VOLUME 11, ISSUE 3, MARCH 2024

Abstract: Computational Fluid Dynamics (CFD) is revolutionizing the oil and gas industry by offering powerful insights and innovative solutions. This paper explores the cutting-edge applications of CFD in enhancing and innovating within the sector. CFD simulations provide engineers with invaluable insights into fluid behavior, enabling optimized designs and informed decision-making. The software facilitates foresight by predicting system performance, optimizing drilling techniques, and maximizing reservoir management strategies. Furthermore, CFD optimizes equipment design, increases operational efficiency, and reduces costs through virtual testing, eliminating the need for costly physical prototypes. The application of CFD aligns with the United Nations Sustainable Development Goals (SDGs), promoting energy efficiency, climate action, responsible production, and sustainable consumption. It addresses flow assurance challenges, enhances safety protocols, and mitigates environmental impacts. CFD is a powerful tool driving innovation, resilience, and sustainability within the oil and gas industry, ensuring a more efficient, safe, and environmentally conscious future. As advancements in CFD methodologies continue, the potential for further enhancements and breakthroughs within the sector becomes even more promising, driving the industry towards a sustainable and prosperous future.

Keywords: CFD, Application, Oil and Gas, Sector, SDGs. Optimizing

Abstract: The research explores the challenge of identifying fake reviews, utilizing machine learning and natural language processing. It examines diverse methodologies, including deep learning and linguistic analysis. Categories of deceptive reviews are scrutinized, such as those from competitors or employees. The study addresses associated costs for businesses and impacts on consumer trust. Challenges like natural language mimicry and skilled deception are acknowledged. It emphasizes the necessity for advanced strategies to combat fraudulent reviews effectively, aiming to bolster trust and accuracy in the digital realm.

Keywords: Fake product reviews, Deceptive reviews, Fraudulent reviews, Machine learning, Natural language processing, Deep learning models.

Abstract: The Slope stabilization is an important aspect of civil engineering, geotechnical engineering, and environmental engineering, as it helps to ensure the safety and stability of structures built on or near slopes, as well as protect the natural environment from damage caused by landslides and erosion. Slope stability is a measure of how resistant a natural or man-made slope is to failure due to collapse or sliding. Slope stabilization refers to any implemented technique that aims to stabilize an unstable or inadequately stable slope. The purpose of slope stabilization techniques is to increase the Factor of Safety of a slope to a level that is considered adequate. The important geotechnical properties affecting stability of a slope are shear strength of material, particle size distribution, density, permeability, moisture content, plasticity and angle of repose.

Keywords: Slope Stabilization, Shear Strength, Permeability, Stabilization Technique.

Abstract: In the foreseeable future, the widespread adoption of artificial intelligence (AI) is anticipated to bring about a revolutionary transformation, impacting not only the economy but also society on a broad scale. The application of AI technology has the potential to automate hazardous and labor-intensive human occupations, thereby enhancing the overall quality of life. While the successful implementation of this technology promises significant benefits, it is imperative to address inherent challenges and concerns before its widespread utilization. This research examines the potential risks and apprehensions associated with AI, particularly in the domains of privacy, security, and discrimination. The authors advocate for the adoption of proactive measures, including thorough investigations, the establishment of regulations, and vigilant oversight. The study delves into the future trajectory of artificial intelligence, exploring both optimistic aspirations and legitimate concerns. In the contemporary landscape, hackers leverage a diverse array of AI-driven techniques to pose threats to governments, businesses, and individuals. The existing cyber defense mechanisms prove insufficient against these sophisticated cyber weapons. The incorporation of artificial intelligence into the realm of cybersecurity holds the potential to either elevate or diminish the current state of cyber security. This research aims to investigate how AI contributes to the defense against cyber attacks in the IT sector, with the overarching goal of enhancing cybersecurity. The significance of this study lies in its provision of tangible evidence regarding the positive impact of artificial intelligence technology on IT personnel, particularly in the context of implementing preventive measures against cyber attacks

Keywords: Artificial intelligence, Cyber Security, IT sector, Hackers, cyber attacks, privacy, security

Abstract: The objective of this project is to control the trolley for industrial applications using remote through IOT section. So we can control the robot for a certain distance. It is operated by motor and keypad. In industries time saving is the major need. To fulfill this need in industries here is a solution with the help of trolley. It is used to carry the material from one place to another place.

Keywords: IOT, smart industrial trolley.

Abstract: The integration of Artificial Intelligence (AI) with advanced technologies has significantly enhanced safety measures in various domains, including transportation. In this project, we propose an innovative AI-based automatic fire extinguisher system designed specifically for vehicles. This system employs Arduino Uno microcontroller, GSM module, GPS, and fire sensors to detect and mitigate fire incidents effectively. The primary objective of this system is to detect fire outbreaks in vehicles at an early stage and promptly initiate fire extinguishing procedures to minimize damage and ensure passenger safety. The integration of AI algorithms enhances the system's capability to accurately identify fire hazards while minimizing false alarms. The system utilizes fire sensors strategically installed within the vehicle's compartments to continuously monitor the surrounding environment for any signs of fire. Upon detecting abnormal temperature rise or smoke indicative of a fire outbreak, the sensors trigger the Arduino Uno microcontroller. The Arduino Uno, functioning as the central processing unit, employs AI algorithms to analyze sensor data and determine the severity of the fire. Based on the analysis, the system activates the appropriate response mechanisms to address the situation effectively. In case of a confirmed fire incident, the system initiates the deployment of the onboard fire extinguisher. The AI algorithms optimize the extinguisher's deployment by considering factors such as fire location, intensity, and vehicle occupants' safety. Additionally, the system utilizes the GPS module to transmit the vehicle's location to emergency services, facilitating swift response and assistance. Furthermore, the integration of the GSM module enables real-time communication capabilities, allowing the system to send alerts and notifications to relevant stakeholders, including vehicle owners, emergency contacts, and authorities. This ensures timely intervention and coordinated efforts to mitigate the fire incident.

Keywords: IOT, smart industrial trolley.

Abstract: This explores innovative and integrated strategies for water conservation in urban settings. The study addresses the escalating challenges of water scarcity and outlines a comprehensive framework encompassing technological, policy, and behavioural interventions. Through a multidisciplinary approach, the paper aims to provide practical insights and solutions to foster sustainable water management practices, emphasizing the crucial role of technology and community engagement in achieving long-term water conservation goals.

Keywords: water conservation, urban settings, innovative strategies, water scarcity, comprehensive framework, sustainable water management practices.

