VOLUME 13, ISSUE 1, JANUARY 2026

Abstract: This research categorized a deep learning based framework for multimodal emotion recognition in conversa- tions, while addressing class imbalance in emotion datasets. The framework combined text, audio, and visual modalities with methods of imbalanced learning to help the recognition of minority emotions. Evaluations across benchmark datasets for the multimodal framework achieved improvements over baseline methods overall, and with respect to the underrepresented classes.

Keywords: Multimodal emotion recognition, unbalanced learning, deep learning

Abstract: Recurring refinery shutdowns in West Africa are frequently attributed to technical failures, aging infrastructure, or financing constraints. This article advances a governance-based explanation, arguing that procurement governance configurations rather than technical capacity alone systematically shape refinery operational fragility. Using an asymmetric comparative design, the study anchors empirical analysis in Ghana through survey-based Partial Least Squares Structural Equation Modeling (PLS-SEM) (n = 146) and extends interpretation to Nigeria through structured institutional analysis of publicly documented sector dynamics. Ghanaian results show that procurement challenges are strongly associated with refinery process disruptions (β = 0.482, t = 6.284, p

Keywords: procurement governance; refinery shutdowns; institutional weakness; regulatory compliance; Ghana; Nigeria; downstream petroleum

Abstract: HealthConnect is a web-based healthcare information platform designed to simplify access to reliable and location-based healthcare services. In many regions, users face challenges in identifying nearby hospitals, clinics, diagnostic centers, and doctors, particularly during emergency situations. Healthcare-related information is often fragmented across multiple sources, resulting in confusion, inefficiency, and delayed decision-making. HealthConnect addresses these challenges by providing a centralized, user-friendly web platform that organizes healthcare services into clearly defined and easily navigable modules. The system includes Home, Services, Doctors, Articles, City-wise healthcare facilities, Clinics with interactive maps, Checkups, and Contact information. Developed using HTML, CSS, and JavaScript, the platform emphasizes simplicity, accessibility, and usability while delivering a professional user experience. This Project-Based Learning (PBL) initiative demonstrates the practical application of front-end web development concepts, UI/UX design principles, teamwork, and problem-solving skills.

Keywords: Web-Based Healthcare System, HealthConnect, Location-Based Healthcare, UI/UX Design, HTML-CSS-JavaScript, Digital Health.

Abstract: Urban security and personal safety have become critical challenges due to increasing crime rates and limitations of traditional surveillance systems. Conventional CCTV-based monitoring and manual patrolling rely heavily on human intervention and often fail to provide real-time threat detection and immediate response. This paper presents an AI-driven intelligent autonomous surveillance and women safety system that integrates robotic patrolling with a personal emergency protection device. The proposed system consists of an autonomous patrol robot equipped with real-time video streaming, AI-based object detection using MobileNet SSD, line-following navigation, and metal detection for threat identification. In parallel, a compact women's safety device is designed using GPS and GSM modules to transmit emergency alerts with live location information and provide physical self-defense during critical situations. Experimental results demonstrate effective autonomous navigation, accurate object detection, low-latency video streaming, and rapid emergency alert delivery. The integrated approach significantly reduces human dependency, enhances situational awareness, and improves response time. The proposed system is suitable for deployment in campuses, residential areas, public spaces, and other security-sensitive environments.

Keywords: Autonomous Surveillance, Artificial Intelligence, Object Detection, Women Safety, Raspberry Pi, Embedded Systems.

Abstract: The increasing demand for electrical energy and the need for efficient energy utilization have emphasized the importance of real-time electricity monitoring and management systems. Conventional electricity meters rely on manual readings, which are time-consuming, prone to human error, and lack real-time visibility of energy consumption. To overcome these limitations, this project presents the design and implementation of a Blynk-enhanced wireless smart energy meter with cloud-integrated energy management. The system utilizes an ESP32 microcontroller as the core processing unit, interfaced with a ZMPT101B voltage sensor and an SCT-013 current sensor to measure real-time electrical parameters such as voltage, current, power, and energy consumption accurately. The measured data is transmitted wirelessly to the Blynk cloud platform using Wi-Fi connectivity, enabling remote monitoring through mobile and web applications. Cloud integration ensures secure data storage, real-time visualization, and historical data analysis, allowing users to track consumption trends and make informed energy-saving decisions. Instant alerts and notifications further enhance system functionality by indicating abnormal power usage or system faults. The proposed system minimizes human intervention, improves billing accuracy, and promotes energy conservation. Its low-cost design, wireless operation, and user-friendly interface make it suitable for residential and small-scale industrial energy monitoring applications.

Keywords: Smart energy meter, IoT, ESP32, Blynk platform, cloud computing, energy management.

Abstract: Refinery downtime remains a persistent constraint on petroleum supply and industrial performance in many developing economies. While refinery shutdowns are frequently attributed to aging infrastructure and capital constraints, limited empirical attention has been given to procurement-related drivers of operational disruption. This study investigates the relationship between procurement challenges and refinery downtime in Ghana's downstream petroleum sector. Using a sequential explanatory mixed-methods design, survey data from 150 industry professionals were analyzed through Partial Least Squares Structural Equation Modeling (PLS-SEM), followed by qualitative interviews to contextualize the findings. Results reveal a strong and statistically significant relationship between procurement challenges and refinery downtime (β = 0.62, p < .001). In addition, procurement processes significantly moderate this relationship (β = 0.31, p < .01), indicating that weak procurement governance amplifies operational disruptions. Anchored in Transaction Cost Economics and Agency Theory, the findings reposition refinery downtime as not only a technical reliability issue but also a supply-chain governance and execution problem. The study contributes empirical evidence from an emerging-economy context and offers actionable implications for strengthening procurement systems to reduce unplanned outages and improve refinery performance.

Keywords: procurement challenges; refinery downtime; supply disruptions; downstream petroleum; Ghana

Abstract: Procurement performance in capital-intensive, continuous-process industries is commonly assessed using cost-centric indicators such as purchase price variance, budget adherence, and procedural compliance. In crude oil refining, however, where unplanned downtime can generate losses that dwarf procurement savings, cost-based metrics may misrepresent procurement's true contribution to organizational performance. This study re-examines procurement performance measurement in Ghana's crude oil refining sector and argues for a shift from cost savings to value preservation, defined in terms of refinery uptime, throughput stability, and maintenance continuity. Using survey data from 150 industry professionals analyzed through Partial Least Squares Structural Equation Modeling (PLS-SEM), the results indicate that procurement processes have a strong positive effect on refinery efficiency (β = 0.56, p

Keywords: procurement performance; value preservation; refinery efficiency; cost savings; continuous-process industries; Ghana

Abstract: Managing agricultural wastes is still a major problem in the world; and poor management of it leads to pollution, global warming and economical loss. The AgroLoop is a ground-breaking, AI-based digital platform developed in relation to these challenges by transforming decisions about agricultural waste management, analysis and monetisation. It combines a waste trading platform, bio-input marketplace, AI- driven insights and community management features in one single ecosystem. The system is built on a Node. js, React, MongoDB and OpenAI APIs for smart analytics of data and insight- allowing farmers as well as other related parties to convert waste into resources. AgroLoop serves a circular- economy goal by linking farmers, and buyers while fostering sustainable agricultural practices through digital innovation.

Keywords: Agricultural waste management, AI, IoT, digital platforms, circular economy, sustainability, intelligent farming, marketplace systems

Abstract: Road accidents continue to be a major cause of fatalities across the world, largely due to the delay in detecting accidents and the inability to communicate the victim's location to emergency responders in time. In many critical situations, accident victims are unconscious or physically unable to seek help, which significantly increases the risk of severe injury or death. To overcome this challenge, this paper presents the design and development of an IoT-based Accident Collision Detection and Safety Alert System using an ESP32 microcontroller integrated with GPS and GSM communication modules and multiple safety sensors. The proposed system automatically detects collisions using a limit switch-based impact sensor and immediately stops vehicle movement to prevent further damage. Once an accident is detected, the system sends emergency SMS alerts and initiates call notifications containing real-time GPS location information to predefined emergency contacts, ensuring rapid response. In addition to collision detection, the system includes ultrasonic sensors for obstacle detection, smoke sensors for identifying fire hazards, and a manual SOS push button that allows users to request emergency assistance during medical or critical situations. Distinct audio and visual alerts are generated using a buzzer and LED to indicate different emergency conditions. Furthermore, the ESP32 hosts a Wi-Fi-based web control interface that enables remote vehicle operation and manual override, enhancing system usability and flexibility. Experimental observations confirm reliable accident detection, accurate location tracking, and fast alert delivery, demonstrating that the proposed system is a low-cost, scalable, and effective solution for smart vehicles, autonomous platforms, and intelligent transportation systems, thereby significantly improving road safety and emergency response efficiency.

