Volume 13 | Issue 5 |

 Abstract

This paper presents Campus Commute, a campus-exclusive ride-sharing application designed to provide secure, efficient, and affordable transportation solutions for college students and faculty members. Unlike commercial ride-hailing platforms, Campus Commute restricts its users to verified members of the college community, ensuring a safer and more familiar commuting environment. The system integrates real-time ride booking, GPS tracking, student ID verification, and emergency support features. It leverages modern mobile technologies to enhance user experience while promoting eco-friendly travel through ride-sharing among peers.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

College, Riding, Pooling

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Automatic gender classification and age detection may be a fundamental task in computer vision which has recently attracted immense attention. Here, a new type of intelligent system which is based on several neural networks connected on two levels of classification with an efficient and simple Convolutional Neural Network (CNN) model architecture by considering gender and age estimation as a multi-label classification problem. The proposed model is trained and then evaluated on the publicly available audience benchmark dataset. The model first performs feature extraction on the input image which can classify eyes, lips, beard, hair etc supporting these featured the model will classify the gender as male or female. Here we have used the Haar Cascade for feature extraction purpose. Age is estimated with the assistance of Caffe Model. We have used various detection methods for analysis like skin colour Segmentation and lip detection and many more. The CNN model is built by using VGG-16 architecture. The CNN model is then trained using epochs, where each epoch contains a certain number of training images. To remove distorted and unwanted images, the loss Gauss function is used. For testing, the input image is given by the user. The model makes the predictions to estimate age, gender and emotion of that input image by comparing with the trained images.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Convolutional Neural Network, Recurrent Neural Network, Support Vector Machines, Deep EXpectation, Generative Adversarial Network, Conformal Embedded Analysis

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The study was conducted with an aim to assess and improve the knowledge and attitude of school teachers regarding first aid skills, to promote safety in school environments and encourage prompt and effective management of emergencies. A descriptive research design was used for the study in order to evaluate the existing knowledge and attitude regarding first aid among teachers of selected schools at Charar-I-Sharief, Budgam, Jammu and Kashmir. A total of 60 teachers were selected through convenient sampling technique from the accessible population. Data was collected using structured questionnaires and attitude scale for assessing knowledge and attitude respectively. The main study was conducted over a period of four weeks. The data collected was analyzed using descriptive and inferential statistics.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Knowledge, Attitude, First Aid, CPR, Wound, Bleeding

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The present paper examines the effects of new economic reforms on the livelihoods and development of marginalized groups in India. Marginality addresses the socio-cultural and human issues faced by individuals from diverse segments of society, including Scheduled Castes, Scheduled Tribes, impoverished farmers, laborers, artisans, and others. Agriculture serves as a fundamental component of the Indian economy, with many marginalized groups in rural areas relying on it as their traditional means of sustainable livelihood. The livelihood project serves as a strategic initiative aimed at empowering individuals to enhance their economic value, optimize production systems, and promote social justice. The policies of New Economic Reforms (NER, 1991) have multiple dimensions that have affected vulnerable communities both favorably and unfavorably. Since the emergence of LPG, there has been an increase in GDP growth and a favorable impact on various factors. These measures have also resulted in the excessive exploitation of natural resources in rural India, upon which the marginalized masses depend. Finally, this paper includes necessary recommendations for future research work.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

New economic reforms, marginalised groups, liberalization, privatization, globalization, sustainable livelihood

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

In the ever-evolving landscape of education, traditional learning management systems (LMS) often fail to cater to the diverse needs of students pursuing different career paths. Pathwise Academy is an adaptive learning platform designed to provide personalized learning experiences for college students. This research paper presents the architecture, methodologies, and potential impact of Pathwise Academy in assisting students to navigate multiple career options while still in college. The system leverages machine learning (ML) algorithms to analyze student progress, recommend tailored learning paths, and integrate real-world career insights. By combining data analytics, career-based recommendations, and interactive learning modules, Pathwise Academy aims to bridge the gap between academic learning and career readiness. This study highlights the significance of personalized education in improving student engagement, retention, and employability. The research further evaluates the performance of the system through empirical analysis, user feedback, and industry relevance. The findings indicate that adaptive learning frameworks like Pathwise Academy can significantly enhance students' ability to make informed career decisions, ultimately reducing dropout rates and increasing job market readiness.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Personalized Learning, Learning Management System (LMS), Artificial Intelligence, Career Guidance, College Education, Machine Learning, Adaptive Learning