Abstract: Significant piles of trash by the side of the road are now rather common, and many municipalities do not adequately maintain their trash cans. It causes an unsanitary state to grow along with a significant insect and mosquito population. The outdated practices that are still in use today require a lot of time and labour, and they cannot compete with contemporary innovations. To solve this issue, a project called IOT-based smart bin system has been launched. In order to quantify the status of the garbage can, this project aims to exhibit smart trash cans outfitted with an ultrasonic sensor and a Node MCU that can connect with a mobile application via a WIFI module. The garbage cans are inspected by this gadget, which also notifies users of how much waste has accumulated inside. The garbage cans are inspected by this gadget, which also notifies users of how much waste has accumulated inside.

Keywords: Ultrasonic sensor, Internet of Things, node MCU.

Abstract: The present paper deals with the analyses of different air quality parameters including Ambient Air Quality Index, Particulate matter, NO2, etc. for Udaipur city throughout the various lockdown phases, which include the Pre-Lockdown phase and the Lockdown phase 1, 2, & 3. This resulted in the decrease in air pollution within the city. The data for all the phases were collected from "Rajasthan SPCB", and compared with the help of graphs of AQI, PM, NO2. A noticeable reduction in the concentration of air pollutants was observed, with the most significant changes occurring during the first phase of the lockdown compared to the subsequent two phases. These changes were attributed to restricted human activities.

Keywords: COVID-19, Ambient Air Quality, Air pollution, Particulate Matter, NO2.

Abstract: Phase absence is a very common and severe problem in any industry, home or office. Many times one or two phases may not be live in three phase supply. Because of this, many times, some electrical appliances will be on in one room and OFF in another room. This creates a big disturbance to our routine work. Also load demand is increasing on daily basis; the major problem consumers are confronting is power interruption. Due to this power break, a lot of damage is caused to household appliances and occasionally to life. The problem of power pause originated from single phase faults in distribution system while power is available in other phases. While most domestic loads are connected to single phase supply and if the fault occurs in any one of the phases and the power is available in other phases, we cannot utilize that power. There is therefore a need to automatically switch from one phase to other and auxiliary supply when there is a power failure in any one or all of three phases of the power supply. This system added the Iot system to get information of phase.

Keywords: IOT, phase selection, controller.

Abstract: As cloud computing continues to revolutionize the way organizations store, process, and access data, ensuring robust security measures becomes paramount. This paper examines the myriad security challenges inherent in cloud computing environments and proposes effective solutions to mitigate these risks. Key challenges addressed include authentication and access control, data privacy and confidentiality, data integrity and encryption, network security, compliance and legal issues, incident response, and emerging threats. By implementing best practices and leveraging advanced technologies, organizations can enhance the security posture of their cloud environments and safeguard sensitive information. Real-world examples and case studies illustrate the practical application of these solutions. Insights into future trends offer guidance for staying ahead of evolving security threats. Ultimately, a proactive approach to cloud security is essential to protect sensitive information and maintain trust in cloud services. With the development of cloud computing, privacy security issues have become increasingly prominent, which is of concern to industry and academia. We review the research progress on privacy security issues from the perspective of several privacy security protection technologies in cloud computing. Cite: A. Sathiya Priya, S. Sangeetha, "Security Challenges and Solutions in Cloud Computing Environments", IARJSET International Advanced Research Journal in Science, Engineering and Technology, vol. 11, no. 3, 2024, Crossref https://doi.org/10.17148/IARJSET.2024.11311.

Abstract: Water quality detection plays a crucial role in safeguarding human health, protecting ecosystems, and ensuring sustainable water management practices. This abstract provides an overview of recent advancements in water quality detection methodologies, highlighting the integration of innovative technologies, the challenges faced, and the emerging opportunities in this field. Key technological advancements include the development of sensor technologies such as biosensors, nano material-based sensors, and IoT-enabled devices. These sensors offer real- time monitoring capabilities for various water quality parameters, including pH, dissolved oxygen, turbidity, and the presence of contaminants such as heavy metals and pathogens. Furthermore, advancements in data analytics, including machine learning algorithms and data fusion techniques, enable the integration of heterogeneous data sources to provide comprehensive insights into water quality dynamics.

Keywords: water conservation, urban settings, innovative strategies, water scarcity, comprehensive framework, sustainable water management practices

Abstract: Scientists are looking to nature for inspiration in their hunt for effective and adaptable robotic systems, particularly in the form of bird flight. In biomimetic robotics, foldable flapping wing systems have become a promising field with advantages in mobility, agility, and energy efficiency. The main topics of this paper's thorough literature assessment are the design ideas, manufacturing methods, and applications of foldable flapping wing systems. The most recent developments in control techniques for coordinating wing motion and attaining stable flight are covered in this study. This paper intends to provide insights into the state-of-the-art, identify research gaps, and suggest options for further inquiry into foldable flapping wing mechanics for biomimetic robotics by integrating findings from various sources.

Keywords: Foldable flapping wing, flapping wing mechanism, biomimicry, bat wings.

Abstract: Our project aims to identify ingredients from food images using deep learning techniques. By leveraging convolutional neural networks, we accurately recognize various ingredients present in the images. Additionally, we provide nutritional facts for the identified ingredients, offering users valuable dietary information. With this system, users can gain insights into the composition of their meals swiftly and conveniently.

Keywords: Food Image Recognition, Deep Learning, Ingredient Identification, Nutritional Facts.

Abstract: Parkinson's disease (PD) is a neurodegenerative condition generated by the dysfunction of brain cells and their inability to produce dopamine, an organic chemical responsible for controlling a person's movement. Diagnosis involves many physical and psychological tests and specialist examinations of the patient's nervous system, which causes several issues. The PD Speech data-set used in this experiment exhibits huge dimensionality with comparatively less data-points. Random Forest classifier is used to classify individuals as either PD or healthy control (HC). The proposed system offers a non-invasive, cost-effective, and accessible approach to PD diagnosis, potentially improving healthcare outcomes and patient quality of life. This method extracts a set of features from a recording of the person's voice. Then machine-learning (ML) methods are used to analyse and diagnose the recorded voice to distinguish Parkinson's cases. This project aims to promote the integration of voice analysis into routine clinical practice for early PD detection and intervention.

Keywords: Parkinson's Disease, Machine Learning, Audio Analysis, Random Forest, Diagnosis.