Keywords: Accident Collision Detection, Internet of Things (IoT), ESP32 Microcontroller, GPS Tracking, GSM Communication, Safety Alert System, Intelligent Transportation System

Abstract: Melanoma is one of the highly aggressive types of skin cancer, and early detection plays a critical role in patient survival. Although dermoscopy exposes subtle lesion patterns for clinical evaluation, manual diagnosis can be slow and heavily dependent on specialist expertise. Deep-learning methods have improved automated melanoma identification substantially, yet many current models still encounter real-world challenges, including noisy inputs, non-lesion images, variable lighting conditions, and class imbalance. To address these limitations, this study introduces Melanoma Spotter, a dual-stage diagnostic system that combines a lesion-validation network with a hybrid VGG16-DenseNet121 classifier. The validation stage removes irrelevant or low-quality images to ensure that only true dermoscopic data proceeds to analysis, while the fused CNN model exploits the complementary strengths of both architectures to produce more stable and accurate predictions. Experimental results on dermoscopic datasets show improved reliability, higher confidence calibration, and better robustness than standalone networks. Overall, Melanoma Spotter demonstrates strong promise as a practical deep-learning solution to support early detection of melanoma in clinical settings.

Keywords: VGG16, DenseNet121, HAM10000, Deep Learning, Melanoma, Hybrid Model, Skin Lesion Detection

Abstract: This paper presents an enhanced intelligent vehicle monitoring and security system integrating multi-factor driver authentication, real-time GPS tracking, geo-fencing, and distance-based vehicle locking using Raspberry Pi and Python. Unlike traditional systems, the proposed model incorporates biometric fingerprint matching, face-recognition-based driver identification, and single-bit authentication to activate vehicle ignition. The system continuously collects GPS and sensor data to monitor vehicle movement, enforce geo-fence boundaries, and automatically restrict operation when predefined KM limits are exceeded. AI-enabled modules further support driver activity prediction and periodic in-drive re-authentication to prevent unauthorized access, misuse, and safety risks. Experimental implementation confirms reliable performance across real-time tracking, identity verification, geo-fence breach response, and automated lock mechanisms, demonstrating strong potential for applications in fleet monitoring, rental automation, and intelligent transport management.

Keywords: Fleet Management, Theft Prevention, GPS Tracking, Real-time Monitoring, Microcontroller Automation.

Abstract: In the digital era, rapid advancements in computing technologies have increased dependence on interconnected systems, leading to heightened concerns regarding cyber security, data privacy, and ethical computing. OPIC (Organizational Practices in Information Computing) represents a framework that integrates secure systems, responsible data handling, and ethical decision-making in computing environments. This paper explores the importance of cyber security in protecting digital assets, the role of data privacy in safeguarding personal information, and the necessity of ethical computing to ensure responsible use of technology. The study highlights current challenges, emerging threats, and best practices to build trustworthy and secure digital ecosystems.

Keywords: OPIC, Cyber Security, Data Privacy, Ethical Computing, Information Security

Abstract: The rapid integration of digital technologies in educational contexts presents a paradoxical challenge: while technology-enabled learning (TEL) offers unprecedented access and personalization, it simultaneously introduces significant threats to learner well-being through attention fragmentation, cognitive overload, and blurred boundaries. This paper examines how Human-Computer Interaction (HCI) principles can mediate this tension by designing learning environments that actively promote digital well-being. We argue that effective TEL must transcend mere functionality to incorporate intentional design strategies that foster focus, metacognitive awareness, and sustainable engagement patterns. Through analysis of current implementations and proposed design frameworks, we demonstrate how HCI can shift from creating addictive interfaces to cultivating mindful learning habits. The paper concludes with practical design protocols for educators and developers seeking to align technological affordances with human cognitive and emotional needs in educational settings.

Keywords: Digital Well-being, Technology-Enabled Learning (TEL), Human-Computer Interaction (HCI), Mindful Design ,Cognitive Load , Attention Regulation ,Metacognition.

Abstract: Agriculture is the backbone of India's economy, and sugarcane is one of the most crucial commercial crops. However, manual identification of sugarcane leaf diseases often leads to delayed treatment and reduced yield. This paper presents an AI-based chatbot system for early detection and management of sugarcane diseases. The system integrates a machine learning model built using the Random Forest Classifier, trained on sugarcane leaf image data. The chatbot is developed using Flask and provides users with disease identification, treatment guidance, and multilingual voice/text interaction. The proposed model achieved accurate classification performance and enables farmers to receive real-time diagnosis and recommendations in their preferred language, improving productivity and sustainability in agriculture.

Keywords: Sugarcane Disease Detection, Artificial Intelligence, Chatbot, Random Forest, Flask, Agriculture Automation.

Abstract: The rapid advancement of artificial intelligence has enabled automation in creative domains such as animation and visual storytelling. Traditional animation tools require extensive technical expertise, time, and manual effort for modeling, rigging, and motion design. This paper presents Express Animate, an AI -powered system that automatically converts written textual content into fully animated videos. The proposed system utilizes Natural Language Processing (NLP) to extract characters, actions, and scene information from text, Text -to-Speech (TTS) for realistic audio narration, and AI-based motion generation models to produce synchronized facial and body animations. Backgrounds and environments are generated automatically based on contextual understanding of the input text. The system integrates multiple AI components into a unified pipeline, enabling users with minimal technical knowledge to create high-quality animated content. Experimental evaluation demonstrates that the platform efficiently produces visually coherent animations with reduced production time and cost. The proposed approach contributes toward democratizing animation creation and supports applications in education, storytelling, marketing, and digital entertainment.

Keywords: Artificial Intelligence, Text-to-Animation, NLP, Text-to-Speech, Motion Generation, Video Rendering.

Abstract: Effective asset management is essential for making the most of financial resources and reducing operational risks in today's organizations. Traditional asset management systems depend on manual monitoring and fixed rule-based methods. This often leads to slow decision-making, human mistakes, and a lack of real-time information. To tackle these issues, this paper details the design and development of an AI-based Asset Management System that uses an Intelligent AI Agent for automated portfolio monitoring and decision support. The proposed system reviews user asset portfolios made up of stocks, mutual funds, gold investments, fixed deposits, and savings accounts. It uses machine learning-based forecasting models, intelligent agent logic, and rule-based decision making to assess asset performance, spot risk patterns, and create improved investment suggestions. The system also sends alerts for portfolio imbalances, unusual market activity, and deposit maturity events. A secure web-based interface allows users to manage asset data, view analytics, and receive AI-driven insights in real time. Experimental testing shows reliable forecasting accuracy, low processing delays, and consistent alert notifications. This solution provides a scalable, affordable, and smart framework for modern financial asset management needs.

Keywords: Asset Management System, Artificial Intelligence, Intelligent Agent, Portfolio Analysis, Investment Forecasting, Financial Decision Support, Alert-Based Monitoring.

Abstract: This paper presents a Soldier Health Monitoring System using the ESP32 microcontroller for real-time physiological and environmental data acquisition. Sensors are used to continuously monitor vital parameters such as body temperature, heart rate, and surrounding conditions. The collected data is transmitted wirelessly to a remote monitoring station for timely analysis and alerts. The proposed system enhances soldier safety by enabling continuous health tracking and rapid response in critical situations.

Keywords: ESP32 Microcontroller, Soldier Health Monitoring, Internet of Things (IoT), Wearable Sensors, Real-Time Data Transmission.

Abstract: Rapid, reliable detection of forest fires is critical to minimize ecological, economic, and human losses. This paper presents a practical AI-driven system for early forest-fire detection trained on the D-Fire dataset and deployed end-to-end with a Flask web service and HTML/CSS/JS front-end. The proposed pipeline detects both fire and smoke in single images, videos, and live streams, triggers configurable alerts, and exposes REST endpoints for easy integration. We report model and system design choices, training regimen, evaluation results, and field-deployment considerations. The solution supports live IP-camera feeds, user image/video upload, and dashboards for incident review. A modular microservice design enables scaling, audit logging, and integration with emergency notification channels.

Keywords: Forest fire detection, smoke detection, deep learning, YOLO, Flask, real-time inference, edge deployment, early warning.

