Category Archives: Uncategorized

Authors: Aditiya Sawant, Devansh Sojitra, Rohan Maheta

Abstract: In modern educational environments, a significant number of students face learning difficulties due to slower cognitive processing, limited conceptual understanding, low confidence, and the inability of traditional teaching systems to address individual learning needs. These students, commonly referred to as slow learners, often require personalized academic support and innovative teaching strategies to achieve educational success. This paper presents Supporting Slow Learners with Remedial Innovation, an intelligent and inclusive educational support platform designed to enhance the academic performance and confidence of slow learners through customized remedial solutions. The proposed system integrates personalized learning plans, adaptive teaching methodologies, educator guidance, progress monitoring, and technology-assisted learning resources to create a supportive learning ecosystem. The platform allows educators to identify student weaknesses, assign customized study materials, track academic progress, and provide targeted interventions based on individual performance. Students can access simplified learning content, practice modules, motivational feedback, and continuous assessments according to their pace of learning. The system is developed using modern web technologies with a scalable frontend-backend architecture to ensure accessibility, usability, and performance. It supports multiple user roles including students, educators, and administrators for efficient management and monitoring. Experimental outcomes indicate improvements in student engagement, learning consistency, conceptual understanding, and confidence levels when compared with conventional classroom-only teaching approaches. This project demonstrates how remedial innovation combined with digital technologies can transform the educational journey of slow learners by promoting equal learning opportunities, reducing academic gaps, and creating an inclusive learning environment. The proposed framework can be extended in future with Artificial Intelligence, predictive analytics, and multilingual learning support for wider educational impact.

DOI: http://doi.org/

Published by: vikaspatanker

Authors: Jyoti Gupta, Ayush Patel, Siddharth Prabhudesai, Rahul Neve

Abstract: Customer churn prediction plays a vital role in helping businesses retain customers and minimize revenue loss in competitive markets. This study focuses on developing a predictive framework to identify customers who are likely to discontinue a service based on historical data. The dataset used in this project consists of customer demographic, behavioral, and financial attributes, which are preprocessed and transformed through feature engineering techniques to improve model performance. Multiple machine learning classification models are implemented and evaluated to determine their effectiveness in predicting churn. To address the issue of class imbalance, appropriate techniques are applied to ensure fair model training. The models are assessed using key performance metrics such as accuracy, precision, recall, F1-score, and ROC-AUC, providing a comprehensive comparison of their predictive capabilities. The analysis highlights the importance of factors such as customer tenure, service usage patterns, and billing characteristics in influencing churn behavior. The results demonstrate that machine learning models can effectively capture underlying patterns in customer data and provide reliable predictions. This study offers valuable insights into churn prediction and presents a data-driven approach that can support businesses in designing targeted customer retention strategies.

DOI: https://doi.org/10.5281/zenodo.19692500

Published by: vikaspatanker

Authors: Kanuri jai sai Prakash, Challa uday kiran, Gugilla Harshith, V.vidya sagar

Abstract: With the aid of a specially designed Graphical User Interface (GUI), a combination of Machine Learning and Deep Learning techniques was used to detect brain strokes. Images of "Stroke" and "Normal" cases were categorized from a dataset. Following the loading of the dataset, preprocessing and feature extraction were carried out, and then the data was divided into training and testing sets. The Convolutional Neural Network (CNN) algorithm achieved a significantly higher accuracy of 98% than the Support Vector Machine (SVM) algorithm, which only managed 59%. CNN outperformed SVM in stroke image classification, according to comparative analysis. The trained CNN model was then applied to new test image prediction, effectively differentiating between normal and brain cases. These findings demonstrate how well deep learning techniques work for precise Brain stroke detection from medical images. A crucial medical application that makes use of contemporary technologies like machine learning (ML) and deep learning (DL) for early stroke diagnosis and prediction is brain stroke detection. The automatic detection of ischemic and hemorrhagic strokes from CT and MRI scan images is the main focus of this study. Support Vector Machines (SVM), Random Forest (RF), and Logistic Regression are important algorithms for classification tasks. Images are classified, features are extracted, and stroke-affected brain regions are segmented using deep learning models, specifically Convolutional Neural Networks (CNNs) and Artificial Neural Networks (ANNs). Key procedures for the project include image enhancement, data preprocessing, and model training with frameworks like PyTorch, TensorFlow, or Keras. Metrics like accuracy, precision, recall, and F1-score are used to assess these models' performance. The accuracy of the model's stroke prediction is improved by adding clinical data, such as blood pressure, diabetes, smoking patterns, and other risk factors. Building an effective clinical decision support system that can aid in the early detection of strokes is the ultimate goal, as it may lower the death and disability rates related to cerebrovascular accidents (CVA).