Abstract: This literature study examines tailless Unmanned Aerial Vehicles (UAVs), focusing on design, aerodynamics, control systems, materials, and applications. Tailless UAVs present advancements in maneuverability, weight reduction, and simplified design. Challenges in stability and control are addressed through aerodynamic optimization. Control systems integration enhances flight stability and autonomy. Material advancements contribute to structural integrity and weight reduction. Diverse applications include surveillance, agriculture, and environmental monitoring. This study provides insights into tailless UAV research, identifies gaps, and suggests avenues for further exploration.

Keywords: Tailless UAV, Aerodynamics, Control system, Stability.

Abstract: Garbage classification plays a crucial role in waste management. The existing method employs Convolutional Neural Networks (CNN) for garbage classification, providing accurate but computationally intensive results. This paper proposes the integration of YOLOV8, a state-of-the-art object detection algorithm, for real-time garbage classification categorization(like paper, cardboard, biological, metal, plastic, green-glass, brown-glass, white-glass, clothes, shoes, batteries, and trash) through live camera feed analysis. The proposed YOLOV8 model aims to address this limitation, optimizing both accuracy and speed for live garbage detection.

Keywords: Deep Learning, YOLOv8, Waste Management, Garbage Classification, Object Detection, Real-time, Environmental Monitoring.

Abstract: Phishing websites pose a severe risk to internet security because they try to obtain private information from gullible visitors. Researchers have created a number of methods, including machine learning algorithms, for identifying phishing websites in order to counter this problem. Large datasets of reputable and phishing websites can be used to train machine learning algorithms to find patterns and traits that differentiate the two. Subsequently, these algorithms can be employed to detect and prevent phishing websites from exploiting users. Feature extraction is one method of machine learning-based phishing website detection in which several aspects of a website, like URL structure, domain age, and content, are examined to detect phishing websites. These methods have the potential to be a valuable weapon in the fight against online phishing assaults with additional study and refinement.

Keywords: : SVM, Xgboost, Gradient boosting, Adaboost, Machine learning techniques

Abstract: This research presents an innovative approach to accident classification within tunnels using deep learning algorithms. Given the unique challenges posed by tunnel environments, such as limited visibility and confined spaces, effective accident detection is paramount for ensuring swift response and safety. Utilizing a dataset comprising various tunnel accidents, we trained and evaluated multiple deep learning models. Our results show a significant improvement in classification accuracy compared to traditional methods.

Keywords: Collection Of Unexpected Accidents, Detection Of Unexpected Events, Tunnel Cctv Accident Detection System, Deep Learning

Abstract: The Face Mask Identification With Automated Door Entry Control using Deep Learning addresses the critical need for public health safety during the COVID-19 pandemic by automating the process of identifying individuals wearing face masks in public spaces. This system utilizes deep learning techniques to detect faces and classify whether the individuals are wearing masks or not, thereby allowing automated door entry based on compliance with face mask regulations. The system has undergone extensive testing and validation, proving its efficacy in correctly recognizing people who are wearing face masks and giving access in accordance with that identification. Results indicate high accuracy, speed, and reliability, with potential implications for improving public health and safety measures in various settings. Moreover, when the system detects an individual not wearing a mask, it provides a warning message through voice output, urging them to wear their mask. Conversely, when the system identifies a person wearing a mask, it delivers a message of acknowledgment, thanking them for their compliance. overall our project offering insights into its development, implementation, and potential impact on public health and safety.

Keywords: covid-19,deep learning, Mask Identification ,voice, door entry

Abstract: An emerging area in machine vision is a real dog biometric system that can identify and describe animal life in images and videos these programs offer methods for classifying animals using computer vision CNN features a well-liked deep learning technique are the foundation of the current system for classifying animal faces. Here, the suggested system analyses photos of animal footprints to categorise them using deep learning. Using a clever method, the footprint photos are pre-processed and turned into grayscale boundaries. Gabor filter are used to extract features of segmented image. The dimensionality reduction is carried out based on unsupervised model, Principal Component Analysis (PCA). The classification model is then fed with reduced feature vectors. The categorization and identification of the animal class is done using probabilistic neural networks, or CNNs.Footprints 0 dataset of five different animal categories of 100 images is to be used for classification. The performance analysis of the system is evaluated using the measure accuracy, precision, recall and fl-measure.

Keywords: Probabilistic Neural Network, precision, recall, F1score

Abstract: wet days, dark nights, gloomy and/or wet nights, foggy days, and many other situations with poor visibility conditions are very dangerous for traffic accidents. Current vision-based driving assistance systems are engineered to function best in temperate climates. A process called classification is used to determine the kind of optical properties that vision improvement algorithms need in order to function more effectively. A multi-class weather classification system based on numerous weather features and supervised learning is provided to enhance machine vision in inclement weather. Images of multi-traffic scenes are first processed to extract underlying visual elements, which are then expressed as an eight-dimension feature matrix. Second, classifiers are learned with five supervised learning strategies. The investigation demonstrates that the classifiers have a high recognition accuracy rate and are adaptive, and that the retrieved features may effectively capture the semantics of the image. The suggested approach offers the foundation for improving the driver's field of vision on a cloudy day and for further improving the detection of anterior vehicle detection during variations in night time illumination.

Keywords: difficult meteorological circumstances, intelligent vehicles, supervised learning, underlying visual features, and categorization

Abstract: The landscape of business in India has been transformed by online shopping. With platforms like Amazon and Flipkart catering to global markets, consumers have access to a wide array of products and services. However, local vendors are in need of an online platform to expand their reach. Our app provides a solution by offering native retailers a platform to showcase and sell their merchandise online, thus boosting their brand visibility. Users can easily purchase everyday essentials such as milk, bread, and groceries using their smartphones. Additionally, the app allows users to check product availability at nearby stores, saving valuable time. By utilizing this app, users can conveniently buy products from local retailers without the need to physically visit stores, enhancing convenience and efficiency. Furthermore, the app's second module offers users access to information about various service providers, including carpenters, cable operators, plumbers, artisans, and more.

Keywords: Android Application, Android Studio 4.2, Database, Home Services and Shopping, Service provider appointment, Customer.

Abstract: The innovation known as block chain is highly valued for its ability to record and distribute transactions in the enduring, jumbled record. Customers cannot be guaranteed of the products' legitimacy in a typical supply chain because there is no means to question the hygienist and genuineness. Building a decentralised, blockchain-based system to verify the product's source and quality is the aim of this research. We are going to establish a certified organic food supply chain system in order to confirm the authenticity of the commodities. This study aims to explain the application of block chain technology to enhance the security of supply chain participants' data. We will lower the danger of fraud and data tampering by utilising blockchain technology in "smart contracts," and by offering a quality certification certificate, customers can be certain of the product's quality. This article helps people from a variety of industries comprehend the benefits of the blockchain-based system and put it into practice to improve the system's overall efficiency.