Abstract: The advancement of Autonomous Vehicle technology hinges on the system's ability to perceive its surroundings accurately and make timely, intelligent decisions. One of the major challenges in autonomous navigation is achieving reliable perception in dynamic and complex environments. This paper investigates the integration and fusion of heterogeneous sensors to improve situational awareness and decision-making for autonomous vehicles. The data from multiple sensors are combined by the system which includes LiDAR, RADAR, Ultrasonic Sensors, and RGB cameras, it is observed that the data from each of the sensor is found to be complementary about the environment. LiDAR offers precise depth and 3D mapping, cameras feed the visual data in the view of object detection, radar is effective when the visibility is poor, and ultrasonic sensors support close-range obstacle detection. Through the technique of sensor fusion, the strengths of each sensor are leveraged while minimizing their individual weaknesses. Simulation environments are developed using MATLAB, where realistic driving scenarios are created with various actors (vehicles, pedestrians, static objects) and environmental conditions. The data from the various sensors are processed through perception algorithms to perform object detection, classification, and tracking. Based on the interpreted environment, decision-making algorithms enable actions such as lane- maintenance, obstacle avoidance, and speed control. The results demonstrate that a multi-sensor fusion approach significantly enhances the reliability, accuracy, and robustness of autonomous vehicle perception and decision-making, particularly in challenging scenarios. This work contributes to the design of safer, more intelligent self-driving systems and lays a foundation for future improvements in real-world autonomous navigation.

Keywords: Autonomous Vehicle, Muti sensor, Data fusion, perception, Decision making.

Abstract: This project aims to develop a real-time forecasting system to predict dengue outbreaks using climatic conditions as key indicators. By leveraging historical dengue case data alongside real-time weather data obtained from public APIs, the system utilizes machine learning techniques, primarily Random Forest Regressor, to model and forecast potential outbreaks. The model processes live rainfall, temperature, and humidity information with lag features to predict the risk level of dengue in different geographical regions. Predictions are visualized through an interactive web-based dashboard, providing timely insights and automated alerts to health authorities and the public for early intervention and proactive mitigation of dengue spread.

Keywords: Dengue Outbreak Forecasting, Machine Learning, Random Forest Regressor, Climatic Conditions, Real-time Weather API, Lag Features, Time-Series Prediction, Interactive Dashboard, Public Health Surveillance, Ensemble Learning

Abstract: This paper introduces a web based platform Cruzevo, an interactive online car-buying system designed to modernize automotive retail through immersive digital exploration. The platform enables users to browse brands, select vehicle types, explore detailed car models, and interact with key components through clickable hotspots. Built using HTML, CSS, and JavaScript, Cruzevo aims to replicate and improve the showroom experience by offering virtual access to car features such as headlights, wheels, engine compartments, boot space, and interiors. The system provides a smooth interface, dynamic feature popups, and a guided purchase flow. Cruzevo reduces dependency on physical showrooms and enhances customer decision-making with a structured, responsive, and user-friendly.

Keywords: Online Car Buying, Web-Based System, Interactive Car Model, Automotive Retail, HTML, CSS, JavaScript.

Abstract: Java applications run on the Java Virtual Machine (JVM), which provides automatic memory management through garbage collection. Despite this feature, memory leaks remain a critical problem in long-running JVM-based applications. A memory leak occurs when objects that are no longer required are unintentionally retained in memory, leading to increased heap usage and eventual application failure. This research paper explores the causes of memory leaks in JVM applications, techniques for detecting them, tools used for leak analysis, and preventive best practices. The paper emphasizes monitoring and profiling approaches to identify leaks efficiently and proposes a systematic methodology for memory leak detection.

Abstract: The durability of concrete is a critical parameter governing the service life of structures, particularly under aggressive environmental exposure. The incorporation of recycled plastic fibres offers a sustainable approach to enhancing durability while addressing plastic waste management. This study experimentally investigates the influence of recycled plastic fibres on the sorptivity, water permeability, and chloride ion penetrability of M30 grade concrete. Fibres with varying volume fractions and aspect ratios were uniformly dispersed in the concrete matrix, and durability-related tests were conducted in accordance with relevant ASTM, DIN, and IS standards. The results indicate that fibre inclusion significantly modifies the pore structure of concrete, leading to reduced permeability and improved resistance to chloride ingress up to an optimum fibre content. Beyond the optimum dosage, fibre agglomeration adversely affects durability performance. The findings demonstrate that appropriately proportioned recycled plastic fibres can produce dense and durable concrete, contributing to sustainable construction practices without compromising performance.

Keywords: Concrete durability; recycled plastic fibres; sorptivity; water permeability; chloride ion penetration; sustainable concrete; fibre aspect ratio; permeability resistance; experimental evaluation.

Abstract: With the introduction of intelligent and adaptive personalized learning systems, artificial intelligence (AI) has completely changed the educational landscape. Due to variations in learning styles, speeds, and comprehension levels, the standardized teaching methods used in traditional educational institutions do not work for all students. AI makes personalization possible by using sophisticated algorithms to examine student behavior, performance, and preferences. The architecture, methods, advantages, difficulties, applications, and potential future research areas of AI-enabled personalized learning systems are all covered in this paper. To help educators make data-driven decisions, the system also incorporates predictive analytics, performance tracking dashboards, and real-time feedback mechanisms. By offering tailored guidance, IntelliLearn boosts academic performance, increases student motivation, and improves learning efficiency. IntelliLearn shows great promise for transforming contemporary education through intelligent personalization and scalable AI-powered learning environments, despite issues with algorithmic fairness, data privacy, and implementation complexity.

Keywords: Artificial Intelligence, Education, Personalized Learning, Adaptive Learning Systems, Machine Learning, EdTech.

Abstract: An integrated study combining multiple perspectives on sustainable waste management across industries and nations draws an insights from various research works, explores the integration of technological, ecological, and organizational strategies that contribute to effective of waste management practices. It emphasizes circular economy principles, collaborative models in waste startups, ecological safety in cross-border waste management, workplace safety algorithms in waste processing plants and innovative designs for circular waste management systems. Furthermore identifies how digital technologies, including Artificial Intelligence and IoT, can transform traditional waste systems into smart and sustainable frameworks. Through a comparative analysis of case studies and existing models, the paper outlines challenges, best practices, and scalable approaches that can guide global waste management initiatives towards achieving sustainability goals. The findings highlight the need for international collaboration, legal frameworks, and technological innovation to ensure effective resource utilization and environmental safety.

Keywords: Waste management, Circular economy, Sustainability, Artificial intelligence, Ecological safety, Collaboration

Abstract: The aim of this paper is to apply the principle of Rough neutrosophic ideals to a BCK-algebra. We establish structural characteristics of each and several related properties, theorems, and are investigated in this paper.

Keywords: Rough neutrosophic set, Neutrosophic sub - algebra, Rough neutrosophic ideals.

Abstract: Agriculture is an important sector for economic reasons and for feeding purposes. It relys on traditional methods of monitoring plantation which requires a great deal of labour, time-consuming and prone to errors. This research paper considers the possibility of smart technologies in the enhancement of ease and reliability in plantation monitoring and management. The system focuses on sensors for soil moisture, temperature, humidity, and light measurements, which will aid the farmers in keeping track of their crop conditions. These sensor readings are transmitted to a cloud system to enable real-time viewing of data. Farmers will be able to view information either through the web or mobile application without necessarily visiting the field. Machine learning tools are utilized to predict issues such as crop health conditions, irrigation, and early disease symptoms. Thus, it would allow farmers to make necessary decisions fast before facing any huge damages. The wireless communication approaches such as Wi-Fi and LoRa (Forest Ranger) are integrated to make data sharing smooth from the field all the way to the app. By doing so, the aim is to support farmers by reducing undue labour and helping them to effectively make use of water, fertilizers and other resources. From this, it can be concluded that smart monitoring helps improve productivity while preventing environmental waste. The conclusion of this study is that smart technology can enhance the efficiency and sustainability of plantation management hence, farmers will get better control over their crops, increase yields with better utilization of the same land and resources.

Keywords: Plantation monitoring, Sustainable Farming, satellite imaging, automation, soil testing, Machine Learning.

Abstract: Accurate evaluation of highway performance is essential for planning, design, and operational analysis of multi-lane highways, particularly under heterogeneous traffic conditions commonly observed in developing countries. Conventional regression-based models often fail to capture the nonlinear relationships between traffic flow, roadway geometry, and performance measures such as operating speed and level of service (LOS). This study presents a machine learning-based framework for modelling operating speed and LOS on multi-lane highways using Artificial Neural Networks (ANN). Field data comprising traffic volume, percentage of heavy vehicles, and geometric characteristics were used to develop and validate the proposed models. The performance of ANN models was compared with conventional regression approaches using statistical indicators. Results demonstrate that ANN models provide superior predictive accuracy and better representation of complex traffic behaviour. The findings confirm the suitability of machine learning techniques for highway performance evaluation and provide practical insights for transportation planners and highway authorities.

