Volume 13 | Issue 5 |

 Abstract

This study aims to explore the factors influencing employees investment decisions, With the growing importance of financial independence and investment planning, understanding the role of financial literacy, risk tolerance, and demographic factors in shaping investment behavior is crucial. A structured questionnaire was administered to 201 employees using simple random sampling. Both primary and secondary data were collected and analyzed using non-parametric tools (Kruskal-wallis H test, Mann-whitney and correlation). The findings reveal that financial literacy and risk tolerance significantly impact employees investment decisions, while demographic factors such as age, income, education, and marital status also play a critical role. The study concludes that higher financial literacy and risk-taking ability lead to more confident and diversified investment behaviors.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Financial literacy, Risk tolerance, Demographic factors, Non-parametric tools, Investment decision.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Geographic Information Systems (GIS) have transformed with the integration of data science, enabling advanced spatial analysis, predictive modeling, and decision-support across fields like urban planning, environmental science, and public health. This review explores how machine learning (ML), spatial statistics, and big data are revolutionizing GIS, covering foundational techniques such as supervised/unsupervised learning for geospatial pattern recognition (e.g., land cover classification using CNNs), spatial regression models (e.g., geographically weighted regression) for localized predictions, and graph-based analytics for network-constrained problems like traffic flow optimization. Real-world applications include precision agriculture through crop yield prediction using satellite imagery and IoT sensor fusion, disaster response with real-time flood mapping via social media geodata and hydrological models, and smart cities using ML-driven urban sprawl simulation and infrastructure planning. The paper also critically examines challenges like data heterogeneity, computational scalability, and ethical concerns (e.g., location privacy), and highlights emerging trends such as AI-powered GIS automation and the potential of quantum computing for spatial data, proposing future research directions.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Geographic Information Systems (GIS), Data Science, Spatial Machine Learning, Big Geospatial Data, Remote Sensing, Spatial Optimization, Urban Informatics, Environmental Modeling, Geoprivacy, AI-Driven GIS

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This project presents an integrated system combining computer vision, deep learning, and IoT-based V2V (Vehicle-to-Vehicle) communication to improve road safety and enable smarter transportation solutions. The system is developed in three main stages. First, a real-time lane detection module is implemented using Python and OpenCV. It employs image processing techniques such as color thresholding, edge detection, and Hough Transform to accurately identify lane boundaries from a live camera feed, enhancing driver assistance and road alignment. Second, object detection is performed using the YOLOv3 deep learning model, which identifies surrounding vehicles, pedestrians, and other road objects from real-time video frames. YOLO's high-speed and accurate detection capability makes it suitable for safety-critical environments. The model processes input frames, applies non-maximum suppression to eliminate duplicate detections, and marks detected objects with bounding boxes and labels. Third, the V2V communication system is developed using the ESP32 microcontroller and IoT platform Blynk. This system monitors temperature and collision status using a DHT11 sensor and digital input pin. When critical conditions such as engine overheating or accidents are detected, alerts are displayed on an LCD and transmitted to a mobile application via Wi-Fi, enabling remote awareness. All three components work together to provide a robust and real-time vehicle monitoring and safety system. This approach not only aids in lane discipline and object awareness but also ensures timely communication in emergencies. The integration of vision-based detection, AI models, and IoT connectivity forms a foundation for future autonomous and connected vehicle technologies.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Vehicle Trajectory Prediction, Long Short-Term Memory (LSTM), Vehicle-to-Vehicle Communication (V2V), Deep Learning, Time Series Forecasting, Intelligent Transportation Systems (ITS), Autonomous Vehicles, Neural Networks, Real-time Prediction, Safety and Collision Avoidance.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This project focuses on developing an innovative solution to combat cryptographic ransomware using AI-driven Honeypots, BiLSTM (Bidirectional Long Short-Term Memory) model, and Format Preserving Encryption (FPE). The system autonomously detects and defends against ransomware attacks by analyzing behavior patterns, protecting critical data, and continuously adapting to new attack techniques.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Ransomware, Cryptographic ransomware, AI-Driven Honeypots, BiLSTM (Bidirectional Long Short-term Memory), Format Preserving Encryption (FPE), Behavior patterns.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

CAPTCHAs are widely used to differentiate between human users and automated bots, ensuring security in online interactions. However, traditional CAPTCHA systems often suffer from usability issues and vulnerabilities to evolving machine learning-based attacks. This research presents a novel machine learning-driven approach to refining CAPTCHA mechanisms, enhancing both security and user experience. Our proposed solution leverages deep learning models to analyse and improve CAPTCHA complexity, making it more resistant to automated solvers while maintaining accessibility for genuine users. By utilizing advanced image processing and adaptive challenge generation techniques, the system dynamically adjusts CAPTCHA difficulty based on real-time threat analysis, reducing friction for legitimate users while thwarting bots. Experimental results demonstrate that our approach significantly improves CAPTCHA robustness against automated attacks while ensuring a seamless experience for human users. This research contributes to the ongoing development of secure and user-friendly authentication mechanisms, bridging the gap between security and usability in modern web applications