Keywords: Transparency, Ethereum, smart-contract, quality assurance, food supply chain.

Abstract: Individual Human Machine Interference (HMI) systems are available now to provide improved human-computer communication. People used to use keyboards and mice as input devices back in the day. Individuals experiencing locomotor difficulties are unable to operate computers. For those who are disabled or handicapped, the concept of operating computers with the eyes will be quite helpful. Additionally, having this kind of control will do away with the need for additional assistance from someone to operate the computer. The pupil's center is intimately related to the movement of the cursor. Finding the center of the eye would therefore be our first task. OpenCV and Eye-Tracking are used to carry out this pupil detection technique.

Keywords: eye-ball movement curve, eye-tracking algorithm, deep learning, and webcam.

Abstract: In order to highlight the need of effective integrity checks, this article delves into the topic of public auditing for encrypted data kept on cloud servers. The main objective is to enable data dynamics, which includes additions, changes, and removals. By means of a meticulous examination of current auditing protocols, we pinpoint the primary element placing constraints on data dynamics concerning costs. To address this difficulty, we introduce a novel public auditing methodology that aims to accomplish data dynamics at a substantially faster rate than existing techniques. Our novel challenge-response technique significantly lowers the cost of computation for motivation: Data security and integrity are becoming more and more of a problem as cloud servers are used for data storage. In order to ensure that the encrypted information on cloud servers is trustworthy, public audits is essential. Nevertheless, the inefficiencies of current auditing techniques make it difficult to effectively manage data dynamics including additions, deletions, and revisions.

Keywords: Cloud computing, data dynamics, and public auditing.

Abstract: As the world's population gets more urbanised, many of the fastest-growing cities are experiencing worsening air quality. According to a study, ambient air pollution concentrations are at a level where significant health consequences have been observed in 20 out of the 24 global megacities. Although it is commonly known that air pollution can have a substantial negative impact on agriculture, urban growth, and public health, there are evident gaps in the methods used by existing approaches to collect reliable data on air pollution.

Keywords: Convolutional Neural Network, AQI, ResNet-50, and air pollution levels

Abstract: Modern technology has advanced to the point that employing staff through an online process is now possible for businesses. This enables businesses to hire workers for necessary positions more quickly and immediately. It will also be reasonably priced. One can quickly find a job that fits their skills and field of interest by searching the internet. People may not be aware that the jobs that are posted are false or authentic. We developed new technologies to forecast job posts and determine if they are legitimate or fraudulent in order to solve these kinds of issues. We are creating a fake job system. Utilising the idea of machine learning for post-prediction, we are employing the Random Forest classifier, which generates precise outcomes quickly. Comparing the designed algorithm to the previously utilised algorithms, the result is 98%. When students or users look for work, they can have trouble spotting phoney job postings and applying, inadvertently providing all of their personal information. In certain instances, people could fall victim to scams that include paying money in the form of application fees in order to obtain employment or receiving a guarantee of employment upon payment. The framework assists us in determining if the jobs listed are fraudulent or not.

Keywords: Fraudulent Job Post, support vector machine, Random Forest Classifier, Machine Learning, NLTK, Hyperparameter Tuning.

Abstract: In the rapidly evolving landscape of online shopping, the amalgamation of web scraping and data analysis has emerged as a powerful toolset, enabling businesses and data scientists to extract valuable insights and make informed decisions. This paper explores the utilization of Selenium, a robust automation tool, in conjunction with data science methodologies for extracting, processing, and analyzing data from e-commerce websites. The methodology involves the utilization of Selenium, a browser automation tool, to navigate through web pages, simulate user interactions, and extract data elements such as product details, prices, reviews, and other relevant information.

Keywords: Web Scraping, Data Analysis, Selenium, E-commerce, Webdriver, Customer behaviour.

Abstract: Palm vein recognition using image processing is a cutting-edge biometric authentication technology that identifies individuals based on the unique patterns of veins in their palms. This method leverages near-infrared light to capture images of the veins beneath the skin's surface, which are then processed using advanced image processing techniques. The extracted vein patterns are analysed and compared against stored templates to authenticate individuals with a high level of accuracy and security. Unlike other biometric modalities, such as fingerprints or iris recognition, palm vein patterns are internal and difficult to replicate, making this approach highly resistant to forgery and spoofing. This paper provides an overview of palm vein recognition, highlighting its key characteristics, benefits, and applications across various industries including security, healthcare, finance, and personal devices. Additionally, it discusses the role of image processing in enhancing the accuracy and reliability of palm vein recognition systems, as well as future research directions aimed at further improving this technology. Overall, palm vein recognition offers a promising solution for secure and convenient authentication in diverse environments, with the potential to revolutionize the way individuals are identified and verified.

Keywords: palm vein recognition, image processing, near-infrared light, authentication.

Abstract: We offer a framework that the land registration industry might utilize to apply blockchain technology to Land Records. Our suggested framework aims to do two things: first, it will provide secure electronic record storage by setting chain access restrictions for the land users inside it; and second, it will apply blockchain technology for land records. Furthermore, through the utilization of chain storage for records, this initiative addresses the scalability issue that blockchain technology generally faces. A scalable, secure, and essential blockchain-based solution is being offered to the Land Records system through this initiative.

Keywords: BlockChain; PoW; Hash: Merkle Tree, SHA-256

Abstract: The Crime Reporting Management System is a software that is intended to handle all aspect of a police station's operations, including the case management procedure in its entirety. Through computerized recording of complaint data, most wanted offenders, and police station operations, it facilitates the reporting of crimes and oversees all station activities. Workflows can be readily and effectively controlled by computerizing station operations, as many processes are now done by hand. The main components of this project are the user and admin login, the registration of complaints, the viewing of complaint status, the management of criminal registrations, the upkeep of case files, the management of the most wanted criminals list, the provision of general news about crimes in the city, and the provision of safety advice, especially for women and merchants. This project helps automate the administration, user, and police station management systems, as well as complaints and criminal records.

Keywords: Crimes, Investigations, Complaints, etc.

Abstract: The amount of digital content available on the Internet has grown exponentially in recent years, and this rise has coincided with an increase in the number of non-English Internet users as a result of the Internet's globalization. This emphasizes how crucial it is to make materials available to people who wish to research things rather than restricted to the languages they are able to speak. For instance, those who wish to utilize the Internet to research medical information about their ailments (self-diagnosis) but are unable to access resources in their native tongue. Language barriers are overcome by Cross Lingual Information Retrieval (CLIR), which enables document searches in languages other than the query language.