Keywords: Level of service; Operating speed; multi-lane highways; Artificial neural networks; Heterogeneous traffic

Abstract: As personal financial decisions become increasingly complex in the digital era, it has become vital to explore not just what people know, but how people think and behave about money. This article explores the psychological basis of Financial Freedom by investigating the effects of four behavioral constructs - Overconfidence Bias, Financial Self-Efficacy, Self-Control Bias, Herding Bias - with Financial Literacy as a mediating variable. Based on Behavioral Finance Theory, Social Cognitive Theory (Bandura, 1997), and the Financial Capability Framework, the study adopts a quantitative explanatory research design with 207 working professionals in Chennai, India. Standardized Likert-scale instruments were applied and the data was analyzed in SPSS by correlation, multiple regression, and mediation analysis. According to the findings, Financial Literacy is a strong mediator of the relationships between Overconfidence Bias, Financial Self-Efficacy, and Self-Control Bias and Financial Freedom; Herding Bias has no mediation effect. Financial Self-Efficacy displayed the most indirect and total influence by far of the predictors, suggesting a central role of knowledge and confidence to financial freedom. The results confirm that effective financial behavior is a function of belief, discipline, and self-regulation, not just information. The result of this study helps to deepen behavioral finance research and explains that biases and literacy among individuals in a behavioral finance theory jointly determine financial freedom through this psychological model.

Keywords: Behavioral Finance, Financial Self-Efficacy, Overconfidence Bias, Financial Literacy, Self- Control Bias, Herding Bias, Financial Freedom, Social Cognitive Theory, Financial Capability.

Abstract: Early retirement has conventionally been treated as a financially-determined exit from paid work, yet digital nomadism has primarily been considered as work or mobility-based lifestyles. These literatures have developed concurrently, rarely coming together in a set of theories. This paper proposes to fill this gap by conceptualizing digital nomadism as a psychological reorientation of early retirement-one that does not replace working nor replaces a leisure-centered occupation. Based on Self-Determination Theory, Continuity Theory, and Life-Course Theory, the research contends that factors associated with premature retirement-burnout, autonomy deprivation, and work identity dissatisfaction-are often psychological antecedents long before financial readiness and induce retirement-like behaviors long before formal retirement planning begins. Digital nomadism is seen as a strategic work redesign in which individuals gradually gain autonomy to pursue identity continuity through which they make sense, while remaining economically active. Through repositioning retirement planning as an ongoing mental journey instead of a single dollar purchase, the paper presents an integrative view that conceptualizes digital nomadism as a link between traditional work and hybrid or staged retirement options. In this study, retirement theory, work psychology, and future-of-work scholarship are addressed as the new way of thinking about retirement as a state that can be attained through intentional career planning.

Keywords: Digital Nomadism, Early Retirement Planning, Psychological Pathways, Career Redesign, Life-Course Theory, Identity Continuity

Abstract: Breakthroughs in smart technology and land management provide a sustainable roadmap for protecting water and the soil. Intelligent Wireless Systems act as automated guardians by sensing full tanks and instantly shutting off pumps to prevent overflow and wasted energy. Modern research reveals a powerful strategy for protecting water and the land. The most significant breakthroughs involve smart technology and ingenious setups, such as the Intelligent Wireless System, function as automated guardians. In urban centers like Gauteng, South Africa Internet of Things (IoT) solutions combat the hidden crisis of leaky pipes, using real-time data to pinpoint and stop water loss. Conservation also reaches the Earth through Information Management Systems that monitor soil erosion during massive infrastructure projects, such as building high-voltage power lines, ensuring environmental integrity. On farms, practical conservation methods like specialized planting reduce mud runoff and sediment loss while helping the soil store carbon for the benefit of the climate. To address the broader picture, a new Assessment System measures the "water-wise" status of societies by analyzing total consumption impacts. Within the industrial sector, evidence shows that high-consumption factories can realistically save one-fifth of current water usage through better management practices and modern technology. These advancements combine to create a resilient future for vital natural resources.

Keywords: Internet of Things (IoT), Smart Systems, Automation, Leakage Detection, Sustainability, Smart Metering.

Abstract: The project focuses on reducing harmful automobile emissions through a water injection system integrated into the exhaust manifold. The proposed setup consists of a water tank, control valve, heat- resistant pipes, honeycomb pads, and nozzles. Water is sprayed onto the heated honeycomb pads, reducing exhaust gas temperature and converting toxic gases such as NOx, CO, and HC into less harmful forms. This simple, cost- effective modification shows significant emission reduction while maintaining system efficiency. Experimental results demonstrate notable decreases in exhaust temperature and emission concentration, making it an eco- friendly and retrofit-compatible solution for small engines.

Keywords: Emission Control, Exhaust Manifold, Water Injection, Honeycomb Pad, Pollution Reduction.

Abstract: The rapid digital transformation of the Indian banking sector has significantly increased the demand for intelligent, inclusive, and efficient customer support systems, particularly in public sector banks (PSBs). India's linguistic diversity poses a major challenge for traditional customer interaction mechanisms that rely primarily on English-centric interfaces. This research paper proposes the design and development of a smart Natural Language Processing (NLP)-driven multilingual customer interaction module tailored specifically for public sector banks in India. The proposed module integrates advanced NLP techniques such as language detection, speech-to-text processing, intent classification, sentiment analysis, and multilingual response generation to enable seamless communication between banks and customers across regional languages. The study adopts a design-oriented methodology supported by a review of recent Indian research in banking automation, AI-driven customer service, and multilingual NLP systems. The paper outlines clear objectives, system architecture, and functional components of the module, emphasizing financial inclusion, service quality improvement, and operational efficiency. Discussion and analysis highlight the potential impact of the module on customer satisfaction, grievance redressal, and accessibility for rural and semi-urban populations. The findings suggest that NLP-based multilingual systems can significantly enhance customer experience while reducing workload on bank staff. The study concludes by recommending phased implementation and future integration with core banking systems and regulatory compliance frameworks.

Keywords: NLP, Multilingual Banking, Public Sector Banks, Customer Interaction, Artificial Intelligence

Abstract: This paper introduces an advanced gaze-driven cursor control system, exemplifying subject expert excellence in human-computer interaction (HCI) and assistive technology, enabling seamless hands-free computer operation for motor-impaired users through precise eye movements and blinks captured via standard webcam footage. The hybrid CNN-LSTM deep learning architecture at its core employs convolutional layers for high-fidelity extraction of spatial eye features-including pupil centroid, iris boundaries, and geometric landmarks-from real-time video frames, coupled with LSTM recurrent units that adeptly model temporal dependencies to forecast gaze trajectories with sub-pixel smoothness and jitter below 1 pixel variance, while blink detection attains surgical precision (>98% accuracy across diverse head poses) via Eye Aspect Ratio (EAR) derived from eyelid contours and an optimized Support Vector Machine (SVM) robust to occlusions and micro-expressions. User-centric calibration further refines gaze-to-screen homographic mapping through adaptive gain constants, dead zones suppressing physiological noise such as saccades, and dynamic sensitivity regions yielding sub-degree estimation errors (30 minutes) confirming blink precision >97% and pointer control F1-scores >0.95-unequivocally demonstrating consumer-grade hardware's parity with commercial eye-tracking systems in affordability, accessibility, and production viability.

Keywords: gaze-driven cursor, CNN-LSTM, eye tracking, blink detection, assistive technology, webcam-based HCI.

Abstract: This study analyses the temporal variation of CRI recorded at four geographically distinct monitoring stations-Oulu (Finland), Jungfraujoch (Switzerland), Moscow (Russia), and Rome (Italy)-over the period 2020 to 2024. The objective of this research is to identify long‑term trends, inter‑station variability, and possible implications related to solar modulation of cosmic rays. The results indicate a consistent declining trend in CRI across all stations, with Jungfraujoch showing the highest absolute CRI values and Rome exhibiting comparatively lower magnitudes and stronger year‑to‑year variability.

Keywords: Cosmic Ray Intensity, Solar Modulation, Neutron Monitor, Long‑term Trend.

Abstract: The exponential growth of digital banking has heightened transactional fraud risks, resulting in significant financial losses. This study introduces a real-time fraud detection system employing an ensemble of Statistical Processing Model (SPM), K-Nearest Neighbors (KNN), Logistic Regression, and Convolutional Neural Networks (CNN) to monitor user transactions characterized by amount, geolocation, device fingerprint, IP address, frequency patterns, and behavioral history. KNN detects anomalies against user-specific baselines, Logistic Regression computes fraud probabilities, and CNN extracts deep spatiotemporal features from sequential transaction data to identify complex fraud signatures. Detected anomalies trigger immediate security responses including user notifications, account suspension, and administrative alerts. Evaluation demonstrates superior AUC-ROC and F1-scores compared to baseline methods, validating the system's efficacy for scalable, production-ready deployment in securing digital payment ecosystems while preserving legitimate user experience.