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The aim of this study is to explore the potential of sentiment analysis on election news article titles using machine learning techniques and to determine the most effective methods for text representation in this context. Traditionally, sentiment analysis has relied on part-of-speech tagging and word polarity counts, which work well in broad domains and when large labeled datasets are unavailable. However, in more specific domains with pre-labeled data, supervised learning methods are more suitable. This thesis evaluates the performance of a Convolutional Neural Network (CNN) and a Support Vector Machine (SVM) on various datasets, which were designed to capture different linguistic features

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Sentiment Analysis Feature Selection of Newspaper Articles on Election

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This article explores the complex relationship between folklore and mind culture, focusing on how traditional narratives are shaped by cognitive processes. Folklore, as a repository of collective wisdom and social memory, plays a crucial role in the development and transmission of cultural knowledge. By examining the cognitive roots of folklore, the article investigates how stories, myths, and legends are not only vehicles for cultural identity but also function as cognitive tools that influence perception, memory, and understanding of the world. The article examines how traditional narratives serve as cognitive templates, organizing and simplifying complex social and natural phenomena. These narratives are passed down through generations, reinforcing shared values, norms, and social roles while also adapting to changing cultural contexts. The article also explores how folklore impacts individual and collective memory, particularly in how myths and stories are internalized and recalled within the cultural consciousness. Through the mind culture, this study highlights the dynamic interaction between individual cognition and the broader cultural narratives that shape it. . By understanding these cognitive processes, the article offers new insights into the function of folklore not only as a cultural artifact but as an active component in the cognitive landscape of human societies

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

folklore, mind culture, narratives

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Modern distributed systems demand dynamic and intelligent load balancing to ensure optimal performance, high availability, and fault tolerance. Traditional load balancers often follow static routing strategies that fail to adapt to real-time backend conditions such as latency spikes, load variation, or system failure. This paper proposes an AI/ML-based intelligent load balancer that leverages machine learning algorithms to select the most suitable backend server based on live metrics including load, latency, and failure rate. The proposed system integrates Decision Tree, Random Forest, and XGBoost models to predict optimal routing paths, supported by real-time health checks and CSV-based metric logging. Among the models tested, XGBoost demonstrated the highest accuracy and was deployed in a Flask-based microservice architecture for intelligent request redirection. The results indicate a marked improvement in success rate and resource efficiency when compared to traditional random backend selection. This work enhances routing precision, improves infrastructure reliability, and lays the foundation for intelligent backend management in cloud-native and large-scale distributed systems.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Load Balancing, Machine Learning, Artificial Intelligence, Backend Optimization, Predictive Routing, System Reliability

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This paper presents a dynamic education application developed using the LangChain LLM framework and LangGraph agent architecture to enhance personalized learning and educational management. The system integrates a context-aware conversational agent, built with LangGraph, enabling users to interact with educational content, manage resources, and receive tailored assistance. Core functionalities include automatic quiz generation based on user-provided titles or topics, class-wise report generation from SQL database records, and AI-powered report writing that leverages large language models for insights and recommendations. A centralized dashboard visualizes student performance data, supporting educators in tracking progress and identifying areas for improvement. Additionally, the platform offers a student management system for maintaining student records and managing learning resources such as quizzes and PDFs. By combining conversational AI with database-driven insights, the application provides an interactive, data-informed, and agent-based solution for modern educational environments.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Langchain , LangGraph, Conversational Agent, Matplotlib, Dynamic Education System, Quiz Generation, Student Performance Dashboard

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Predicting crop yields is a pivotal aspect of modern agriculture, directly influencing farmers' incomes and a nation's food security. However, traditional crop yield forecasting often overlooks crucial factors like soil quality, focusing primarily on weather. This paper introduces a novel machine learning method that integrates soil nutrients with rainfall data, significantly enhancing the precision of predictions. This study demonstrates the effectiveness of this innovative approach by leveraging past data and advanced machine learning techniques such as Random Forest, Support Vector Machines, and Gradient Boosting. The results underscore the importance of considering soil and weather information, as it markedly improves prediction accuracy, providing invaluable insights for farmers and agricultural experts.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Crop Yield Prediction, Machine Learning, Soil Nutrients, Rainfall, Agriculture, Data Science, Predictive Modelling, Sustainability, Food Security

  License

Creative Commons Attribution 4.0 and The Open Definition