DOI: https://doi.org/10.5281/zenodo.19691995

Published by: vikaspatanker

Authors: Noyal Biju, Dharunkumar C, Aziz Pardiwala, Abhishek Pillai

Abstract: Accurate and timely detection of brain tumors is a critical challenge in medical imaging, directly influencing treatment planning and patient prognosis. Conventional diagnostic approaches based on manual interpretation of Magnetic Resonance Imaging (MRI) scans are often limited by subjectivity, inter-observer variability, and increasing workload on radiologists. This study presents a robust deep learning–driven framework for automated brain tumor detection and classification, leveraging advanced Convolutional Neural Network (CNN) architectures. The proposed model employs a transfer learning approach using a pre-trained VGG16 network, fine-tuned on a curated dataset of MRI images to capture domain-specific features. A comprehensive preprocessing pipeline—including image normalization, resizing, denoising, and intensity standardization—is integrated with data augmentation techniques to address class imbalance and enhance generalization. The architecture incorporates fully connected layers with dropout regularization to mitigate overfitting and improve model stability Model performance is rigorously evaluated using standard metrics such as accuracy, precision, recall, F1-score, and Area Under the Receiver Operating Characteristic Curve (ROC-AUC). Experimental results demonstrate high classification performance, indicating the model’s capability to effectively distinguish between tumor and non-tumor cases. Furthermore, comparative analysis with baseline models highlights the superiority of the proposed approach in terms of feature extraction efficiency and predictive accuracy. The system offers significant potential for real-world clinical integration by reducing diagnostic latency, minimizing human error, and providing decision support for radiologists. This research underscores the transformative role of deep learning in medical image analysis and establishes a scalable foundation for future advancements, including multi-class tumor classification and explainable AI-driven diagnostics.

Published by: vikaspatanker

Authors: Mr.M.Aakash, K. Kaviya, S. Lavanya, K. Mounika

Abstract: Deep, coordinated reforms in the areas of energy, industry, cities, 6 and government are required by India's Viksit Bharat 2047 aim. According to this analysis, if policy, funding, and infrastructure all work together, electric mobility can be a potent, all-encompassing tool that creates new industrial jobs, cleaner air, reduced greenhouse gas emissions, and increased energy security. Based on government plans (NEMMP; FAME I & II; PM-E-Bus Sewa; PLI for Advanced Chemistry Cells), major institutional reports (IEA; NITI Aayog; CEEW; WRI; TERI; World Bank), lifecycle and grid studies, and evidence at the state level, the paper summarizes findings on emissions savings, total cost of ownership, depot and charging needs, battery supply-chain risks, and institutional capacity gaps. Research indicates that electrifying high-use vehicles, such as buses and three-wheelers, results in the greatest reductions in emissions and improvements in air quality per rupee spent; those electrifying depots and coordinating with DISCOMs is necessary for dependable bus operations; and that increasing domestic battery capacity is essential to reducing reliance on imports and generating green manufacturing jobs. High upfront costs for fleets and STUs, metro-concentrated charger networks, geopolitical dangers surrounding vital minerals, and inadequate coordination between ministries and utilities are still major challenges. The analysis concluded that if electric mobility isViksit Bharat, it needs be integrated into a long-term, 2047-aligned roadmap that integrates battery circularity, innovative finance, renewable energy growth, and STU capacity building.

</p

Published by: vikaspatanker

Authors: Sunkara Sravallika, Banala Sai Revanth, Madasi Hema, M Efraiem, Bharat Tank

Abstract: The main focus of this project is to develop an intelligent, user-friendly portfolio generation platform and examine the effectiveness of template recommendations using machine learning techniques during the development and deployment phases. To carry out this project, two stages are considered — the frontend/template development phase and the backend/ML integration phase — with the completion of the frontend serving as the baseline milestone. The frontend/template phase covers the design and implementation of interactive UI components, template layouts, and live preview functionality, whereas the backend/ML phase covers API development, data handling, template recommendation algorithms, and export functionalities. The completed system uses data provided by users — including skills, education, experience, and achievements — as the sample input for generating customized portfolios. A recommendation engine, employing embedding-based similarity search and rule-based heuristics, is integrated to suggest templates best suited to the user’s industry and expertise. System evaluation considers performance metrics such as recommendation accuracy, export reliability, and user experience responsiveness as control variables. Findings from internal testing indicate that the frontend design and predefined templates significantly improve the user’s ability to customize portfolios efficiently during the pre-integration phase. In the post-integration phase, it is observed that the machine learning model enhances personalization, while backend optimizations ensure reliable export. In terms of system-specific factors, it is found that a clean template structure and low-latency API responses improve usability and adoption rates.