Keywords: Cross-lingual Information Retrieval, Machine Translation, Consumer Health Search, NLP

Abstract: Persistent congestions of varying intensities and durations within dense transportation networks provide the biggest obstacle to sustainable mobility. This type of congestion is beyond the scope of traditional Adaptive Traffic Signal Control. In order to enhance decision-making regarding traffic length estimates, deep learning-based algorithms have demonstrated their importance in predicting adjective outcomes. This work shows that depending on the length of the vehicle, DL models can effectively alleviate traffic congestion by only permitting traffic to pass through a signal.

Keywords: Traffic, Image Processing, YOLO, Deep Learning.

Abstract: Brain tumours are a serious health danger, and the prognosis of patients is greatly enhanced by early identification. Deep learning techniques have surfaced as a viable method for automated brain tumour identification, utilising artificial intelligence to effectively and precisely analyse medical pictures. The purpose of this work is to investigate the most advanced deep learning methods available today for the detection of brain tumours, including RNN and its variants, and to assess how well they perform over a range of datasets.

Keywords: Recurrent neural network (RNN), Ultrasound, and brain tumor.

Abstract: This project focuses on improving medical disease identification through a chatbot built over linked data, overcoming challenges like understanding user queries and supporting multiple knowledge bases. It first designs an interactive user interface architecture for smooth interaction. Then, it proposes a machine learning approach combining intent classification and natural language understanding to accurately interpret user intents and generate SPARQL queries. By leveraging these technologies, the project aims to revolutionize medical disease identification, offering a sophisticated tool for healthcare decision-making and support.

Keywords: Chatbot, Deep Learning, LSTM, Python, Natural Language Processing, Intent Classification, Recurrent Neural Network, Dataset, JSON, Conversation.

Abstract: This paper is a detailed review of BALUN transformer. The paper covers the concept behind the transition of field from unbalanced line to balanced line. All the available techniques are discussed in details. The proposed paper also covers concept behind balanced and unbalanced line.

Keywords: Balanced line, unbalanced line, coplanar strip line, microstrip line, slot line, quarter wavelength line.

Abstract: The global imperative to mitigate food waste and foster sustainable practices has led to the development of innovative solutions, among which the integration of deep learning techniques in an online fruits and vegetables recycling and reuse system stands as a promising approach. This paper outlines the conceptualization and implementation of an intelligent system leveraging deep learning to revolutionize the management of surplus or aesthetically imperfect fruits and vegetables The system's foundation rests upon a robust deep learning model trained to accurately assess and categorize the quality of fruits and vegetables based on visual attributes. Utilizing convolutional neural networks, the model can identify and classify produced items, distinguishing between those suitable for consumption, redistribution, or recycling based on Grade A, B, C. Through a user-friendly online platform, consumers, retailers, and farmers can seamlessly upload images of surplus or imperfect produce. The deep learning model swiftly evaluates the condition of these items, providing real-time assessments and recommendations.

Keywords: CNN, Machine Learning, Deep Learning, Visual Attribute.

Abstract: Deep fake videos, which employ artificial intelligence to manipulate and generate highly convincing fake content, have emerged as a significant threat to society, potentially undermining trust in visual media. Detecting these deceptive videos is outmost importance to combat the spread of misinformation and protect the integrity of digital media. In this study, we propose a novel approach for deep fake face video detection utilizing Long Short-Term Memory (LSTM) networks, a type of Recurrent Neural Network (RNN). Our approach capitalizes on the temporal patterns and context within video sequences, harnessing the unique strengths of LSTM in capturing sequential information. We demonstrate the effectiveness of our methodology by training the LSTM network on a diverse dataset comprising both real and deep fake videos. The network's ability to learn temporal dependencies and identify inconsistencies in facial expressions, eye movements, and other subtle cues allows it to distinguish between genuine and manipulated content. To further enhance the accuracy and robustness of our deep fake face detection system, we integrate pre-processing techniques for frame-level analysis, such as optical flow computation and facial landmarks extraction. Additionally, we employ a comprehensive ensemble of LSTM models and other machine learning algorithms to improve the overall detection performance. In our experiments, we evaluate the LSTM-based deep fake detection system on a large-scale dataset of both known and unseen deep fake videos, achieving high detection accuracy and low false positive rates. We also compare our approach with existing methods, demonstrating its superiority in terms of robustness and generalization. The results of this study signify the potential of LSTM-based models for mitigating the adverse effects of deep fake content on society. As deep fake technology continues to evolve, our approach showcases a promising step towards combating the dissemination of deceptive multimedia, promoting media integrity, and upholding trust in visual information.

Keywords: LSTM Networks, Recurrent Neural Network, Optical flow computation, Facial landmarks extraction, False positive rates.

Abstract: Effective communication is a critical social skill that helps us understand and relate to others. It is also crucial in job-related interviews. In this project, candidates' communication skills in two types of behavioural interviews-a written interview that includes a brief essay and an interface-based, asynchronous video interview-are methodically studied and automatically measured. Next, by utilizing deep learning methods and machine learning XGBOOST, we suggest a prediction model that makes use of automatically extracted multimodel features such as audio, visual, and lexical. While all currently available technologies predict essays with an accuracy of 80-90%, our XGBOOST technology predicts essays with an accuracy of 95-96%. The capacity to effectively and efficiently convey knowledge to others is known as communication proficiency.

Keywords: Communication Skills, XGBOOST, Interviews, Deep Learning, CNN.

Abstract: For self-driving cars and intelligent transportation systems, detecting and recognizing traffic signs is crucial. Real-time traffic sign detection and recognition from camera photos is the task at hand. Across a range of computer vision tasks, Convolutional Neural Networks (CNN) have demonstrated efficacy in achieving high accuracy. In this work, we provide a CNN-based method for identifying and detecting traffic signs. Our method makes use of a deep CNN architecture that is capable of simultaneous traffic sign detection and classification. We use a sizable dataset of photos of traffic signs to train the CNN model, and we assess its effectiveness using a dataset from real-world data. Our test findings show that the suggested method can identify traffic signs in real time with minimal processing overhead and high accuracy.

Keywords: Traffic sign detection, Traffic sign recognition, Deep Learning, Convolutional Neural Network (CNN).

