Authors: Dr. Meghna Utmal, Sakshi Singh, Kunti Uikey, Vaishali Gupta, Sajal Pandey

Abstract: — Heart disease remains a major health concern worldwide, affecting a large proportion of the global population. According to reports by the World Health Organization (WHO), approximately 17.9 million deaths occur annually due to cardiovascular diseases. In the context of the COVID-19 pandemic and its post-infection complications, cardiac failure has emerged as a commonly observed condition, highlighting the critical need for early diagnosis and prediction of heart disease to enable effective prevention. Timely detection can significantly reduce mortality rates. Recent advancements in machine learning techniques have greatly contributed to the healthcare sector, particularly in the prediction of heart diseases, thereby saving numerous lives. This paper presents an efficient ensemble-based machine learning approach for predicting heart-related disorders, achieving an accuracy of 88.52%.

DOI: https://doi.org/10.5281/zenodo.19882012

Published by: vikaspatanker

Authors: Nv Subhasri, Madhunisha. A, Shruthi. T

Abstract: This dissertation examines the growing intersection of law, technology, and regulation in the context of autonomous vehicles (AVs) in India, with particular emphasis on issues of privacy, data protection, and cybersecurity. It analyzes existing Indian legal frameworks, such as the Information Technology Act and the proposed Personal Data Protection Bill, to assess whether they are equipped to handle the unique challenges posed by AV technology. The study also compares India’s approach with international standards, including the GDPR and regulatory models followed in countries like the United States and China. Through this comparative perspective, the research highlights existing gaps and suggests areas where India can strengthen its legal and regulatory response.

Published by: vikaspatanker

Authors: Rajat Takkar, Gunjan Lathwal, Devanshi Dadwal, Bhumika Aggarwal, Gaurang Batra

Abstract: AI chatbots and large language models show up almost everywhere these days – customer support, healthcare, schools, even hiring. While they’re good at handling language, there’s still a big question about bias. These systems often pick up biases from their training data and then reflect them back in their answers. That includes biases related to gender, jobs, places, or wealth. This study explores whether chatbots respond to demographic-based questions with built-in bias. We used a set of structured prompts and gathered answers from several AI chatbots, recording all responses for analysis. Every answer was examined using sentiment analysis and a neutrality scoring method. This measured how fair or unbiased each system was. We performed all our analysis using Python tools like Pandas, TextBlob, and Matplotlib. Our expectation was that chatbot responses would usually be objective, but some subtle biases could sneak in depending on how you ask the question or what the topic is. Some questions just lead to more bias than others. By scoring fairness, we can actually quantify differences and see which systems are more neutral. This approach helps assess how these AI tools deal with real-world issues and fairness.

Published by: vikaspatanker

Authors: Acharjee Partho Protim, Wei Zhang

Abstract: Lightweight design is essential in modern automotive systems to improve energy efficiency, reduce emissions, and enhance performance. This study presents a simulation-driven framework for the lightweight design of an automotive reducer housing using finite element analysis (FEA) and topology optimization (TO). A baseline reducer housing is analyzed under multiple load conditions, including maximum torque, emergency braking, and cornering. Stress distribution and deformation behavior are evaluated to identify structurally redundant regions. A Solid Isotropic Material with Penalization (SIMP)-based topology optimization method is applied with a volume reduction constraint to minimize compliance while maintaining stiffness. The optimized topology is reconstructed into a manufacturable design considering casting constraints. Comparative FEA validation shows significant mass reduction while preserving structural integrity, safety factor, and stiffness. The proposed methodology provides an effective and practical framework for lightweight automotive component design.

DOI: https://doi.org/10.5281/zenodo.19880845

Published by: vikaspatanker

Authors: Khadija Elkattany, Md Mutasim Billa

Abstract: This paper presents a hybrid machine learning framework that addresses scalability and accuracy challenges in retail inventory management by integrating real-time demand forecasting with anomaly detection, evaluated using Walmart’s historical sales data. Traditional approaches face a trade-off: maintaining individual models for each product category is computationally prohibitive, while generalized models often underperform for dissimilar items, resulting in stock outs or overstocking. To address this, we propose a department-level aggregation strategy that balances specificity and generalization, combined with a hybrid methodology: ARIMA for linear trend and seasonality modeling, cubic spline interpolation to capture nonlinear residual patterns, and neural networks for complex interactions. The framework dynamically adjusts predictions using real-time sales streams and applies residual-based anomaly detection with threshold triggers to identify sudden demand spikes or supply disruptions. Experiments on a filtered Walmart dataset (12 months, 15 departments) indicate an 18% reduction in mean absolute error (MAE) compared to exponential smoothing baselines, while spline-enhanced neural networks achieve a 24% improvement over standalone ARIMA. The anomaly detection module identifies 92% of simulated irregularities with a 7% false-positive rate. The proposed framework provides three principal advantages: (1) scalable department-level modeling without per-product customization, (2) real-time adaptability to fluctuating demand, and (3) cost-efficient inventory optimization through integrated anomaly alerts. This work offers a practical blueprint for retailers to enhance forecasting precision, mitigate supply chain risks, and reduce operational costs in volatile markets.