Published by: vikaspatanker

Authors: Darshankumar Patel

Abstract: The Indian wedding and event planning industry, valued at over INR 3 lakh crore annually, remains largely fragmented and dependent on manual processes. This paper presents Happenings and Happiness, a comprehensive dual-role Android application that digitizes the complete wedding planning lifecycle for both event organizers and service vendors. The system integrates Firebase Firestore for real-time data synchronization, Firebase Cloud Messaging (FCM) V1 API with JWT-based OAuth2 authentication for push notifications, RazorPay payment gateway for secure transaction processing, and Cloudinary for cloud-based media management. The application implements real-time bidirectional chat, vendor discovery and booking management, guest list management, budget tracking, and an earnings analytics dashboard. The dual-role architecture supports seamless interaction between users and vendors within a single application while maintaining strict role-based data access through Firestore security rules. Performance evaluation demonstrates sub-second message delivery in real-time chat, reliable push notification delivery across both user roles, and consistent UI performance across Android 10–14 devices. The system addresses critical gaps in existing wedding planning applications by providing an end-to-end digital solution tailored for the Indian market.

Published by: vikaspatanker

Authors: Abubakar Umar Hamza

Abstract: The rapid advancement of artificial intelligence (AI), particularly deep learning and large-scale neural networks, has created significant demand for high-performance and energy-efficient computing architectures. Conventional electronic processors such as GPUs and TPUs are increasingly constrained by power consumption, memory bandwidth limitations, and data movement bottlenecks. In response, photonic neural networks and optical AI accelerators have emerged as promising alternatives that exploit the properties of light to perform computation at high speed and low energy consumption. This paper presents a comprehensive systematic narrative review of photonic neural networks and optical AI accelerators, focusing on their architectures, material platforms, and key engineering challenges. The methodology employed involves structured literature collection from recent peer-reviewed studies, thematic classification of photonic architectures (including Mach–Zehnder interferometer meshes, microring resonator networks, and diffractive optical systems), and comparative analysis of material platforms and performance metrics such as energy efficiency, scalability, and computational latency. The results of the review indicate that photonic systems offer significant advantages over electronic computing, particularly in terms of energy per multiply–accumulate operation (femtojoule-level), ultra-high bandwidth (terahertz range), and low-latency computation. However, practical deployment remains limited by challenges in scalability, fabrication variability, noise sensitivity, and the lack of efficient optical training mechanisms. The analysis further shows that hybrid photonic–electronic architectures currently represent the most viable pathway toward near-term implementation, while heterogeneous material integration is essential for achieving fully functional photonic AI systems. The contribution of this research lies in providing a structured and critical synthesis of recent advancements in photonic AI hardware, identifying key technological bottlenecks, and outlining future research directions toward scalable and commercially viable optical computing systems. This work serves as a reference framework for researchers working at the intersection of photonics, electronics, and artificial intelligence.

DOI: https://doi.org/10.5281/zenodo.19686160

Published by: vikaspatanker

Authors: E Umachandrika, Dr L Sangeetha

Abstract: The construction of masculinity in African literature, particularly in the works of Chinua Achebe, has often been interpreted through the lens of tradition, authority, and patriarchal dominance. However, a closer examination reveals that Achebe’s narratives not only depict but also interrogate and complicate these masculine ideals. This article explores how masculinity is constructed, performed, and ultimately destabilized in Achebe’s major novels, with particular attention to the relationship between gender and leadership. By analyzing key texts such as Things Fall Apart, No Longer at Ease, and A Man of the People, the study argues that Achebe simultaneously represents and critiques patriarchal structures embedded within Igbo society and postcolonial governance. Drawing on postcolonial theory and gender studies, the paper examines how leadership is coded as masculine and how this coding contributes to both personal and societal crises. Furthermore, it highlights the often-overlooked roles of female characters and alternative masculinities that challenge dominant norms. The article ultimately contends that Achebe’s fiction offers a nuanced critique of patriarchal authority, suggesting the need for a reimagined model of leadership that transcends rigid gender binaries.

Published by: vikaspatanker

Authors: Aryan D. Vekariya

Abstract: When working across different devices, moving a file securely from a phone to a laptop is surprisingly annoying. People usually end up emailing files to themselves or logging into a cloud drive just for one small transfer. This not only wastes time but also leaves junk data sitting on third-party servers forever. To fix this, we built QuantumDrive, a simple web app that lets you transfer files directly without forcing you to make an account. We used React for the frontend and Node.js for the server. Instead of saving your files permanently, the app encrypts them right inside your browser. The receiver then downloads the file using a temporary QR code, and the file gets deleted from the server shortly after. This paper explains how we designed the app, how the encryption works, and what we learned while building it during our internship.

Published by: vikaspatanker