Category Archives: Uncategorized

Authors: Deepa Barethiya, Prajwal Suklal Bankar

Abstract: Artificial Intelligence (AI), particularly Generative AI (GenAI) tools such as ChatGPT, has significantly influenced programming education by providing instant code generation, debugging support, and conceptual explanations. These tools are increasingly used by beginner programmers to assist in learning and problem-solving tasks. While AI has the potential to enhance learning efficiency and boost learner confidence through immediate feedback, concerns remain regarding its impact on independent thinking and long-term skill development.This study investigates the influence of AI tools on the problem-solving ability and confidence of beginner programmers. The research examines how learners interact with AI-assisted systems, how frequently they rely on generated solutions, and how such usage affects their understanding of programming concepts. Data was collected through a survey-based analysis of beginner programmers using AI-assisted tools. The findings indicate that AI tools can improve problem-solving efficiency and significantly enhance learner confidence by reducing frustration and providing instant support. However, excessive reliance on AI-generated solutions may limit the development of critical thinking and independent problem-solving skills. The study highlights the importance of balanced AI integration in programming education. This research contributes to the growing field of computing education by providing insights into both the benefits and limitations of AI-assisted learning. It also offers recommendations for educators to design effective learning strategies that leverage AI tools while preserving core problem-solving abilities.

DOI: https://doi.org/10.5281/zenodo.20954427

Published by: vikaspatanker

Authors: Deepa Barethiya, Pratik Gajbhiye, Siddhi Lokhande

Abstract: This paper explores the extent to which artificial intelligence (AI) systems, increasingly capable of creating visual artworks indistinguishable from human-created ones, are part of the broader conversation about creativity and the role of AI in the creative process. Expanding on existing research that considers AI creativity as a whole construct, this paper focuses on a component-based approach to creativity, examining it as a series of discrete components. An empirical analysis is also presented to compare AI-created and human-created artworks with respect to the most important factors traditionally associated with human creativity: emotional depth, intentionality, originality, awareness of context, and experiential authenticity. A quantitative approach was taken using a survey-based methodology, in which a series of artworks were evaluated using a structured Likert-scale survey. The results were analyzed using comparative statistics to determine performance differences between AI-created and human-created artworks across each creativity component. The results show that AI-created artworks exhibit uneven creative performance, with higher visual originality and significant shortcomings in emotional depth and intentionality compared to human-created artworks. These results suggest that creativity is a multidimensional construct and that current AI systems have difficulties in recreating several core components of human creativity. This paper contributes to the existing literature on AI and creativity by providing a structured approach to evaluating AI-created artworks beyond superficial visual aesthetics and highlighting implications for the role of AI as a creative tool versus an autonomous artist.

DOI: https://doi.org/10.5281/zenodo.20954101

Published by: vikaspatanker

Authors: Mwinilombe Joseph Mushabati, Dr. Sampa Nkonde

Abstract: This study investigates the design and implementation of a Smart Healthcare System (SHS) integrated into a Disaster Management and Mitigation System (DMMS), using Lusaka, Zambia as a case study. The increasing frequency of disasters such as cholera outbreaks, floods, and the COVID-19 pandemic have demonstrated the limitations of conventional healthcare systems in responding effectively. The SHS aims to enhance real-time data collection, health monitoring, early warning systems, and coordinated emergency response. Through qualitative methodology, data were collected from healthcare professionals, ICT experts, and disaster management personnel. Findings show that a well-integrated SHS can significantly improve response time, resource allocation, and resilience during disasters. The research contributes to local and continental knowledge on digital health innovations in disaster-prone regions.

