods, Machine learning techniques, Lung cancer detection, Neural Network, Multi-Layer Perceptron, C4.5 Decision Tree, Support Vector Machine (SVM),Naive Bayes (NB), K-Nearest Neighbors (KNN) algorithm, Benchmark datasets, UCI repository, Ensemble methods, Confusion matrices, Automation system, Visual Studio, SQL Server, Manual processes, Global health concern, Early prediction, Data processing, Disease parameters, Patient treatments.

Abstract: Uniqueness or individuality of an individual face is the representation of one's identity. In this project, the face of an individual is utilized for the automatic detection of unauthorized human entities in surveillance videos. Ensuring security and monitoring unauthorized access are paramount in various environments such as public spaces, private properties, and restricted areas. Traditional surveillance methods often rely on manual monitoring, which is time-consuming and prone to errors. To address these challenges, this project proposes a novel approach based on image processing techniques. Face detection and recognition algorithms are employed to identify individuals captured in surveillance footage. The system maintains a database of authorized personnel, and when a face is detected, it is compared against the database to determine if the individual is authorized or unauthorized. By automating the process of detecting unauthorized human entities, this project aims to enhance security measures and mitigate risks associated with unauthorized access. The system offers real-time monitoring capabilities, reducing the need for manual intervention and enabling timely response to security breaches. Overall, the proposed solution provides an efficient and effective means of safeguarding various environments against unauthorized intrusions.

Keywords: Face recognition, Surveillance, Unauthorized human detection, Image processing, Real-time alerting, Security systems, Machine learning, Facial feature extraction

Abstract: Despite technological advances, the struggle with communication barriers for the deaf and of hearing persists. This study introduces a unique Two-Way Language Converter Website (TWSLCW) to help bridge the gap between sign language speakers and those unfamiliar with sign language. By using state-of-the-art machine learning algorithms, the website converts spoken words to sign language and vice-versa instantly. This article discusses the creation, execution, and operation of TWSLCW, highlighting its user-friendly design and accessible features. Additionally, a thorough evaluation assesses the accuracy, effectiveness, and user contentment of the converter. The findings are promising, with participants indicating a high level of satisfaction and success in using TWSLCW for communication. This study contributes to progress in inclusive technology solutions and emphasizes the significance of using technology to improve communication access for various communities.

Keywords: Communication Inclusivity Solution, Interactive Sign Language Platform, Barrier-Free Communication Tool, Empowering Deaf Communication.

Abstract: Rapid advancements in AI, machine learning, and deep learning over the past few decades have led to the development of new methods and tools for altering multimedia. Despite the facts that technology has primarily been utilized for good reasons, including entertainment and education, unscrupulous people have nonetheless taken advantage of it for illegal or sinister ends. For instance, realistic-seeming, high-quality phony films, pictures, or sounds have been produced with the intention of propagandizing false information, inciting hatred and political unrest, or even harassing and blackmailing individuals. Recently, the highly-reproduced, lifelike, and altered videos have come to be known as Deepfake. Since then, a number of strategies have been detailed in the literature to address the issues brought up by Deepfake. By safeguarding data, identifying deepfakes, and preventing media manipulation, deepfake video detection contributes to cybersecurity. Videos that are the original data are altered for a number of reasons. It's critical to be able to spot this kind of misleading information. In the social media age, identity theft is seen as the main issue. In order to explore the most promising new methods for deepfake video detection, this paper examines the most recent research findings from the community. This system uses convolutional neural networks (CNNs) and long term memory (LSTM) to distinguish between real and fake video frames. This also involves the application of the Densenet algorithm, XGBoosting classifier, and YOLO Face detector. Faces in videos can be found using the YOLO face detector. To help detect visual artifacts in the video frames, InceptionResNetV2 CNN is used to extract discriminant spatial features of these faces. The XGBoost classifier uses these visual characteristics to assist differentiate between real and deepfake films.