Abstract: For all researchers, recovering lost colours in underwater photographs with complete flavour is still a difficult undertaking. A physically realistic model was provided, and it was demonstrated that the atmospheric image creation model's broad application to underwater photographs was partially to blame for this problem. The updated model demonstrated that: 1) the attenuation coefficient of the signal is not constant throughout the scene but rather depends on reflectance and object range; and 2) the back scatter coefficient, which controls the increase in backscatter with distance, is different from the attenuation coefficient of the signal. Here is the method that uses RGBD photos to recover colour using an updated model. Using the darkest pixels and their known range information, the Sea-thru approach estimates backscatter. The range-dependent attenuation coefficient is then obtained using the spatially variable illuminate. It is demonstrated that the approach utilizing the updated model performs better than the models utilizing the atmospheric model. With the aid of potent computer vision and deep learning algorithms, the regular removal of water will lead to the opening up of enormous underwater datasets for technical development, intriguing potential for underwater research, and conservation.

Keywords: Underwater, image, colour, Sea-thru

Abstract: This study explores the application of deep learning techniques for crop pest classification and pesticide recommendation. Leveraging neural networks, the model aims to accurately identify pests from images. Additionally, the system integrates a recommendation component based on identified pests, suggesting optimal pesticide solutions for effective crop protection. The approach showcases the potential of advanced technology in enhancing agricultural practices for improved yield and sustainability.

Keywords: Crop pests, Pest Classification, pesticide recommendation, Deep Learning, Convolution Neural Network, Agriculture Productivity.

Abstract: In today's world communication has become very easy due to integration of communication technologies with internet. Focusing and addressing the problems faced by the differently abled people such as visually, audibly and vocally challenged is a tough job. A lot of research has been done on each problem and solutions have been proposed separately but not all of them are addressed together. The main purpose of this project is to make the differently abled people feel independent confident by seeing, hearing and talking for them. This project aims at developing an email system that will help for impaired person to use the services for communication without previous training. The system does not require the use of keyboard and mouse. This system can also be used by any normal person, for instance someone who is abled.

Keywords: blind, deaf, hearing.

+91-7667918914 iarjset@gmail.com 0 Items International Advanced Research Journal in Science, Engineering and Technology A Monthly Peer-Reviewed Multidisciplinary Journal ISSN Online 2393-8021 ISSN Print 2394-1588 Since 2014 Home About About IARJSET Aims and Scope Editorial Board Editorial Policies Publication Ethics Publication Policies Indexing and Abstracting Citation Index License Information Authors How can I publish my paper? Instructions to Authors Benefits to Authors Why Publish in IARJSET Call for Papers Check my Paper status Publication Fee Details Publication Fee Mode FAQs Author Testimonials Reviewers Topics Peer Review Current Issue & Archives Indexing FAQ’s Contact Select Page VEHICLE STARTER BY VOICE RECOGINITION USING ARDUINO Dr. G. Srinivasa Rao, D.Nagalakshmi, CH.Rajitha, D.Prasanthi

Abstract: Nowadays the vehicle theft is increasing rapidly by increasing the number of vehicles. Handling keys in automobiles is another issue. Keys must be carried, and loosing or misplacing them will be a serious problem. Using a fingerprint-authenticated vehicle starter system, this issue can be solved in the existing method. The proposed method gives accurate result for voice system. Any users can sign up to be authorized by the system. Arduino's versatility and accessibility make it an ideal platform for implementing voice recognition, ensuring reliable performance and easy integration. The system checks the user's authorization before starting the vehicle for only authorized users during voice recognition. Here Arduino Microcontroller is made use of the microcontroller is connected to the voice module, push buttons, a motor driver, Buzzer, LCD display are used. The motor servers as the vehicle's starter in the demonstration. Using a voice module system automates vehicle security in addition to doing so.

Keywords: Arduino UNO, Voice module, LCD, Microcontroller, Push buttons, Buzzer, Automobiles. Cite: Dr. G. Srinivasa Rao, D.Nagalakshmi, CH.Rajitha, D.Prasanthi,"VEHICLE STARTER BY VOICE RECOGINITION USING ARDUINO", IARJSET International Advanced Research Journal in Science, Engineering and Technology, vol. 11, no. 3, 2024, Crossref https://doi.org/10.17148/IARJSET.2024.11345. Downloads: | DOI: 10.17148/IARJSET.2024.11345 How to Cite: [1] Dr. G. Srinivasa Rao, D.Nagalakshmi, CH.Rajitha, D.Prasanthi, "VEHICLE STARTER BY VOICE RECOGINITION USING ARDUINO," International Advanced Research Journal in Science, Engineering and Technology (IARJSET), DOI: 10.17148/IARJSET.2024.11345 Copy Citation Call for Papers Rapid Publication 24/7 April 2026 Submission: eMail paper now Notification: Immediate Publication: Immediately with eCertificates Frequency: Monthly Downloads Paper Format Copyright Form   Submit to iarjset@gmail.com or editor@iarjset.com   Submit My Paper Author CenterHow can I publish my paper? Publication Fee Why Publish in IARJSET Benefits to Authors Guidelines to Authors FAQs (Frequently Asked Questions) Author Testimonials IARJSET ManagementAims and Scope Call for Papers Editorial Board DOI and Crossref Publication Ethics Editorial Policies Publication Policies Subscription / Librarian Conference Special Issue Info ArchivesCurrent Issue & Archives Conference Special Issue Copyright © 2026 IARJSET This work is licensed under a Creative Commons Attribution 4.0 International License. Open chat

Abstract: Today businesses are prioritizing customer-centric approaches, leading to an increased adoption of AI-driven personalization strategies. Using artificial intelligence, companies gain deep insights into individual preferences, behaviors, and needs, enabling the delivery of tailored content, recommendations and services. From e-commerce to healthcare, AI-driven personalization is transforming how businesses interact with their audiences, fostering engagement, loyalty and overall success. This shift represents a significant change in customer engagement strategies, emphasizing the importance of understanding and empathizing with customers. Moreover, AI-driven content personalization not only enhances customer satisfaction and loyalty but also drives business growth and competitive advantage. Technology continues to evolve, the potential for personalized customer experiences remains limitless, making AI-driven personalization indispensable in today's digital market.