Keywords: transactional fraud detection, digital banking security, ensemble machine learning, CNN anomaly detection, real-time fraud prevention, behavioral biometrics.

Abstract: Food is a basic necessity; many people are still unaware of the level of cleanliness and care required to keep it safe. The food stalls face challenges in maintaining proper hygiene, handling food safely, and managing waste effectively. These issues increase the risk of foodborne illnesses and also contribute to environmental pollution around food-selling areas. In many cases, these problems are not caused by negligence but by a lack of proper infrastructure, training, and awareness. The study emphasizes the importance of basic hygiene practices such as regular handwashing, keeping cooking and serving areas clean, and disposing of waste responsibly. Even small steps can greatly reduce health risks and improve overall food safety. This research also highlights that food safety is a shared responsibility among vendors, consumers, and local authorities. By promoting awareness and cooperation among all stakeholders, safer and cleaner food environments can be created, leading to improved public health and a more pleasant dining experience for the community.

Keywords: Hygiene, inspection, contamination, temperature, sanitization, disinfection.

Abstract: Efficient water management has become a major challenge in modern agriculture due to increasing water scarcity and unpredictable climatic conditions. Conventional irrigation methods operate without real-time feedback from the field, often leading to excessive water usage and reduced crop efficiency. This paper presents the development of an Internet of Things (IoT) based smart irrigation system using an ESP32 microcontroller integrated with environmental and flow sensors. The system continuously monitors soil moisture, ambient temperature, humidity, and rainfall to determine irrigation requirements. A water flow sensor is employed to measure the exact quantity of water delivered during each irrigation cycle. Cloud-based weather information is obtained using the OpenWeather API, while real-time monitoring and control are achieved through the Blynk IoT platform. Irrigation is automated based on soil moisture conditions, with rainfall given the highest priority to prevent unnecessary watering. Experimental evaluation shows that the proposed system significantly reduces water wastage while providing accurate monitoring of irrigation parameters. The solution is low-cost, scalable, and suitable for practical deployment in smart agriculture applications.

Keywords: Internet of Things (IoT), Smart Irrigation System, ESP32 Microcontroller, Soil Moisture Monitoring, Water Flow Measurement, Automated Irrigation, Cloud-Based Agriculture

Abstract: The "Intelligent Detection of Sapthashira and Its Diseases" project develops a deep learning framework for the automated identification of diseases affecting Sapthashira (betel) leaves, even when obscured by overlying pepper leaves, while providing targeted preventive recommendations for each diagnosed condition. Leveraging an EfficientNetB4 transfer learning architecture implemented in TensorFlow-Keras, the system preprocesses and augments input leaf images to achieve robust classification of healthy versus diseased specimens across diverse real-world scenarios. Integrated into a Flask-based web application, it enables users to upload images for real-time diagnostic output, including evidence-based interventions such as isolating infected plants, excising severely compromised foliage, and administering specified fungicides or bactericides-thereby optimizing crop protection, minimizing yield losses, and reducing superfluous agrochemical applications. This extensible platform establishes a scalable foundation for precision agriculture, with potential for adaptation to additional pathogens and crop varieties in subsequent developments.

Keywords: deep learning, EfficientNetB4, Sapthashira diseases, transfer learning, Flask web application, and preventive measures.

Abstract: Social media sites such as Facebook, Instagram, blogs, and Twitter have become the most popular places for people of all ages to spend much of their time because they allow users to share information rapidly and broadly, which in turn attracts new users. The huge rise in daily visitors to these sites is increasing the risk of giving false information and becoming a victim of fraudulent accounts. A phoney account is frequently used to spread misleading information, send spam, forward phishing attack URLs, and steal contacts for personal benefit or the detriment of competitors. Therefore, Finding fraudulent users and spammers on online social networks (OSNs) is a popular research topic. This study examined the effects of fake profiles and new methods for identifying them, including deep learning and machine learning algorithms like Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), and K-Nearest Neighbours (KNN). A comparison of different techniques for cross-platform profile verification or re-identification is also provided in order to mitigate the harm caused by fraudulent profiles.

Keywords: Cross-platform identification, online social media networks, profile cloning, fake profiles, and profile re-identification.

Abstract: Substance Use Disorders (SUDs) involving alcohol, nicotine, and opioids constitute a substantial global health burden, with current pharmacotherapies often limited by efficacy issues or adverse effects. This review examines the emerging therapeutic potential of Glucagon-Like Peptide-1 (GLP-1) receptor agonists, specifically Semaglutide, in modulating reward circuitry. A comprehensive literature search was conducted using PubMed, Scopus, and Web of Science for studies published between 2018 and 2024. Preclinical findings indicate that Semaglutide significantly attenuates the intake of alcohol, opioids, and nicotine in rodent models by suppressing dopamine release in the nucleus accumbens and enhancing GABAergic transmission. Clinical observations from metabolic disorder treatments suggest a concurrent reduction in substance cravings. The underlying mechanisms appear to involve the restoration of blood-brain barrier integrity, reduction of neuroinflammation, and direct modulation of the mesolimbic reward system. These findings suggest Semaglutide possesses significant neuroprotective and anti-craving properties, warranting further investigation through large-scale randomized controlled trials.

Keywords: Semaglutide, GLP-1 Receptor Agonists, Substance Use Disorders, Neuroprotection, Addiction, Reward Circuitry.

Abstract: This research explores the potential of iron filings as a sustainable adsorbent for the removal of synthetic dyes from wastewater, with a focus on Methyl Orange and Methylene Blue, two dyes commonly used in industrial processes. The iron filings were comprehensively characterized through chemical analysis, mineralogical assessment, particle size distribution, scanning electron microscopy (SEM), and Fourier transform infrared (FTIR) spectroscopy to evaluate their adsorption properties. The effects of key operational parameters-including adsorbent dosage, initial dye concentration, and contact time-on removal efficiency were systematically investigated, with experimental data analyzed using Design Expert software. Findings show that iron filings exhibit high adsorption capacity toward Methyl Orange, with FTIR analysis confirming the functional groups responsible for the adsorption mechanism. Adsorption isotherm and kinetic modeling indicated that Methyl Orange removal is consistent with Langmuir and Freundlich isotherms and follows both pseudo-first- and pseudo-second-order kinetics, while Methylene Blue removal aligns primarily with pseudo-first-order kinetics. Overall, the study highlights iron filings as an efficient, cost-effective, and environmentally sustainable material for dye removal in wastewater treatment applications.

Keywords: Iron filings, Methyl Orange (MO), Methylene Blue (MB), FTIR, SEM, RSM, adsorption isotherms, kinetics, wastewater treatment.

Abstract: This paper focuses on how to apply to the prediction of Korean economic trend by AI based econometrics. The traditionally, the economic trend analysis has been using the mathematic-based the prediction or the directions of changes in the economy using such as linear regression, ARIMA (Auto-Regressive-Integrated Moving Average) or VAR (Vector Auto-Regression) However, there are always many non-linearities in economic models and the issues during research process because of the process of linearization. On the other hand, the function of AI such as LLM (ChatGPT: Chat Generative Pretrained Transformer AI) technology neural network, and its combined learning system has a powerful learning (supervised learning, unsupervised learning, and reinforcement learning to train language). The generative AI model-based LLM (Large Language Model), TIM (Text-to-Image Model), and ITM (Image-to-Text Model) are rapidly increasing their functions and it has so many possibility for applying in everywhere because a new generation of user-friendly tool (Generative AI: Chat GPT) is useful for texts, images, and videos. It is very important to exactly understand and decide on how and what we have to do for the Korean economic analysis process for business, policy, and job patterns. The first aim of his paper is to provide study strategies and simulation on how AI-based generative model and related technologies apply to economic analysis processing and what we have to prepare and study Korean econometrics.

Keywords: AI, LLM, Econometric analysis, Econometrics Model.

Abstract: Streaming services today really struggle with providing personalized recommendations at a large scale, which calls for some pretty advanced modeling techniques. This paper presents a new recommendation framework designed specifically for Netflix, combining collaborative, content-based, and time forecasting methods. We used Apriori association rule mining to find hidden patterns in genres and metadata, built a knowledge graph to make things easier to explain, and applied k-Means clustering to learn similarities. For predictions, we went with a multi-layer perceptron (MLP) deep neural network, and on top of that, we included a Prophet time-series model to forecast content trends. When we tested our approach, we ended up with a Mean Absolute Error (MAE) of 38.23 and a Mean Squared Error (MSE) of 2144.39 for regression tasks, while the k-Means part scored a silhouette score of 0.4170. Overall, this hybrid setup showed better robustness and interpretability than traditional systems, making it a solid option for suggesting content in large video-on-demand platforms.

