Category Archives: Uncategorized

Authors: Dr. Praveen B. Hulloli, Dr.Venugopal Jalihal

Abstract: This research focuses on determining the applicability of Bradford’s Law of Scattering within the corpus of Indian medical research on Artificial Intelligence (AI) in healthcare. The study analyzing 9,774 papers that amassed 123,043 citations, the data was retrieved from the Web of Science citation database covering the period from 2005 to 2024. The study examined annual research output trends, researcher communication preferences, and the productivity of journals. The results show that year 2023 recorded the highest volume of publications, totaling 2104 (21.53%. The year 2021 demonstrated the peak research influence, as measured by total citations 26356 (21.42%) and an h-index of 69. Furthermore, journal impact was not solely linked to publication volume. Despite publishing fewer papers than volume leaders, the highly specialized “Expert Systems with Applications” demonstrated superior quality, achieving the highest Average Citations per Paper (ACPP) of 36.03. The Bradford’s analysis strongly confirmed the law’s applicability, with the core zone consisting of 1.90% of journals contributing 33.22% of the literature. This clear stratification, supported by a negligible negative error (0.49%), confirms the concentration of key AI medical literature in a small core of highly productive journals.

DOI: http://doi.org/10.5281/zenodo.20837913

Published by: vikaspatanker

Authors: Krishna Prisad Bajgai, Dr. Bhojraj Ghimire, Niraj Kumar Shah, Netra Prasad Joshi

Abstract: Artificial Intelligence (AI) and Machine Learning (ML) technologies are increasingly applied in financial institutions for credit scoring, fraud detection, algorithmic trading, and risk management. Although these techniques offer high predictive performance, many models operate as complex “black-box” systems whose decision-making processes are difficult to interpret. This lack of transparency creates challenges related to trust, fairness, and regulatory compliance. Explainable Artificial Intelligence (XAI) aims to provide transparency and interpretability to AI-based models by offering explanations for their predictions. This paper explores the role of explainable AI in financial decision systems, focusing on its applications in credit risk assessment, fraud detection, and financial forecasting. The study reviews existing explainability techniques such as SHAP, LIME, and interpretable models, and proposes a conceptual framework for integrating explainable AI into financial decision-making systems. The findings highlight that integrating explainability mechanisms improves trust, transparency, and regulatory compliance while maintaining model performance. The paper concludes with future research directions for developing trustworthy AI-driven financial systems.

DOI: http://doi.org/10.5281/zenodo.20837802

Published by: vikaspatanker

Authors: Assistant Professor Dilip Badrinarayan Soni, Dr. Hariom Singh Tomar

Abstract: An inevitable issue with integrative alternative healthcare systems (IAHS) is that although clinical reasoning is fuzzy, qualitative, and dependent on the practitioner's expertise, current evidence-based requirements mandate a precise and quantifiable approach. This paper proposes a new framework for decision making within IAHS using fuzzy logic by considering the fuzzy nature of Ayurvedic doshas, TCM meridians, and constitutional types within naturopathy. In this regard, we propose a hierarchical structure of fuzzy inference systems (FISs) containing 27 rules that map qualitative input statements ("Vata moderately high," "Qi slightly weak") to recommendations of therapy along with an MCDM process using the Fuzzy TOPSIS algorithm for treatment prioritization. Applied to clinical information from 180 patients suffering from metabolic syndrome, our system yields a consensus with an expert panel of 86.4% (κ=0.82), while decreasing variability in prescription by 58% in comparison with unassisted practitioners.

DOI: https://doi.org/10.5281/zenodo.20829144

Published by: vikaspatanker

Authors: Assistant Professor Dilip Badrinarayan Soni, Dr. Hariom Singh Tomar

Abstract: Personalized alternative medicine holds substantial promise for holistic healthcare; however, systematic optimization of multi-herb, multi-target interventions is still an open problem in terms of computational difficulties associated with combinatorics, nonlinearity, and individual differences. This paper develops a comprehensive mathematical optimization approach to personalized alternative medicine interventions by combining three approaches: evolutionary algorithms to optimize prescription of herbs, reinforcement learning to adapt the therapy, and Bayesian multidimensional hierarchical models to characterize patients’ responses to the medication. The effectiveness of the proposed optimization framework is validated through experimental analysis utilizing clinical records from traditional Chinese medicine (n=5,216). It is found that the optimized prescriptions with the use of evolutionary algorithms result in 28.5% higher effectiveness than the conventional methods (95% CI: 18.7-37.3%).

DOI: https://doi.org/10.5281/zenodo.20828820

Published by: vikaspatanker

Authors: Gowda Yashvi Manjunath, Ranjitha H, Impana P.S, Assistant Professor Chaithra K

Abstract: Road safety is a very important problem in today’s transportation systems. Rear-end collisions are among the most frequent and dangerous accidents on highways and city streets. The paper proposes a MATLAB based simulation of an intelligent obstacle detection and autonomous lane changing system for collision avoidance. We consider a scenario where an ego vehicle drives on a two-lane road and continuously observes a slower vehicle in front and a fast-approaching vehicle in the adjacent lane. The system features front obstacle detection, blind spot monitoring, adaptive speed control, and smooth lane-change execution based on a rule-based decision-making algorithm. When the vehicle in front enters the pre-set detection range of 45 m, the system checks the side lane for safety before beginning an overtaking maneuver. In case of a detected speed-risk vehicle in the blind spot zone, the lane change is delayed, and a warning alert is issued. Simulation results show successful collision avoidance, safe gap maintenance, and smooth overtaking operations, validating the effectiveness of the system as a simplified Advanced Driver Assistance System (ADAS) prototype. Index Terms — Collision prevention, lane change, blind spot detection, ADAS, V2V communication, obstacle detection, MATLAB simulation.