Keywords: Customer-centricity, AI-driven personalization, Recommendations, Content personalization Customer data, digital market

Abstract: Code Together is a collaborative code editor facilitating real-time communication among developers through voice calls and chat. Its whiteboard feature aids in algorithm framing and collaborative planning. Saved code updates are instantly reflected across collaborators' screens. Access to relevant articles aids in resolving coding queries. Developed by a team of remote developers, it caters to Agile teams and troubleshooting sessions alike. It's very good at pair programming, mob programming, and code review.Unlike traditional screen sharing, When another developer wants to edit the file, they download and edit the copy locally and send the edited copy to the interested group through a communication channel. It supports multiple IDEs including Eclipse, IntelliJ, and VS Code. Its versatility spans pair programming, code review, project design, and more. Code Together streamlines unit testing, education, interviews, and remote development. With its intuitive interface, it merges functionality and simplicity seamlessly. Whether for professional projects or educational purposes, Code Together enhances collaborative coding experience.

Keywords: Code Together,real-time communication,Integrated development environment,code editing tools

Abstract: Creating a skin disease detection system using Convolutional Neural Networks (CNNs) involves leveraging deep learning techniques to classify skin conditions from images. CNNs are particularly well-suited for image recognition tasks due to their ability to automatically learn hierarchical features from data. The first step in building such a system would be to gather a dataset of skin disease images, categorized by their respective conditions. This dataset should ideally be diverse, containing images of various skin diseases, with different severities, angles, and lighting conditions to ensure robustness.

Keywords: Convolutional Neural Networks (CNN), Medical image processing, Data augmentation, Machine Learning, Deployment, Training dataset.

Abstract: Sand mining is a prevalent activity worldwide, driven primarily by the demand for construction materials. However, the environmental consequences of sand extraction are extensive and multifaceted, affecting various ecosystems and communities. This review paper synthesizes the current understanding of the environmental effects of sand mining, encompassing diverse aspects such as land degradation, habitat destruction, water pollution, and socio-economic repercussions. By examining the interplay of geological, hydrological, biological, and societal factors, this paper aims to provide a comprehensive overview of the challenges posed by sand mining and potential strategies for sustainable management.

Keywords: Sand mining, Environmental Impact, land degradation, Socio-economic implication

Abstract: The proliferation of digital documents necessitates the development of secure and reliable methods for their storage and authentication. This paper explores a novel system that leverages blockchain technology to address these challenges and create a robust document management solution. By harnessing the core strengths of blockchain, namely its immutability, tamper-proof nature, and distributed ledger architecture, the proposed system ensures the secure storage and verifiable authenticity of documents. Documents are uploaded in a hashed format, generating a unique fingerprint that guarantees data integrity and prevents unauthorized modifications. Furthermore, access control mechanisms are implemented to restrict unauthorized access and ensure data security. To provide non-repudiation of document origin and prevent forgery, cryptographic signatures are employed, allowing users to verify the authenticity of documents and identify their creators. This blockchain-based system offers several advantages over traditional document management approaches. It significantly enhances security by offering a tamper-proof and immutable record of all documents and their associated actions. Additionally, the system promotes transparency by providing a clear audit trail for all document interactions, fostering trust and accountability. Finally, the distributed nature of blockchain technology eliminates the need for a central authority, streamlining document management processes and reducing reliance on third-party verification. Overall, this paper presents a compelling solution for secure document storage and authentication, offering significant benefits for various sectors that rely heavily on digital documentation. Cite: Mr. Sachin Dighe, Aditya Mehta, Bhaveshsingh Rathod, Rishabh Mishra,"DocBlock: Blockchain based document storage and authentication system", IARJSET International Advanced Research Journal in Science, Engineering and Technology, vol. 11, no. 3, 2024, Crossref https://doi.org/10.17148/IARJSET.2024.11350.

Abstract: Now a day's mobile phone has become a major source of business as well as personal communication. These solar panel convert sun light energy into DC current for a range of voltage that can be used for charging the battery. Mobile will get charge, only when a coin is inserted at the coin insertion slot. In this proposed system IR Sensor is used for the correct coin detection and we are adding START and STOP buttons to turn off the charging circuit and the timer. After inserting the coin, turn on the start button then the charging circuit will turn on. Suppose, if any call occurs in the middle of the charge press the stop button to turn off the charging circuit and then the charging circuit will turn off and at the same time timer will also turn off. Then after completion of call press the start button to continue that process without wasting the energy in battery and this all instructions will display on the LCD.

Keywords: Solar panel, Coin, Mobile, Charging circuit, IR sensor, Battery, LCD, Relay.

Abstract: We are slowly reaching the age of electric vehicles. The major issue behind the mass use of electric vehicles is the battery charging time and lack of charging stations. So here we propose a regenerative breaking system. This system allows a vehicle to generate energy each time brakes are applied. The stronger the brakes, the more power are generated. We use friction lining arrangement in a brake drum. As a drum rotates the friction lining does not tough the drum As soon as brakes are applied, the friction lining touches the drum from inside and moves the motors connected to lining in same direction, thus generating electricity using motors as dynamo. Thus this system allows for charging car battery each time brakes are applied, thus providing a regenerative braking system. It moves us another step ahead towards a pollution free transportation system.

Keywords: Regenerative braking, Energy recovery, Kinetic energy, Electromechanical conversion, Energy storage

Abstract: The Internet of Things has transferred various production by authorizing the seamless combination of physical tools with the digital world. In this condition, the IOT Weather Monitoring System represents a sophisticated solution for real-time and remote weather data acquisition and analysis. This project aims to design a comprehensive IoT-based weather monitoring system that provides accurate and timely meteorological information for various applications, including agriculture, disaster management, and general public awareness. The proposed system incorporates a network of sensor nodes strategically deployed in different geographic locations to capture diverse weather parameters such as temperature, humidity, air quality, sound, UV rays, light intensity. These sensors utilize advanced technologies to ensure precision and reliability in data collection. The integrated information is transmitted wirelessly to a main server for storage, processing, and study.

Keywords: Sensor Nodes, Microcontrollers and Communication Modules, Central Server, Web or Mobile Application, Data Security and Privacy.

Abstract: AI is the today's advanced approach of implementing marketing strategies focusing on advanced technology which benefits such as better user experience by getting personalized suggestion, preference based browser, customer demand anticipation, availing advanced search options as image-based product search and improved inventory management, and efficient delivery management and many more. The benefits of using the AI technology includes development of tailored solutions, products and experiences as per the changing market demands, the applications such as data analytics, customer relationship management (CRM) systems, email marketing platforms, social media advertising and more, are racing to incorporate AI features to improvise the marketing strategies for business. However, the consideration also be made so as to focus on the ethical approach of tapping the potential market and generating the more business benefits by way if ethical practices includes privacy, bias, and accountability.

