Manuscripts

Recent Papers

Research Paper

Life Cycle Assessment of Electric Vehicles vs. Internal Combustion Engine Vehicles: A Post-2020 Comparative Analysis

The rapid electrification of transportation after 2020 has increased discussions about whether electric vehicles (EVs) are more environmentally friendly than internal combustion engine vehicles (ICEVs). Although EVs do not produce tailpipe emissions, their total impact on the environment depends on the manufacturing process, battery production, the combination of electricity production, and end-of-life treatment. In this work, the LCA of EVs and ICEVs on the basis of cradle-to-grave life cycle analysis is provided under the conditions of technological progress and the grid in the post-2020 period, with references to the Indian electricity mix. Mathematical emission modeling, break-even analysis, and sensitivity analysis are conducted for a functional unit of 150,000 km. Results indicate that EVs exhibit higher manufacturing emissions but lower operational emissions. Compared to ICEVs, EVs exhibit 6–30% lower total life cycle emissions under current grid conditions (0.7 kg CO₂/kWh). The study also emphasizes how important grid decarbonization is to improving EV sustainability performance.

Published by: Khushdeen Singh Khosa, Harpreet Singh

Author: Khushdeen Singh Khosa

Paper ID: V12I1-1182

Paper Status: published

Published: March 2, 2026

Full Details
Research Paper

Computer Networks VR

Computer Networks VR is an engaging educational game that turns key ideas of computer networking into a gameplay experience focused on packet transfer methods. Players take on the role of "Ping," moving through a factory designed like a Wi-Fi router, which serves as a metaphor for actual network operations. By handling packets shown as labeled boxes and setting IP and destination addresses, along with solving routing problems, players gain a solid understanding of data transmission. As they advance through different levels, they come across packet structures and protocols, solidifying their theoretical knowledge with practical simulations. This game highlights the potential of virtual reality as a valuable tool for making abstract networking concepts interactive and hands-on.

Published by: Shrey Sharma, Nendra Namgyel Wangchuk, Abhijeet Sharma

Author: Shrey Sharma

Paper ID: V12I1-1177

Paper Status: retracted

Submitted: February 26, 2026

Full Details Track Status
Research Paper

An Intelligent AI-Based Framework for Handwritten Character Recognition

Handwritten Character Recognition (HCR) remains a fundamental yet challenging problem in pattern recognition due to variations in writing styles, distortions, noise, and inter-class similarity. This study proposes an intelligent AI-based framework for robust handwritten character recognition using a Convolutional Neural Network (CNN). The model is trained and evaluated on a self-curated dataset comprising 13,640 grayscale images representing 62-character classes, including digits (0–9), lowercase letters (a–z), and uppercase letters (A–Z). Images are standardized to a resolution of 28×28 pixels and normalized to enhance learning efficiency. The proposed CNN architecture leverages hierarchical feature extraction through multiple convolutional and pooling layers, followed by dense layers for classification. Experimental results demonstrate a recognition accuracy of approximately 93%, indicating strong generalization capability despite handwriting variability. The proposed framework emphasizes automated feature learning, eliminating the dependency on handcrafted descriptors traditionally used in character recognition systems. The model exhibits strong adaptability across diverse handwriting patterns, demonstrating robustness to intra-class variations. Furthermore, the lightweight CNN architecture ensures computational efficiency, making the system suitable for real-time applications and deployment in resource-constrained environments. The study also highlights the critical role of dataset quality, preprocessing strategies, and normalization techniques in improving recognition performance. Overall, the findings confirm that deep learning-driven approaches offer a reliable, scalable, and efficient solution for handwritten character recognition.