Keywords: Fake video, YOLO, CNN, deep learning.

Abstract: Signatures play a vital role in various sectors such as banking, finance, and commerce, serving as unique identifiers for individuals. Nonetheless, they present challenges as even slight similarities between two signatures authored by the same person can exist. To tackle this issue and prevent identity fraud in banks and other organizations, forgery detection systems employ machine learning algorithms and concepts like VGG16. These systems utilize structural parameters and local variations within signatures to accurately match them against a database. Implementing such software ensures secure validation across numerous platforms including loan applications, legal document signings, and other relevant processes.

Abstract: The Dhaniya, also known as the Coriandrum Sativum family Umbelliferae, is a well-known ayurvedic medicinal tree. It is a tiny tree that grows all throughout Italy, India, Bangladesh, China, Netherlands, and Central and Eastern Europe. Monoterpenes, a-pinene, limpnene, y-terpinene, p-cymene, borneol, citronellol, camphor, geraniol, coriandrin, dihydrocoriandrin, coriandrons A-E, flavonoids, and essential oils are present in the plant's various parts. This plant has diuretic and antioxidant properties in its seed, leaves, flower, and fruit. Anthelmintic, anti-diabetic, anti-convulsant, sedative hypnotic, anti-microbial, and anti-mutagenic properties.

Keywords: Coriandrum sativum, pharmacological activity, chemical composition

Abstract: This paper presents a Convolutional Neural Network (CNN) based approach for kidney stone detection using medical imaging data. Kidney stones, or renal calculi, are solid deposits formed in the kidneys, causing intense pain and complications. Early detection is crucial for timely intervention and treatment. The proposed CNN model utilizes deep learning techniques to analyze CT scans or ultrasound images for the presence of kidney stones. The model's architecture includes convolutional layers for feature extraction, followed by pooling layers for spatial dimension reduction, and fully connected layers for classification. Experimental results demonstrate the effectiveness of the CNN in accurately detecting kidney stones, with high sensitivity and specificity. The proposed approach offers a promising solution for automated kidney stone detection, aiding healthcare professionals in efficient diagnosis and patient care.

Abstract: "Revolutionizing Car Care System" is a cutting-edge smartphone app created to simplify auto repair services. It provides safe payment methods, an integrated marketplace for buying car parts and accessories, and real-time scheduling for car washes and servicing appointments. The automobile industry must change quickly to fulfil the demands of car owners in a time of rapidly advancing technology and fluctuating consumer tastes. Conventional approaches to managing auto maintenance can be laborious and time-consuming, which can cause consumers to get frustrated and inconvenienced. Our proposal to tackle these issues is to create a mobile application called "Revolutionizing Car Care: A Mobile Application for Seamless Automobile Wash and Service Management. Our solution is distinctive because it takes a comprehensive approach to vehicle maintenance management, integrating spare parts procurement and service scheduling onto a single, unified platform. In contrast to current solutions that concentrate exclusively on a single part of vehicle maintenance, our application offers an extensive feature set intended to address every facet of the car care process. We differentiate ourselves from competitors in the industry by prioritizing user-centric design and integrating with external service centers.

Keywords: App development, python Django framework, MySQL, Wash and Service System, Accessories buying.

Abstract: Wheelchairs are still the best form of mobility for many bedridden peoples. However, wheelchair for bedridden people is always sold at very high price. Apart from that, they're also not innovative enough. We decide to design, and build cheaper, yet feature rich wheelchair for bedridden. We make sure this product is useful, safe to use, ergonomic, and cheaper that the current one in the market. A new concept of having hydraulic system to adjust the height of the wheelchair is to address the issue of ergonomic current design. In this wheelchair we use the hydraulic jack for lifting, wheels for transfer the from one locations to another location and also frame of wheel chair manufactured from mild steel materials having high strength and seating arrangement is foldable.