Keywords: Hybrid Recommendation Systems, Association Rule Mining, Knowledge Graphs, Deep Learning, k - Means Clustering, Time-Series Forecasting, Lecture Notes in Computer Science.

Abstract: Landslides constitute a pervasive geohazard in monsoon-driven topographies, inflicting substantial socioeconomic devastation through abrupt slope failures triggered by hydrogeological stressors. This research presents an IoT-RNN/LSTM framework for early landslide prediction, fusing real-time multivariate sensor telemetry rainfall intensity, soil moisture saturation (>30%), pore pressure gradients, inclinometer tilt angles, and seismic vibrometer with deep recurrent architectures to model spatiotemporal failure precursors. ESP32 edge nodes aggregate data via MQTT, preprocessing through min-max normalization and variational mode decomposition (VMD), feeding hybrid LSTM that attain 95.2% F1-score and 24-48-hour lead times on benchmark datasets. Deployed alerts cascade through LED/buzzer/LCD/GPS interfaces, achieving

+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 An Analysis of Ergonomical Hazards/Risks in Construction Industry R.Sarathkumar, R.Boopathi

Abstract: Ergonomic hazards that expose construction workers to include awkward positions, repetitive work, heavy lifting and sustained stationary positions may result in musculoskeletal disorders (MSDs) and low productivity. This study explores ergonomic risks prevalence among construction workers and analyses the correlation among the work conditions, work awareness, and training. A structured questionnaire was utilized in data collection of 80 respondents and SPSS software was used in data analysis. To be knowledgeable of the trends of physical strain, fatigue, and ergonomic awareness, descriptive statistics, one-way ANOVA, correlation, and chi-square tests were implemented. The findings are that a good percentage of workers are having physical discomfort, with moderate levels of repetitions and still postures. Training and ergonomic equipment, rest break and safety awareness gaps were identified. The paper points to the necessity of planned ergonomic measures, regular safety education, and the participation of the management in the study to minimise health risks of workers and improve their well-being in the construction industry.

Keywords: Ergonomics, Construction Industry, Musculoskeletal Disorders, SPSS, Occupational Health, Survey Analysis. Downloads: | DOI: 10.17148/IARJSET.2026.13147 How to Cite: [1] R.Sarathkumar, R.Boopathi, "An Analysis of Ergonomical Hazards/Risks in Construction Industry," International Advanced Research Journal in Science, Engineering and Technology (IARJSET), DOI: 10.17148/IARJSET.2026.13147 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: The present study examined differences in anxiety between swimmers and non-swimmers in the age group of 24-30 years. A total of 185 participants, including 69 swimmers and 116 non-swimmers, were selected for the study. Anxiety levels were assessed using a standardized psychological anxiety scale. Mean scores, standard deviations, and the t-ratio were computed to determine group differences. Results revealed that non-swimmers demonstrated higher mean anxiety scores (M = 12.56, SD = 1.65) compared to swimmers (M = 10.31, SD = 1.35). However, the calculated t-ratio (t = 2.28) did not reach the level of statistical significance at the prescribed level, indicating no significant difference in anxiety between the two groups. Despite the lack of statistical significance, the findings suggest that participation in swimming may be associated with lower anxiety levels. The study highlights the potential psychological benefits of swimming and underscores the importance of physical activity in mental health promotion.

Keywords: Anxiety, Psychological Problems, Swimmers, Non-Swimmers, Physical Activity

Abstract: The growing need to have sustainable and decentralized energy systems has pushed the study of wind energy systems that can effectively perform at the low wind speed. The VAWTs are especially the right choice under such conditions because of their omnidirectional wind acceptance and simple structural design. Nevertheless, traditional Savonius and Darrieus turbines are limited in nature when they are used in isolation. The design and construction of a hybrid Savonius-Darrieus VAWT with the ability to Self Start like the Savonius rotor and high efficiency-based performances of the Darrieus rotor is presented in this paper. The turbine itself is made of low-cost materials, including sheets of metal blades and L-angles of shelter in mild steel. There is a spur gear mechanism that increases the speed of the shaft rotation so that it may allow effective coupling with the dynamo that runs on DC. Generation of this electrical power is proved by using DC LED light as a proof of concept. Low-speed under wind conditions provide experimental performance from low wind conditions, which prove stable operation and dependable energy production. The presented hybrid turbine will be a cost-effective and environmental-friendly solution that might be applied to domestic, rural and off-grid renewable energy sources.

Keywords: Vertical Axis Wind Turbine, Savonius, Darrieus, Hybrid Wind Turbine, Low-Speed Wind Energy, Renewable Energy.

Abstract: Diabetes mellitus, a pervasive chronic metabolic disorder, frequently evades early detection until irreversible complications-cardiovascular disease, nephropathy, neuropathy, and retinopathy-manifest. Conventional diagnostics reliant on laboratory assays and clinical expertise remain constrained by accessibility and cost. This investigation introduces a machine learning-driven diabetes risk prediction system leveraging the Pima Indians Diabetes Dataset, employing systematic data preprocessing, feature selection, and Logistic Regression modelling to deliver interpretable early-stage risk assessment from standard clinical parameters. Deployed through a Flask microservice architecture, the platform furnishes real-time probabilistic predictions with confidence intervals via an intuitive web interface, facilitating patient self-screening and healthcare provider decision support. Empirical validation confirms robust predictive performance suitable for population-scale early warning, while explicit positioning as an educational adjunct-rather than diagnostic substitute ensures clinical responsibility. The system advances accessible prediabetes surveillance, enabling timely lifestyle and pharmacotherapeutic interventions to mitigate long-term morbidity. CheckYourDiabetic introduces a hybrid machine learning framework for early Type 2 diabetes prediction, integrating Logistic Regression, K-Nearest Neighbors, Random Forest, and XGBoost via stacking ensemble on the Pima Indians Diabetes Dataset (n=768, 8 clinical features). Following robust preprocessing-KNN imputation, SMOTE oversampling, and RFE feature selection-the system achieves superior performance (AUC-ROC: 0.94, Sensitivity: 92%) compared to individual classifiers through complementary modeling of linear, local, and nonlinear biomarker interactions. Deployed as a Flask-based web application, it delivers real-time risk stratification with SHAP-based interpretability, enabling accessible pre-symptomatic screening and timely intervention to mitigate diabetes complications in resource-constrained settings.

Abstract: Digital transformation has emerged as a critical strategic imperative for organizations operating in an increasingly competitive and technology-driven global economy. Among emerging digital technologies, Artificial Intelligence (AI) has gained particular prominence due to its ability to automate complex processes, enable predictive decision-making, personalize customer interactions, and generate strategic insights from large volumes of data. This paper examines whether AI can function as a transformative, game-changing tool in reshaping digital transformation initiatives within organizations. Using an exploratory qualitative case study approach, the study analyses AI-driven digital transformation strategies adopted by selected companies across technology, retail, and financial services sectors. The findings reveal that AI significantly accelerates digital transformation by enhancing operational efficiency, enabling data-driven decision-making, improving customer experience, and fostering innovation. However, the study also identifies critical challenges, including data governance issues, ethical concerns, skills shortages, integration with legacy systems, and organizational resistance to change. The paper concludes that AI can be a powerful enabler of digital transformation when embedded within a coherent strategic framework supported by leadership commitment, organizational readiness, and responsible AI governance.

Keywords: Artificial Intelligence, Digital Transformation, Business Innovation, Case Study, Organizational Strategy.