Published by: Ajay Kumar R, Umadevi C, Savitha M M, Dennis Thomas, Sahana G, Bhuvaneshwari MJ, Hemanth V, Roja KV, Tejas NR

Author: Ajay Kumar R

Paper ID: V12I1-1166

Paper Status: published

Published: February 23, 2026

Full Details
Research Paper

Lightweight Machine Learning Models for Detecting DNS Data Exfiltration Attacks in Cloud and Enterprise Networks

Cloud and Enterprise Networks are the foundation of today's digital age, facilitating frictionless communication and service delivery. Cloud and Enterprise Network attacks increasingly depend on trusted protocols, and DNS Data Exfiltration Attacks in Cloud and Enterprise Networks have evolved as a devious and powerful means to evade classic defences. Detecting DNS Data Exfiltration Attacks in Cloud and Enterprise Networks is therefore a pressing challenge that requires efficient and accurate solutions. This study investigates Machine Learning Models for Detecting DNS Data Exfiltration Attacks in Cloud and Enterprise Networks, focusing on lightweight approaches such as Random Forest, Decision Tree, Multi-Layer Perceptron, Logistic Regression, and Gaussian Naïve Bayes. Both Random Forest and Decision Tree achieved perfect evaluation scores (100%) across standard metrics, but closer inspection of confusion matrices revealed Random Forest as the superior model, misclassifying only two malicious instances while generating no false positives. The significance of this research lies in demonstrating that lightweight models, particularly Random Forest, can provide highly accurate, resource-efficient, and practical real-time protection against DNS exfiltration threats, ensuring the resilience of cloud and enterprise infrastructures.

Published by: Tolulope Onasanya, Hannah I. Tanimowo, John Aigberua, Oduwunmi Esther Odukoya

Author: Tolulope Onasanya

Paper ID: V12I1-1155

Paper Status: published

Published: February 21, 2026

Full Details
Research Paper

Tribal Health in India: Status, Challenges, and Strategies for Strengthening Healthcare Delivery

Tribal health remains one of the most neglected domains within the Indian public health system despite constitutional safeguards and multiple targeted programmes. Scheduled Tribes (STs), constituting approximately 8.6% of India’s population, continue to experience disproportionately high morbidity and mortality due to a complex interaction of socio-economic deprivation, geographical isolation, cultural barriers, and systemic inadequacies in healthcare delivery. Historical marginalisation, poverty, low literacy levels, and poor living conditions have collectively contributed to persistent health inequities among tribal communities. Conventional healthcare models, which largely follow a uniform national approach, have failed to adequately address the unique cultural, social, and environmental contexts of tribal populations, resulting in limited utilisation of health services and delayed care-seeking behaviour. This paper presents a detailed narrative analysis of the health status of tribal populations in India, drawing upon secondary data from national surveys, census reports, and published literature. The study examines key indicators related to maternal and child health, nutritional status, communicable and non-communicable diseases, and healthcare utilisation patterns among tribal communities. It further explores systemic barriers such as inadequate infrastructure, workforce shortages, accessibility issues, financial constraints, and discrimination within healthcare settings. By reviewing existing policy frameworks and community-based models, the paper proposes context-specific and culturally sensitive strategies to strengthen primary healthcare delivery in tribal areas. The findings emphasise the need for integrated, participatory, and rights-based approaches to reduce health disparities and improve overall health outcomes among tribal populations.

Published by: Aadya Gaur

Author: Aadya Gaur

Paper ID: V12I1-1159

Paper Status: published

Published: February 13, 2026

Full Details
Review Paper

A Survey on Modern Computational Methods for Drug Repurposing

Drug repurposing, the process of identifying new therapeutic uses for existing drugs, offers a promising strategy to accelerate drug development by significantly reducing costs, time, and risks compared to de novo drug discovery. The increasing availability of large-scale biomedical data has catalysed the development of computational approaches to systematically identify and prioritise repurposing candidates. This survey reviews the state-of-the-art computational methodologies, with a particular focus on network medicine and machine learning-based techniques. We discuss key approaches such as pathway-based analysis, network proximity, matrix factorisation, and the growing application of deep learning, particularly Graph Neural Networks (GNNs), which leverage complex biomedical networks. The paper explores how these methodsutilisee heterogeneous data—including drug-target interactions, gene-disease associations, and molecular structures—to generate repurposing hypotheses. Furthermore, we outline the primary challenges in the field, including data integration, model generalizability, and the need for explainability, and discuss future directions, such as the integration of multi-modal data and the development of more sophisticated, interpretable AI models.

Published by: Aditi Dipak Thorat, Shlok Shivaji Kaule, Paras Vijay Tak, Anuj Prakash Gagare, Vijayendra S. Gaikwad

Author: Aditi Dipak Thorat

Paper ID: V12I1-1157

Paper Status: published

Published: February 13, 2026

Full Details