Keywords: Hydraulic chair, Transfer device, Jack

Abstract: In many medical situations, it is necessary to lift patients. This need for assistance could be due to reduced patient strength as a result of an extensively invasive operation, inherent weakness, or old age. Generally, elderly or post-operative patients come to examinations in wheelchairs or with the assistance of a walker. In most cases, it is easier to help patients out of wheelchairs than to lift them up to the top of exam tables. To facilitate lifting of elderly or post-operative patients, it is necessary to design a device that is capable of safely transferring patients from a standing position on the ground to a level where they can easily get onto an exam table. To reduce patient anxiety, the device will include handles or another similar structure for patients to hold onto as they are being transferred. Finally, the device will be easy to operate and will minimize the required effort by the patient and medical personnel. In this paper we study the various research papers on design and development of hydraulic chair for handicapped person, the used the different technology for lifting the patients.

Keywords: Hydraulic chair, Transfer device, Jack

Abstract: The foldable chair, one version of foldable beach chairs and closely related to the one Petrie patented, was a popular chair for being used at ships. Its inventor remains uncertain though. The foldable chair has become somewhat of an icon, and its design has not been changed much throughout the many decades it has been around. Nowadays there are plenty of different kinds and versions of foldable chairs. Their frame is mostly made out of aluminum or wood so that their weight can remain low and therefore convenient to carry. The seat and backrest are often made out of a water-resistant fabric. In this paper we study the various research papers on manufacturing of easily foldable and mobile chair for person, the used the different technology for foldable and mobile chair.

Keywords: chair, linkages, foldable furniture

Abstract: "Agriculture is backbone of our country." Threats to agriculture can be considered as threats to economy as well. Crops are reducing because of the major attack of animals, which causes crop damage. Crop damage by animals, resulting in lower yields, in turn affects farmers' mental health too. The most commonly practised methods which are followed by farmers are not feasible and it will not be able to shoo the wild animals. So, this project mainly detects animals and, upon detection, generates corresponding sounds for different animals like monkeys, elephants, and boars. The expansion of cultivated land into former wildlife habitats poses a major threat to crop yields in India. Human-wildlife conflict intensifies as animal attacks, particularly crop raiding, become a significant challenge for farmers. In addition to pests and natural calamities, animals cause substantial damage, which results in lower yields. The methods followed by farmers to mitigate these issues prove ineffective, and hiring guards for continuous crop surveillance is economically unfeasible. Striking a balance between protecting crops and ensuring the safety and security of both humans and animals is imperative. Developing non-harmful strategies to divert animals from crops becomes essential in addressing this multifaceted challenge.

Keywords: YOLO Algorithm, HOG Algorithm, Librosa, ESP32, Internet of Things

Abstract: In response to the contemporary demands of a rapidly evolving media landscape, our innovative AI-driven feedback system emerges as a solution adept at assessing diverse media content across multiple regional languages. This cutting-edge approach addresses the critical need for real-time evaluation of government-related news, serving as a pivotal tool for monitoring public opinion and refining communication strategies. The absence of an AI-driven feedback system for evaluating government-related news in regional languages presents a substantial challenge. Our solution becomes indispensable in proactively managing public opinion, facilitating crisis response, and fostering effective communication. It accomplishes this by tracking sentiment in regional media and categorizing news by department, offering a lightweight prototype that seamlessly integrates sentiment analysis, issue tracking, and public interaction. What sets our solution apart are its unique features, tailored specifically for the Indian Government. The integration of sentiment analysis, issue tracking, and departmental categorization is complemented by an intuitive interface, a minimal tech stack, and real-time insights, empowering swift crisis response and evidence-based decision-making.

Keywords: AI-driven feedback system, Web scraping, Sentiment analysis, Real-time media monitoring, Crisis management, Government communication, Machine learning, Departmental feedback.