Abstract: Over the past decade, India has experienced a rapid expansion of its startup ecosystem, supported by increasing venture capital inflows, digital penetration, and policy support. Alongside this growth, however, the ecosystem has also witnessed a growing number of high-profile startup failures, including firms that once achieved unicorn status. This paper examines the role of unit economics and corporate governance in the collapse of Indian startups. Using a qualitative multiple case study approach, the study analyzes selected Indian startups that scaled rapidly but later experienced financial distress or shutdown. The findings indicate that persistent negative unit economics, when combined with weak corporate governance mechanisms, significantly increase the likelihood of startup failure. The study contributes to entrepreneurship and management literature by providing India-specific insights and highlights practical implications for founders, investors, and policymakers

Keywords: Indian startups; unit economics; corporate governance; startup failure; venture capital; emerging markets

Abstract: Career decision-making is a complex process that significantly influences an individual's academic progression and long-term professional success, yet traditional career guidance approaches rely heavily on manual counseling, static assessments, and generalized recommendations that often fail to account for the diverse abilities, interests, and evolving aspirations of students. To overcome these limitations, this project proposes an AI-Powered Career Guidance and Recommendation System that leverages machine learning techniques to deliver personalized and data-driven career recommendations. The system collects structured student information, including academic performance, technical and soft skills, areas of interest, and personality-related attributes, which is then subjected to comprehensive preprocessing steps such as data cleaning, categorical encoding, numerical normalization, and feature selection to ensure compatibility with machine learning models. Multiple supervised learning algorithms are trained and evaluated using performance metrics including accuracy, precision, recall, and F1-score, with the most effective model selected for deployment. The trained model predicts suitable career domains and generates ranked career recommendations tailored to individual profiles, while model persistence and a modular system architecture support scalability, consistency, and future retraining. Experimental results demonstrate that the proposed system provides accurate and reliable career recommendations, highlighting the effectiveness of machine learning in career guidance applications, reducing dependence on manual counseling, and improving accessibility to consistent, objective, and intelligent career decision-support services.

Keywords: AI-Powered Career Guidance, Career Recommendation System, Machine Learning, Student Profiling, Supervised Learning, Random Forest, Feature Engineering, Clustering Techniques, Data Preprocessing, Model Persistence, Joblib, Streamlit, Decision Support System, Educational Data Mining, Personalized Career Prediction.

Abstract: Public transportation systems are pivotal for sustainable urban mobility, yet frequent delays in buses, metros, and trams compromise service reliability, passenger satisfaction, and operational efficiency. This study proposes an AI-based hybrid CNN-LSTM model for public transport delay prediction, classifying trips as "Delayed" or "On Time" using a comprehensive dataset of 2,000 records encompassing operational features (transport mode, route details, scheduled and actual times), temporal attributes (peak hours, weekdays, seasons, holidays), meteorological variables (temperature, humidity, wind speed, precipitation), and exogenous factors (traffic congestion index, event attendance). Rigorous data preprocessing addresses missing values via imputation and employs Recursive Feature Elimination (RFE) with cross-validation to select optimal features, mitigating multicollinearity and enhancing model interpretability. A supervised learning pipeline, implemented in Scikit-learn and TensorFlow, leverages CNN for extracting spatial hierarchies from multivariate inputs, LSTM for modeling temporal dependencies in delay sequences, and Random Forest as an ensemble baseline, achieving superior performance (accuracy > 92%, F1-score > 0.91) over benchmarks via stratified k-fold validation, precision-recall curves, and confusion matrix analysis. Deployed as a Flask-based web application with secure authentication, Plotly interactive dashboards, and real-time inference APIs, the system facilitates proactive decision-making for transit authorities and scalable passenger information services.

Keywords: CNN-LSTM hybrid model, public transport delays, Recursive Feature Elimination, spatiotemporal prediction, Flask deployment, stratified validation

Abstract: Brand positioning is a core strategic activity that determines how a brand is perceived in relation to competitors in the minds of consumers. In highly competitive and saturated markets, effective brand positioning enables firms to achieve differentiation, build strong brand equity, and sustain long-term competitive advantage. This paper provides an in-depth conceptual analysis of brand positioning by drawing primarily from Keller's Strategic Brand Management framework and supporting branding literature. The study strengthens the methodological foundation through a structured conceptual research design and incorporates a detailed case study of Apple Inc. to illustrate practical application. The paper proposes an integrated brand positioning framework and highlights that clarity, consistency, and customer relevance are critical to successful brand positioning strategies.

Keywords: Brand Positioning, Brand Equity, Strategic Brand Management, Competitive Advantage, Apple Inc.

Abstract: Investigation was conducted at Sri Chamarajendra Zoological Gardens, Mysuru (Latitude: 12.3028° N, Longitude: 76.6552° E) after obtaining the permission from the higher authority to record different behaviours and behavioural changes if any with ring-tailed lemur, Lemur catta (Primate: Lemuridae) during different hours of the day under captive conditions during 2025. L. catta was periodically observed by distance without creating any disturbance for its activity by consulting with Zoological Garden Authority, Animal Caretaker, Education Officer and Biological Scientist. Total 17 parameters were observed and the results revealed quite interesting facts as follows. Except sleeping during morning and negative interaction during afternoon, all the 17 behaviors such as locomotion, drinking, eating, sleeping, resting, vigilance, vocalisation, positive and negative interaction abnormal behaviour, approach, depart, jumping, hanging, grooming, scratching, jumping, chest beating, chasing and sun bathing were shown by L. catta. Analysis of variance of different behaviors of L. catta didn't show significant variation (F=0.599; P>0.05) under captive conditions and demonstrated that L. catta exhibited similar type of behavior during most of the periods in a day under captive conditions. Interestingly, no abnormal behaviour was observed during the present investigation and indicated that L. catta adapted well to captive conditions of Sri Chamarajendra Zoological Gardens, Mysuru.

Keywords: Captive primate, Lemur catta, Zoo, Mysore

Abstract: The objective of this study is to compare the therapeutic effects of hand mudras with the benefits obtained through medicinal treatment alone. A total of 500 participants were included in the study, of which 250 participants relied solely on medicines, while the remaining 250 participants practiced hand mudra yoga for 30 days along with their prescribed medication. The study observed that participants who practiced hand mudras experienced greater improvements than those using medicines alone across several dimensions, including mental calmness, energy levels, quality of sleep, immunity, and emotional stability. Data were analysed using t-tests and descriptive statistics, and the findings empirically validate the positive therapeutic impact of hand mudras. This study highlights the scientific applicability of mudras within the framework of India's traditional medical systems.

Keywords: Mudra therapy, medicinal treatment, yoga, hand mudras, practicality, therapeutic effects, health improvement.

Abstract: The exponential growth in mobile internet usage has dramatically escalated user exposure to malicious webpages, including phishing sites, malware hosts, and obfuscated fraudulent URLs. Conventional blacklist and signature-based defenses prove inadequate against zero-day and dynamically generated threats. This paper introduces a real-time mobile malicious webpage detection framework leveraging a hybrid CNN-LSTM architecture that performs character-level URL analysis to autonomously extract discriminative lexical patterns and sequential dependencies indicative of malicious intent. CNN layers capture localized structural features while LSTM networks model long-range temporal relationships within URL sequences. Deployed via a lightweight FastAPI backend, the system delivers sub-100ms inference suitable for mobile environments. Extensive evaluation on benchmark datasets demonstrates superior detection accuracy (97.8%) and reduced false positive rates (2.1%) compared to traditional ML baselines, establishing this hybrid approach as a robust solution for real-time mobile web security applications.

Keywords: Hybrid CNN-LSTM architecture, character-level URL analysis, FastAPI deployment, zero-day threat mitigation, mobile security, and false positive reduction.

+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 A Systematic Review on the Evolution of Emotional Artificial Intelligence Bhuvnesh Kumar Singh , Dr.Upendra Kumar Srivastava Abstract The evolution of Emotional Artificial Intelligence (EAI) represents a transformative trajectory in the intersection of affective computing, machine learning, and human-computer interaction. This systemic review synthesizes scholarly contributions spanning the past three decades to trace the conceptual foundations, technological advancements, and ethical debates surrounding EAI. Early research emphasized emotion recognition through facial expressions, speech, and physiological signals, while contemporary approaches increasingly leverage multimodal data, deep learning architectures, and generative models to achieve nuanced affective understanding. The review highlights key milestones, including the shift from rule-based systems to data-driven frameworks, the integration of cross-cultural emotion modeling, and the emergence of real-time adaptive agents capable of empathetic responses. Beyond technical progress, the study critically examines challenges such as bias in emotion datasets, privacy concerns, and the implications of embedding emotional intelligence into autonomous systems. By mapping trends and identifying gaps, this review underscores the dual potential of EAI: enhancing human-machine collaboration and raising profound questions about authenticity, ethics, and governance. The findings aim to provide researchers, practitioners, and policymakers with a comprehensive perspective on the trajectory of Emotional AI, guiding future innovation toward equitable, transparent, and socially responsible applications. Downloads: | DOI: 10.17148/IARJSET.2026.13159 How to Cite: [1] Bhuvnesh Kumar Singh , Dr.Upendra Kumar Srivastava, "A Systematic Review on the Evolution of Emotional Artificial Intelligence," International Advanced Research Journal in Science, Engineering and Technology (IARJSET), DOI: 10.17148/IARJSET.2026.13159 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: Cadmium (Cd²⁺) contamination in agricultural soils poses a critical threat to global food security and plant productivity. This study examined Cd²⁺ contamination in soils irrigated with municipal wastewater near an open disposal site in Raiganj, Uttar Dinajpur, West Bengal, and isolated eleven Cd²⁺-resistant bacterial strains from the rhizosphere of Amaranthus viridis L. Among these, strain AF2 exhibited superior multi-metal resistance and was selected for detailed characterization. 16S rRNA gene sequencing identified AF2 as Pseudomonas aeruginosa, with 100% sequence identity to strains BQ26 and NCTC 13628. Growth kinetics in Cd²⁺-amended LB medium revealed concentration-dependent growth delays, while biofilm formation was stimulated at low Cd²⁺ levels (up to 1 mM) but inhibited at higher concentrations. SEM-EDAX analysis confirmed Cd²⁺ bioadsorption via multiple binding sites on the cell wall. AF2 also exhibited diverse plant growth-promoting (PGP) traits, including IAA production, ACC deaminase activity, nitrogen fixation, siderophore production, phosphate solubilization, and Zn solubilization, as well as ammonia and HCN production. In vitro application of AF2 significantly enhanced germination (1.1 to 8-fold), root growth (1.5 to 3.3-fold), fresh weight (1.3 to 1.8-fold), dry weight (1.4 to 2.2-fold), and root-to-shoot ratio of A. viridis seedlings under Cd²⁺ stress. These findings highlight AF2 as a potent bioremediation agent and biofertilizer, capable of mitigating heavy metal toxicity while improving crop yields in contaminated agroecosystems.