Keywords: AI, Digital Marketing, IoT, Strategies, Marketing, Innovation, Decision Support System

Abstract: The secured data management systems in the education sector cannot be over emphasized. The storage and sharing model of student education records data still faces many challenges in terms of privacy protection and efficient transmission. The use of block chain technology has been proposed as solution to address the challenges faced in the current centralized education sector. The Practical Byzantine Fault Tolerance (PBFT) consensus algorithm to ensure credible and secure data management. The need for precise privacy data is achieved by constructing a dictionary. Cryptographic techniques such as AES is used for encrypted storage of data and keywords. The random secret key is generated for each record through hashing technique for data security storage in block chain . The storage server store database management system with block size 256 bits using SHA-256. Smart contract provides protection for data keywords, the storage server stores data after data masking. Security analysis, privacy protection and computational cost shows that high efficiency and low cost can be achieved. Meanwhile, this scheme has better robustness compared to other educational records data sharing models

Abstract: The "Pathology Lab Management" project introduces an advanced web-based solution aimed at streamlining pathology laboratory operations. It utilizes React for the front-end, Flask for the back-end, and MySQL for the database. The project focuses on optimizing processes like patient information management, test requests, results, and reporting. Crucial features include robust user authentication, patient record management, and test request initiation and tracking. Result entry and reporting are seamlessly integrated, while inventory management ensures the availability of essential supplies. The project also handles billing and invoicing transparently. Timely notifications keep stakeholders informed about test progress. Overall, it offers a comprehensive solution for efficient pathology lab management.

Keywords: digital pathology, change management, user authentication, patient records, medical records

Abstract: In the realm of online education and artistry, the limitations of conventional mice for digital drawing and illustration have posed challenges for educators, students, and artists. The impracticality of a mouse hinders the fluidity and precision crucial for effective teaching and learning, particularly in visually dependent subjects. Additionally, the high cost of specialized drawing tablets has restricted access, limiting creative expression in the digital realm. The "AirInk Studio" project addresses these challenges by introducing an innovative desktop application. Powered by Python, OpenCV, Mediapipe, and Tkinter, it utilizes computer vision and hand tracking for a seamless drawing experience. Boasting diverse brush styles, an undo feature, and an extensive color palette, the project caters to varied artistic preferences. Not only does it redefine online education, but it also empowers artists with an affordable and versatile digital canvas, democratizing creativity in the virtual space. Furthermore, the project expands its capabilities with features like drawing shapes, including circles, rectangles, and lines, as well as a text box feature for annotations and labels. The integration of a chat web application, developed with React.js and Firebase, enables real-time collaboration and connection among users. Moreover, a community showcase web app, leveraging React.js and Firebase, provides users with a platform to share and exhibit their creations, fostering a vibrant digital art community. Together, these enhancements elevate the "AirInk Studio" project, enriching the digital art experience and promoting collaboration and creativity among users.

Keywords: Python, OpenCV, Mediapipe, Tkinter, Computer vision, Hand tracking, React.js and Firebase.

Abstract: The lack of blood donors is a global problem that prevents the demand for blood prompted by an ageing population and increased life expectancy from being met. The aim of this study was to conduct an initial exploration of the reasons for using digital platforms in blood donation. Using a Theory of Planned Behaviour (TPB) framework, microdata for 389 participants from Latin American countries and Spain, and Partial Least Square-Structural Equation Modelling (PLS-SEM), the study obtained three main prediction paths. The first two started from feelings of trust in the digital community and a positive mood state associated with a modern lifestyle, and they were linked to attitudes and behavioural control in the explanation of the intention to donate and actual blood donation. The third path started from modern lifestyles, and was linked to the subjective norm in the prediction of intention and actual donation. These paths represent one of the very first attempts to predict intentions of donation and collaborative donation by taking a PLS-SEM approach. By determining the paths underpinning collaborative blood donors' motives, the results of this study provide strong support for the usefulness of the TPB model within the context of digital platform use and blood donation.

Keywords: blood donation, digital platforms, collaborative exchanges, consumer behaviour, Theory of Planned Behaviours.

Abstract: Artificial Intelligence (AI) has emerged as a transformative force reshaping industries and societies worldwide. This paper provides an overview of AI, delving into its foundational principles, algorithms, and techniques. It explores the diverse applications of AI across various industries, showcasing its profound impact on healthcare, finance, education, transportation, and robotics. In healthcare, AI is revolutionizing diagnosis and treatment through advanced data analytics and predictive modeling. In finance, AI-powered systems are revolutionizing decision-making processes, optimizing investments, and managing risks more effectively. In education, AI enables personalized learning experiences tailored to individual student needs, fostering greater engagement and academic success. The transportation sector is witnessing a shift towards autonomous vehicles, driven by AI technologies that enhance safety and efficiency on the roads. Meanwhile, advancements in robotics fueled by AI are opening new frontiers in automation and human-robot collaboration, though ethical considerations remain paramount. This paper also discusses the ethical implications of AI development and deployment, addressing concerns surrounding privacy, bias, and accountability. Lastly, it outlines future directions and emerging trends in AI, highlighting opportunities for innovation and growth in this dynamic field.

Keywords: Artificial Intelligence (AI), Ethics, Applications, Healthcare, Finance, Education, Robotics.

Abstract: This research investigates the effect of electronic payment systems (EPS) on financial inclusion within Medchal, Telangana. Employing a structured questionnaire for 105 locals, the study recorded demographic information, mobile internet facility, EPS usage patterns, reasons for transactions, ease of use, and inclusion feelings. Descriptive analyses revealed almost-universal bank account holding (96.2%) and mobile internet connection (96.2%), and 94.3% of the respondents used EPS regularly-mostly UPI (89.5%)-and 77.1% made daily digital payments. Although 82.9% confirmed that EPS made financial transactions easy and 94.3% felt included in the organized financial system, major hindrances still existed: network unreliability (64.8%), apprehension about fraud (51.4%), and low digital literacy (45.7%). Interestingly, 77.2% of users needed help for making transactions. Regression analysis found that assistance need was the only significant predictor of the perception of inclusion (p = 0.022), while education and access to mobile internet were not statistically significant. ANOVA results showed no significant difference in perceptions of inclusion between demographic groups (p = 0.839). The results emphasize the need for a twofold strategy: augmenting digital infrastructure and simplifying interfaces to consumers, coupled with localized support and literacy programs, to achieve equitable and sustainable financial inclusion using EPS in semi-urban Indian settings.

Keywords: electronic payment systems, financial inclusion, digital literacy, mobile internet access, UPI, support mechanisms.