DOI: https://doi.org/10.5281/zenodo.19880805

Published by: vikaspatanker

Authors: K. Sagar, K.Ashok, G. Vijay Kumar

Abstract: This investigation explains the effect of addition of polypropylene fibers and Nano Silica into concrete. This investigation is divided into two phases. First Phase deals with calculations of Compressive and Split Tensile strength. Here we have done compressive strength tests for calculating the optimum percentage of Nano Silica with variation from0% to 3% of cement which is replaced with cement in concrete. Now polypropylene fiber is added to concrete from 0% to 1.4% of cement and those specimens were tested for compressive and Split Tensile strength and obtained the maximum percentage of fiber at which strengths maximum. In second phase, a modal equation is developed using Multiple Regression Analysis (MRA) for compressive and Split Tensile strength based on experimental results which are found in phase one. By using obtained modal equations we will calculate Predicted strength and their residuals and their graphical representation is shown.

DOI: https://doi.org/10.5281/zenodo.19879606

Published by: vikaspatanker

Authors: Rathod Neha, Mojidra kirtika, khandhediya Isha, Harkishan Gohil

Abstract: Federated Learning (FL), was created by McMahan et al (14), has become of interest because it offers a decentralized machine learning framework for developing large scale ML models. This allows many users (or clients) to collaborate on training a shared model while retaining control of their own data. FL is ultimately designed to provide a solution to the conflict between the data demands of machine learning systems and the desire of individuals/companies to keep their personal and commercial data private. This paper is a review of the privacy and confidentiality aspects of Federated Learning. A critical review of the fundamental algorithms used in FL, possible attacks against FL systems, and the four primary techniques for enhancing privacy in FL; Differential Privacy (DP), Secure Multi-Party Computation (SMPC), Homomorphic Encryption (HE), and hardware based Trusted Execution Environments (TEE), is provided. We will review aggregation protocols, determine the strength of FL systems against poisoning and inference attacks, and compare various FL systems implemented in three industries; healthcare, mobile communication and finance. A detailed review of FL reveals research issues related to; statistical heterogeneity, communication overhead, system heterogeneity and fairness. Finally, this review presents a prioritized set of research objectives for the next ten years, with an emphasis on situating FL within the larger context of privacy-preserving ML and potential regulatory developments.

DOI: https://doi.org/10.5281/zenodo.19878825

Published by: vikaspatanker

Authors: Sanskriti Solse, Swarali Karkar, Saneeya Shaikh, Shubham Patil, Ms. Manila Gupta, Prof. Mohammad Juned, Dr. Varsha Shah

Abstract: The escalating cost of academic textbooks in India presents a significant financial burden to engineering students, many of whom purchase books for a single semester only to leave them unused thereafter. This paper presents ReBook, a full-stack, location-aware web platform that facilitates the buying, selling, and donation of second-hand academic books among students. The system employs Java Spring Boot for the backend REST API, MySQL 8.0 for persistent storage, and a JavaScript single-page application for the frontend. Key innovations include GPS-based distance sorting using the Haversine formula, WhatsApp seller integration, a pincode-level hyper-local search filter, and an AI-powered camera-based book condition detection module built on the Claude API (Anthropic). All ten planned feature modules were implemented and verified functional across Chrome, Firefox, and Android mobile browsers. ReBook directly addresses the affordability and sustainability challenges of academic publishing for students across India.

Published by: vikaspatanker

Authors: Assistant Professor Mr. Eknath Prasath M, Mr. Vasanth Kumar S.

Abstract: Marketing strategies play a significant role in influencing consumer behaviour and shaping purchasing decisions in modern markets. Businesses operating in competitive environments must adopt effective marketing techniques to attract customers and maintain long-term relationships. Understanding consumer behaviour is essential for organizations to develop products, pricing strategies, promotional activities, and distribution systems that satisfy customer needs. This study aims to analyze marketing strategies and examine consumer behaviour with special reference to Coimbatore district. The research focuses on the factors that influence consumer buying decisions, the role of digital marketing, and the effectiveness of promotional strategies adopted by businesses in the region. The study mainly relies on secondary data collected from journals, research articles, and online sources. The findings suggest that marketing strategies such as branding, advertising, pricing policies, and digital promotions significantly influence consumer purchase behaviour in Coimbatore. Factors such as brand reputation, product quality, promotional offers, and social media marketing play a crucial role in shaping consumer preferences. The study also highlights the growing importance of digital platforms in influencing consumer decision-making.

DOI: https://zenodo.org/records/19865755

Published by: vikaspatanker

Authors: Prof. Vikas More, Sagar Mahajan, Yash Kadam, Yuvraj Singh, Yashraj Khandar

Abstract: In the modern banking environment, customer experience has become a critical factor influencing customer satisfaction, loyalty, and overall business performance. With the rapid advancement of digital technologies and increasing competition in the financial sector, banks are required to move beyond traditional service models and adopt customer-centric approaches. This study focuses on enhancing customer experience in the Indian banking sector through the application of business analytics and the development of a personalization framework. The primary objective of this research is to analyze how business analytics can be used to understand customer behavior and improve service delivery. The study also aims to identify customer expectations regarding personalized banking services and to examine the existing gaps in service quality. Primary data for the study was collected through a structured questionnaire administered to 50 respondents. The collected data was analyzed using simple statistical tools such as percentages and pie charts to derive meaningful insights. The findings of the study reveal that while customers are generally satisfied with banking services, there is a significant demand for personalized services. Most respondents expressed that banks do not fully understand their needs and expect more customized offerings. The study also highlights that digital banking, particularly mobile banking, is widely preferred due to its convenience and accessibility.

Published by: vikaspatanker