Keywords: Heavy metal, Cadmium toxicity, Plant growth promotion, bioremediation, Pseudomonas aeruginosa strain AF2, Amaranthus viridis L., IAA, siderophore, ACC deaminase.

Abstract: The tufted Capuchin, Sapajus paella (Primate: Cebidae) is commonly called 'Black-capped Capuchin' or 'Brown Capuchin' different behaviours were recorded using standard methods at Sri Chamarajendra Zoological Gardens, Mysuru (Latitude: 12.3028° N, Longitude: 76.6552° E) in Karnataka, India during 2025 after obtaining permission from the higher authority. Systematic planning was made in consultation with Range Officer, Animal Caretaker, Education Officer and Biological Scientist to record the behaviours of S. paella during morning, afternoon and evening hours in its enclosure. S. paella was observed by distance without creating any disturbance for its normal activity. Observations were made two times in a week from morning (10.00 AM), afternoon (01.00PM) and evening (04.00 PM) hours for a period of 56 days i.e., from 4th April to 31st May, 2025 using the focal animal sampling method with each session lasting for a period of 20 minutes. Total 17 behaviours were observed and observations were non-invasive and no interaction or interference with the S. paella. The study was conducted under the awareness of Zoological Gardens Authorities and aligned with the ethical standards for observational studies in Zoological Gardens. Results revealed that S. paella species exhibited a clear biphasic activity pattern, with increased physical and social activities during morning and evening periods, and a considerable drop-in activity during afternoon period. Analysis of variance of different behaviors of S. paella did indicate significant variation (F=7.814; P<0.05) under captive conditions. This clearly indicated that S. paella is active during most of the day and not demonstrated any stereotypic or abnormal behaviours that indicated the overall good welfare of the animal under captive conditions of Sri Chamarajendra Zoological Gardens.

Keywords: Tufted Capuchin, Sapajus paella, captive conditions, Sri Chamarajendra Zoological Gardens, India

Abstract: This paper investigates the extraordinary capability of Man-made consciousness in customizing showcasing systems. It digs into the hypothetical underpinnings of customer association sand researches how Man-made reasoning can be utilized to foster designated and pertinent promoting encounters. Man-made consciousness can customize messages in view of buyer conduct and socioeconomics, affecting the handling course and expanding contribution. This hypothesis investigates the utilization of game mechanics to inspire and connect with clients. Artificial intelligence can customize showcasing encounters, fitting prizes and difficulties to individual purchaser inclinations, driving further inclusion. Calculations can dissect huge measures of client information to foresee individual inclinations and ways of behaving. This considers designated promoting, item suggestions, and content that resounds with explicit purchaser portions. Regular Language Handling, Computerized reasoning - fueled apparatuses break down client surveys, virtual entertainment discussions, and different types of unstructured information. This permits brands to grasp client opinion and customize correspondence styles for ideal contribution Computerized reasoning - controlled talk bots and remote helpers can give customized client assistance and item proposals progressively, cultivating a more intelligent and connecting with brand insight. Likely Advantages and Contemplations Customized advertising messages and encounters take care of individual requirements and inclinations, prompting higher fulfillment and reliability.

Keywords: Artificial Intelligence, Consumer Involvement, Marketing Techniques.

Abstract: This research investigates how group cohesion impacts social loafing and individual effort. Social loafing, a decrease in individual effort within groups, undermines productivity, while group cohesion, reflecting team unity, may counteract this. Through quantitative analysis of employee survey data, we found a significant negative correlation between cohesion and social loafing, indicating that cohesive groups foster greater individual accountability and motivation. This study highlights the critical role of group cohesion in improving team performance and reducing social loafing in organizational settings.

Keywords: Group Cohesion, Social Loafing, Team Performance, Individual Motivation, Employee Effort, Workplace Dynamics, Organizational Behaviour.

Abstract: In today's fast-evolving business landscape driven by the Fourth Industrial Revolution (4IR) and swift technological changes, organizations are under continuous pressure to remain agile and competitive. Because of this, reskilling and upskilling are becoming more and more important as proactive approaches to workforce growth. Examining how reskilling and upskilling affect satisfaction with work, efficiency, and organizational success is the goal of this study, which focuses on a few chosen fast-moving consumer good companies. Full-time employees were given structured questionnaires to answer in order to gather data, which was then analysed using both inferential and descriptive statistical methods. The results show that initiatives for ongoing skill development. The study comes to the conclusion that spending money on reskilling and upskilling improves employee's resilience, output, and retention in addition to filling in current skill gaps. As a result, companies are urged to put in place continuous learning initiatives that complement their objectives and the desires of their workforce.

Keywords: Reskilling, Upskilling, Employee Development, Job Satisfaction, Career Growth.

Abstract: This study aims to assess individual assesses Tax planning Awareness and management, examining its relationship with demographic factors. It focuses on the significance of professional guidance in tax return filing and planning. Data was collected from 100 individual taxpayers in Hyderabad through a structured Google Docs questionnaire. Understanding tax rules is vital for efficient tax planning in India, where personal income tax significantly affects earnings. Taxpayers with income above a specified threshold are required to pay taxes, necessitating comprehensive knowledge of tax regulations. Effective tax planning involves staying informed about annual tax laws and strategically investing in tax-saving instruments to maximize benefits without evading taxes. The research explores how tax awareness and planning influence wealth creation through investments sanctioned by tax laws. By utilizing these investment avenues, taxpayers can reduce their tax burden and accumulate wealth over time. The study aims to show how tax awareness and planning help individuals build a robust investment portfolio, enhancing their financial stability. Tax planning is an essential aspect of financial planning, allowing individuals to minimize tax liabilities by leveraging exemptions, deductions, rebates, and allowances while ensuring investments align with long-term objectives. The study identifies the most popular tax-saving instruments and the extent of savings they provide. Findings reveal that Life Insurance policies are the most widely used tax-saving instrument, followed by Provident Funds.

Keywords: Tax Awareness, Tax Planning, Tax Saving investment, Hyderabad city, Income tax, Financial planning, wealth creation

Abstract: This study aimed to examine the factors affecting customers' decision to use digital banking service in Commercial Bank of Ethiopia. This study used both primary and secondary data. The primary data was gathered through questionnaire distributed to a target of 384 respondents from customers of the selected branches using simple random sampling. And secondary data collected from the existing bank manuals and other sources. Both Quantitative and qualitative research approaches were used to analyse the collected data. The researchers used both descriptive and explanatory research designs for accomplishment of the study. The collected data was analysed using Statistical Package for Social Science (SPSS 2.0). The relationship and influence of the factors was analysed using Pearson correlation and multiple regressions. The researcher Revealed that the explanatory variables on electronic banking service, such as technology, income, speed, security, and demographic factors was identified as significant effects on e-banking adoption. Approaches were also be suggested to enrich the e-banking services including making websites more user-friendly, reducing users risk concerns and the role of government in terms of improving ICT infrastructure. Finally, to bring about sustainable adaptation of e- banking services by financial institutions which best serves the customer needs, more research works are suggested to be done to further analyse the participation of digital banking services to the larger economic transactions. This research will help banks about how to give information related to the system to its customers.

Keywords: Banking, Customer decision, Digital banking; Commercial bank of Ethiopia