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

CAPTCHA Security, Machine Learning, Deep Learning, Automated Bot Detection, Adversarial attacks.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Built with Next.js, the AI-Driven Examination System is a web application that employs machine learning to give adaptive tests and feedback to enhance student performance. The program looks at factors including time-per-question, subject-wise accuracy, and difficulty-level performance to identify individual learning gaps. A Flask-based machine learning model processes this data to provide personalized test recommendations, which are subsequently stored in MongoDB and shown on a dynamic dashboard. The disadvantages of traditional "one-size-fits-all" exams are removed with this approach, which offers personalized practice and real-time progress tracking. The system demonstrates a scalable approach to personalized learning by fusing modern web technologies (Next.js, Tailwind CSS) with artificial intelligence (scikit-learn, TensorFlow).

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

AI in Education, Adaptive Assessments, Next.js, MongoDB, Machine Learning, Flask

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This paper presents an advanced Optimal Power Flow (OPF) strategy that integrates the Line Utilization Factor (LUF) index with the Harris Hawks Optimization (HHO) algorithm for optimal reallocation of generator outputs in the presence of a Thyristor Controlled Series Capacitor (TCSC). The objective is to minimize real power losses and voltage deviation while enhancing system stability. The proposed method is implemented on the IEEE 57-bus system under normal operating conditions. The LUF index is utilized to identify the most critical transmission line, with the weakest line (8-9) compensated by installing a TCSC. The HHO algorithm is employed to solve the multi-objective OPF problem, ensuring efficient generator dispatch and improved voltage profiles. Simulation results demonstrate that the inclusion of TCSC, guided by LUF and optimized via HHO, significantly improves power system performance by reducing losses, stabilizing voltages, and lowering generation costs. This study confirms the effectiveness of combining LUF-based line assessment with HHO for robust and intelligent power system optimization.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Harris Hawks Optimization (HHO), Thyristor-Controlled Series Capacitor (TCSC), Optimal Power Flow (OPF), Power Management, Voltage Stability, Real Power Losses, Line Utilization Factor (LUF), Generator Reallocation, Transmission Line Optimization, Multi-Objective Optimization, Power System Performance, IEEE 57-Bus System.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

English serves as a global language. It plays a significant role in various developed and developing fields. Mastering English has become essential for everyday life. However, there are challenges in acquiring English, particularly for students studying in Tamil medium. Grammar forms the foundation of any language. Specifically, verb tenses are crucial for constructing sentences. This study investigates the effectiveness of Grammar Games in enhancing English teaching among Tamil Medium students at high school level. Grammar Games, encompassing planning, monitoring, and evaluating cognitive processes are increasingly recognized as powerful tools for fostering and deep understanding and academic success. The research employs quantitative analysis of post-test scores of control and experimental groups. High School students are exposed to Grammar Games interventions tailored to English learning tasks, with a focus on self-regulation, reflection, and goal-setting. Results indicate significant improvements in students' English language knowledge, critical thinking skills, and self-efficacy following the implementation of grammar games.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Grammar Games, critical thinking and goal-setting

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The emergence of digital hiring platforms has significantly reshaped recruitment practices across diverse industries, offering highly scalable and efficient methods for identifying, attracting, and acquiring talent, thereby improving the overall effectiveness and speed of the hiring process. This study investigates the role of recruitment metrics in evaluating the effectiveness of digital hiring platforms, aiming to identify and analyse key performance indicators that measure their efficiency, cost-effectiveness, and overall quality in organizational recruitment processes.Structured questionnaires were used to gather primary data from the employees and secondary data is collected from research papers, journals, research scholars. A descriptive research design was adopted, with a 110-sample size determined via the Morgan table, employing Mann-Whitney and Annova.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Recruitment Metrics, Recruitment Strategies, Business Goals, Digital Hiring Platforms, Candidate Quality, Recruitment Tools, Data-Driven Decision

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

In the current fast-evolving and competitive market, companies are feeling increasing pressure to follow sustainable strategies, seeking a balance between an economic, an environmental and a social performance. This study examines the concept of Green HRM and Lean Manufacturing in enhancing operational performance in a manufacturing company. The objective of this study was made and assessed. The data were collected from 152 respondents through questionnaire and analyzed with statistical tools such as Mann Whitney U test, Kruskal Wallis H test and Spearman's Rank Correlation. The results indicate a significant and positive relationship between the implementation of both Green HRM as well as lean manufacturing practices with the performance levels of the organization. The study concludes with a set of recommendations for improving existing practices and integrating them with long-term sustainability goals.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Green HRM, Lean Manufacturing, Operational performance, Sustainability.

  License

Creative Commons Attribution 4.0 and The Open Definition