DOI: http://doi.org/10.5281/zenodo.20953794

Published by: vikaspatanker

Authors: Lalmuanawma Chhangte, Remlalsiama, Lalnunpuia

Abstract: Ground level Gamma Radiation and Radon gas concentration at different depth beneath the ground surface of oil exploration areas in Mizoram, India is studied and correlation graph is drawn. The oil exploration areas of Meidum(MD) and Zanlawn(ZL) in Kolasib district, are studied. The main instrument utilized for the study was RnDuo machine devised to survey Radon 222 (222Rn) connected to soil probe of 1mtr long to be baptized at different depth. Background gamma radiation survey at ground level is conducted with Russian base Gamma Survey Meter (PM 1405). The background gamma radiation at ground level varies from 177 nSv/hr at MD-3 to 202 nSv/h at MD-1 location with an average of 186.5 nSv/h. An in-situ measurement of soil gas was carried out at three different spots at four different depths each namely 10cm, 30cm, 50cm and 70cm. The radon gas concentration beneath the soil, within the study area ranges from 0.10 kBq/m3 at MD-3 to 1.31 kBq/m3 at MD-1 location. A correlation graph between ground level gamma radiation and the radon concentration in soil at different dept shows that the correlation coefficient is highest at 10cm with R2=0.466 and lowest at 70cm with R2=0.175. The Radon gas concentration obtained in these areas are below the worldwide average of 35-40 kBq/m3 .(UNSCEAR 2000).

DOI: http://doi.org/10.5281/zenodo.20948672

Published by: vikaspatanker

Authors: Lalnunpuia, Remlalsiama, Lalmuanawma Chhangte

Abstract: Radon gas concentration at different depth beneath the ground surface is studied at different oil exploration areas of Mizoram, India. The oil exploration areas of Thenzawl(TZ) in Serchhip district, is studied. The main instrument utilized for the study was RnDuo machine devised to survey Radon 222 (222Rn). The other instrument is a soil probe of 1mtr long to be baptised at different depth. The study was conducted at four different depths namely 10cm, 30cm, 50cm and 70cm. For each oil exploration areas, an in-situ measurement of soil gas was carried out at three different spots to cover the oil fields. The minimum value of radon gas concentration is observed at TZ-2 spots at 10cm deep; and the maximum concentration is recorded at TZ-2 spot at 70cm deep. The radon gas concentration beneath the soil, within the study area ranges from 0.14 kBq/m3 to 1.37 kBq/m3. The Radon gas concentration obtained in these areas are below the worldwide average of 35-40 kBq/m3.(UNSCEAR 2000).

DOI: http://doi.org/10.5281/zenodo.20948158

Published by: vikaspatanker

Authors: Jayshree Pansare, Karan Singh, Affan Ali Sayyed, Rushikesh Langhi, Prathamesh Dive

Abstract: The rapid expansion of digital communication platforms has significantly increased the need for secure and efficient messaging systems. Modern users rely heavily on chat-based applications for academic collaboration, professional coordination, and personal communication. However, traditional messaging systems often fail to provide an optimal balance between data security and efficient information management. While some platforms emphasize usability, they frequently compromise on privacy, whereas others focus on encryption but lack intelligent tools to manage large volumes of conversational data. This research presents a Secret Chat Room with AI Summarization System, a web-based platform designed to address both security and usability challenges. The system integrates end-to-end encryption using AES and RSA algorithms to ensure confidentiality and protect messages from unauthorized access. Additionally, it employs WebSocket-based real-time communication to enable low-latency and efficient message exchange between users. A key contribution of this work is the integration of an AI-based summarization module that utilizes transformer-based model Gemini Summarization. This module processes chat histories and generates concise summaries, allowing users to quickly understand lengthy discussions without manually reviewing all messages. This feature significantly reduces information overload and enhances productivity. The system follows a modular architecture consisting of authentication, encryption, messaging, and AI components. Experimental observations indicate that the system achieves efficient performance with minimal latency while maintaining strong security standards. The proposed solution is suitable for applications in education, enterprise communication, and collaborative environments.

DOI: http://doi.org/10.5281/zenodo.20937546

Published by: vikaspatanker

Authors: Vidya Deshmukh, Samradnyi Patil, Akshada Veer, Jayada Talharkar, Tahareen begampalli