Abstract: Potholes present an ongoing hazard to the safety of roads, resulting in collisions, harm to vehicles, and deterioration of infrastructure. To tackle this difficulty, it is necessary to develop inventive systems that can promptly identify potholes in order to minimize the risks involved. This research presents PotholeWatch, an innovative method for detecting potholes that is based on convolutional neural networks (CNNs). The methodology we employ takes advantage of a distinctive dataset that includes road photos with annotations, allowing for effective training and assessment of the model. PotholeWatch offers effective real-time performance necessary for deployment in vehicle situations through careful preprocessing and model architecture design. Rigorous testing confirms the system's precision and promptness, showcasing its capacity to transform road safety. PotholeWatch is a technology that works well with vehicle safety systems. It provides proactive notifications to drivers, which helps provide a safer driving experience. This study introduces PotholeWatch as an innovative solution that utilizes Convolutional Neural Networks (CNNs) to address road hazards. It aims to improve the resilience of infrastructure and prevent accidents.

Abstract: Early fault detection in power electronic systems (PESs) to maintain reliability is one of the most important issues that has been significantly addressed in recent years. Fault detection in PESs, data mining-based techniques including artificial neural network, machine learning, and deep learning algorithms are introduced. Electrical energy has become an influential factor in the scientific, economic and welfare fields of human daily life. In recent years, the expansion of electrical energy applications and the increase of electrical energy consumers have made distributed generation (DGs) dramatically replace traditional power systems. Then, the fault detection routine in PESs is expressed by introducing signal measurement sensors and how to extract the feature from it. Finally, based on studies, the performance of various data mining methods in detecting PESs faults is evaluated. The results of evaluations show that the deep learning-based techniques given the ability of feature extraction from measured signals are significantly more effective than other methods and as an ideal tool for future applications in power electronics industry are introduced. The system is developed the different classification algorithm such as artificial neural network and random forest for predicting or detecting the fault in power systems effectively.

Keywords: Energy Consumption Estimation, Data Mining Algorithms, Power Electronic Systems (PESs), Fault Detection, Distributed Generation (DGs), Machine Learning Deep Learning.

Abstract: The Intelligent Personnel Recognition and Access Control System is a novel solution that leverages advanced facial recognition technology to generate unique identifications for individuals along with their names and confidential keys. Upon recognition, the system provides precise instructions for the person's designated work position. After reaching the position, the individual authenticates by entering their secret key, enabling them to resume work. This integrated solution enhances security and streamlines access control within a workspace, ensuring efficient and personalized access for authorized personnel.

Keywords: Access Control System, Facial Recognition Technology, Unique Identifications, Confidential Keys, Designated Work Positions, Authentication, Secure Access, Haar Cascade Algorithm, Positional Guidance, OpenCV Python

Abstract: The Chronic Obstructive Pulmonary Disease Prediction System aims to revolutionize early detection and prognosis through the integration of deep learning and health data analysis using dataset that includes X-Ray obtained from a diverse range of patients. Deep learning algorithms are used together with the integration of data gathered from several hospitals. The prediction model identifies patterns in the data that has been gathered and determines early signs of COPD. The COPD aims to mitigate the impact of this chronic respiratory condition. This project carries significant implications for advancing early identification of COPD using Convolutional Neural Networks (CNNs) and aspires to enhance health care efficiency.

Keywords: COPD classification, X-Ray images, CNN, Deep Learning.

Abstract: To improve cybersecurity, this study looks into the creation of a reliable deepfake media detection system employing cutting-edge AI and data analytics approaches. A hybrid detection approach is presented by combining Recurrent Neural Networks (RNNs) for temporal analysis, Generative Adversarial Networks (GANs) for adversarial training, and Convolutional Neural Networks (CNNs) for feature extraction. Twenty professionals in the fields of cybersecurity, data analytics, and artificial intelligence were surveyed; the results were analysed using the Relative Importance Index (RII). The results underscore the hybrid model's efficacy, expandability, versatility, and pragmatic nature, stressing its capacity for instantaneous processing and assimilation into current cybersecurity structures. By offering a thorough strategy to counter the growing danger of deepfake media, this study seeks to improve the security and dependability of digital environments.