Abstract: Modern security environments, particularly on the battlefield, demand autonomous systems capable of real-time threat detection and neutralization without relying on human intervention. This paper presents the Autonomous Threat Detec-tion and Elimination System (ATDES), an integrated hardware-software platform designed to detect enemy armored threats — specifically tanks — using a vision-based AI detection pipeline and respond autonomously through a servo-controlled targeting and firing mechanism. The system leverages a Raspberry Pi 3B+ as the central processing unit, integrating a 2- megapixel camera for visual acquisition, an IR transceiver pair for friend-or-foe (IFF) identification, an RF receiver for enemy signal detection, and a servo-mounted firing mechanism for threat neutralization. A lightweight deep learning model is deployed on-device for real-time tank detection from camera frames, achieving sub-50 ms inference latency at a resolution of 480×640 pixels. IR-based IFF communication ensures that allied units are correctly identified and excluded from targeting, minimizing the risk of fratricide. Blynk IoT cloud integration enables remote monitoring and event logging. The system operates off-grid using a battery and solar power combination, enabling continuous 24×7 autonomous surveillance. Simulation results confirm consistent real-time de-tection with high confidence scores, demonstrating the feasibility of deploying edge AI for autonomous military threat response. The proposed system contributes a cost-effective, scalable, and intelligent prototype for next- generation autonomous defense systems.

Published by: vikaspatanker

Authors: Ayush Wankhede, Ajinkya Patil, Partth Thombre, Mohit Patil, Mahesh Korade

Abstract: Online pet adoption platforms face significant chal- lenges with fraudulent listings and attribute misrepresentation, eroding user trust. This paper presents a complete pet adoption system integrating CNN-based image verification to authenti- cate listing attributes before publication. Transfer learning with EfficientNet-B0 is applied to 110,425 images spanning 712 breed classes across dogs, cats, and birds. A two-stage training strategy first trains the classification head with frozen base layers, achiev- ing 84.7% validation accuracy, then fine-tunes the top 40 layers to reach 89.3% validation accuracy. The verification pipeline combines breed confidence, color confidence, and prediction certainty into a normalized trust score (VScore, range 0–100). Server-side scoring with an 85-point threshold prevents client manipulation while achieving 98.0% fraud detection accuracy. A one-way privacy gateway protects adopter identities, and automated digital adoption certificates with unique certification IDs formalize successful adoptions. Experimental validation on 128 verification requests demonstrates an 84.4% acceptance rate, 1.8 s average processing time, and only 1.6% false positive rate.

DOI: http://doi.org/10.5281/zenodo.20930615

Published by: vikaspatanker

Authors: Mayuri Dongre, Arshiya Sahare, Sarang Dumbhare

Abstract: In the age of digitalisation, a lot of transaction information is produced online, and it is significant to understand customer behaviour and market trends. This paper aims at examining the behavioural patterns in transaction data based on a data-driven approach. The information is gathered using web scraping on Flipkart, primarily in the electronic products categories of mobiles, headphones, smart watches, speakers, accessories with the help of Selenium WebDriver and Python. The obtained data is saved in the CSV format and processed with Python libraries, such as Pandas and NumPy, that allow cleaning data, eliminating duplicates, missing values, and categorizing products. Additional analysis is conducted to establish customer preferences, expenditure trends and product demand trends. The end results are presented in visual representations in the form of dashboards and reports to aid in improved business decision-making. This research assists in interpreting the behaviour of transactions and is useful in the data-driven strategies.

DOI: https://doi.org/10.5281/zenodo.20929867

Published by: vikaspatanker

Authors: Deepa Barethiya, Deepak Vinod Chouksey, Ankur Sanjeev Khurpadi

Abstract: Cardiovascular diseases remain the leading cause of mortality worldwide, accounting for approximately 17.9 million deaths annually according to the World Health Organization. Early detection and accurate risk assessment of heart disease are critical for effective clinical intervention and improved patient outcomes. Traditional diagnostic methods often depend heavily on subjective clinical judgment, which can be inconsistent and time-consuming. This research proposes a Machine Learning-based predictive system that leverages clinical data to assess the risk of heart disease with high accuracy. The proposed system employs multiple classification algorithms including Logistic Regression, Random Forest, Support Vector Machine (SVM), and XGBoost, and evaluates their performance on the UCI Cleveland Heart Disease dataset. Feature selection techniques such as correlation analysis and Recursive Feature Elimination (RFE) are used to identify the most significant clinical predictors. The proposed ensemble model achieves an accuracy of 91.8%, sensitivity of 93.2%, and specificity of 90.4%, outperforming individual classifiers. The results demonstrate that machine learning can serve as a reliable and scalable decision-support tool for cardiologists and general physicians in early heart disease diagnosis.

DOI: https://doi.org/10.5281/zenodo.20929505

Published by: vikaspatanker