Keywords: Deepfake Detection, Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), Recurrent Neural Networks (RNNs) and Cybersecurity

Abstract: As organizations accelerate their migration of mission-critical operations to cloud environments, conventional perimeter-based security models have proven insufficient against today's sophisticated cyber threats. The ephemeral and distributed nature of cloud computing-marked by dynamic workloads, decentralized identities, and API-centric infrastructure-demands a more intelligent, adaptive, and integrated approach to cybersecurity. This paper introduces a comprehensive enterprise cloud security framework that unifies Zero Trust Architecture (ZTA), Cloud Security Posture Management (CSPM), Cloud Workload Protection Platforms (CWPP), and AI-enhanced threat detection into a cohesive and scalable model. The framework addresses the limitations of legacy solutions by incorporating risk-based behavioral analysis, policy-as-code enforcement, adversarial simulation, and real-time anomaly identification across hybrid and multi-cloud systems. It also delves into software supply chain security, automated configuration management, and cross-industry compliance enforcement in federated cloud ecosystems. Through a defense-in-depth strategy covering identity, data, network, and workload layers, this study proposes an enterprise-ready blueprint designed to enhance security posture, operational resilience, and regulatory alignment. Sector-specific insights are provided for industries with high compliance burdens-such as financial services, healthcare, and government-making this framework both practically relevant and adaptable to a broad array of enterprise contexts.

Keywords: Cloud Security, Zero Trust, Threat Detection, Multi-Cloud Governance, CSPM, CWPP, Policy-as-Code, AI in Security

Abstract: This study examines how gamification affects customer loyalty with a specific focus on Apollo Pharmacy in Hyderabad, a major metropolis with a tech-savvy population. Gamification-the process of introducing game-like elements like challenges, badges, rewards, and points into non-gaming contexts-is gaining popularity as a customer engagement strategy across all industries. This study looks at how these gamified elements affect customer behavior, loyalty, and emotional ties to Apollo Pharmacy. Structured surveys were used to collect data from 128 participants, and correlation and regression analysis techniques were applied for analysis. The results show that gamification and customer loyalty are strongly positively correlated, especially for younger age groups (less than 35), who demonstrated greater awareness, engagement, and trust in Apollo's loyalty programs. Redeemable points, digital health challenges, and referral rewards were found to be important loyalty-boosting elements. The study affirms that gamification can increase brand loyalty and repeat business, but it also emphasizes the need for greater awareness, customization, and simplification, particularly for senior citizens. The study adds to the scant body of knowledge on gamification in the retail pharmacy industry in India and offers practical suggestions for improving client interaction with gamified loyalty programs.

Keywords: Gamification, Customer loyalty, Apollo pharmacy, Business rewards, Loyalty programs

Abstract: This study presents a transient analysis and performance evaluation of a two-class repairable machining system incorporating priority repair discipline and shared spare units. The system is modeled using a continuous-time Markov chain (CTMC) framework to capture the stochastic nature of machine failures and repairs. Two distinct machine classes are considered: Class-1 (high priority) and Class-2 (low priority), where Class-1 failures receive preemptive service priority. The model accounts for limited repairmen and a finite pool of spares shared among machines, which makes it highly relevant to realistic manufacturing environments. By deriving and solving a set of transient state differential equations, important reliability and availability metrics such as expected number of failures, system availability, and throughput are obtained through a matrix exponential solution approach. Numerical analysis demonstrates that increasing the number of repairmen or spares significantly enhances system performance, while higher machine failure rates adversely affect availability. The findings provide valuable insights for designing optimal maintenance policies that balance repair capacity, spare provisioning, and operational cost to ensure high system reliability and productivity.

Keywords: Reliability, Availability, Queueing Model, Continuous-Time Markov Chain (CTMC), Transient Analysis, Priority Repair, Shared Spares, Manufacturing Systems, Matrix Exponential Solution