Published by: vikaspatanker

Authors: Rajendra S. Dhake, Vinod S. Khairnar, Rajkumar D. Rajkuvar, Sanika Hingalkar

Abstract: The dielectric response of soils is influenced by multiple factors including electromagnetic frequency, volumetric moisture content, soil composition, internal geometry of components and electrochemical interactions. These effects were characterized using the infinite sample technique to determine the real (ε/) and imaginary (ε//) parameters of the complex permittivity (ε*) of soils with different moisture contents. Measurements were conducted using an X-band microwave test bench operating at 9.44 GHz in the TE10 mode with a crystal detector and a slotted section. This configuration enables precise determination of dielectric parameters for bulk soil specimens. The observed behavior of ε/ and ε// shows an initially modest rise with increasing moisture followed by a pronounced increase at higher water contents, reflecting the strong influence of water on dielectric properties at microwave frequencies. Derived quantities such as a.c. electrical conductivity and dielectric relaxation times were also extracted from the permittivity data. The results demonstrate significant alterations in the electrical properties between dry and moist soils, with notable dependence on soil texture. These observations aid in interpreting ground-penetrating radar signatures and in the calibration of both active and passive microwave remote sensing systems.

DOI: http://doi.org/10.5281/zenodo.20825704

Published by: vikaspatanker

Authors: Shukracharya S. Gore, Apeksha R. Malunjkar, Gauri S. Lonare, Manasi R. Mahajan

Abstract: Digital notice board systems have emerged as an efficient alternative to traditional paper-based information dissemination methods. By enabling real-time message updates, such systems improve communication efficiency in educational institution, offices and public spaces. This project presents the design and implementation of a Raspberry Pi based Android application controlled digital display notice board that allows wireless transmission of notices using Bluetooth communication. The proposed system integrates an Android application with voice-to-text functionality, enabling users to input messages through speech, which are then converted into text and transmitted to the Raspberry Pi. Despite the advantages of digital notice boards, challenges such as reliable wireless communication, real-time data processing, system scalability and secure access control must be addressed. Bluetooth-based communication, while cost-effective and suitable for offline operation, is limited by range and device pairing constraints. Additionally, handling dynamic message updates and ensuring smooth system performance require efficient software design and robust hardware integration. The Raspberry Pi zero 2W saves as the central processing unit, leveraging Python-based scripts to manage incoming data and display operations through an HDMI-connects screen. Despite these challenges, addressing them through improved modelling techniques, automated data collection, and interdisciplinary collaboration can significantly enhance the effectiveness of software testing and support more informed decision-making.

DOI: http://doi.org/10.5281/zenodo.20825638

Published by: vikaspatanker

Authors: Priyanka Gonnade, Santosh Selokar

Abstract: The Smart Society Management System is a comprehensive web-based application designed to address the growing needs and complexities of modern residential society management. Developed using Python and the Flask framework, the system seeks to overcome the limitations of traditional, manual processes that often result in inefficiencies, miscommunication, and lack of transparency in daily society operations.The principal aim of the project is to automate and streamline critical tasks such as maintenance billing and tracking, complaint registration and resolution, user management, and administrative communication. The application features robust, role-based modules: an Admin Module that empowers society managers to securely log in, generate and assign monthly maintenance bills, view payment statuses, manage user data, and publish important notices; and a User Module that enables residents to access their maintenance dues, view payment histories, download receipts, submit complaints, and receive instant updates from the administration. A key innovation is the real-time tracking dashboard, providing both admins and residents with up-to-the-minute information on payment status and outstanding balances. The integration of WhatsApp API for automated message delivery further enhances communication by allowing the administration to send payment receipts and critical notifications directly to residents' phones, minimizing information gaps and manual efforts. Security is prioritized through a custom login system with initial credentials managed by the admin and a password reset feature, ensuring data privacy and personal control for users.Initial testing with actual residents has yielded positive feedback, highlighting the application's user-friendly interface and practical utility. The use of an open-source SQLite3 database paired with cloud hosting delivers secure, reliable, and scalable storage of all transactions and user activities. By digitizing the entire workflow, the system eliminates paperwork, reduces errors, and supports transparency and accountability.

DOI: http://doi.org/10.5281/zenodo.20818177

Published by: vikaspatanker

Authors: Vikash, Mrs Sheela Malik, Mr Atul Dubey

Abstract: Earthquakes are one of the most devastating forces on the planet. The seismic waves that travel through the ground can demolish buildings, kill people, and cost billions of dollars in damage and restoration. According to the National Earthquake Information Centre, there are over 20,000 earthquakes every year on average, including 16 major disasters. The damage was caused by the collapse of buildings with people inside, as in previous earthquakes, prompting the development of earthquake-resistant constructions. Constructions intended to withstand earthquakes are known as earthquake-resistant structures. While no structure can be completely safe from earthquake damage, earthquake-resistant construction aims to build structures that perform better than their conventional equivalents during seismic activity. Building rules state that earthquake-resistant constructions must be able to withstand the greatest earthquake with a reasonable chance of occurring at their site. In this paper we are marking comparison between Static and dynamic analysis. It is concluded from paper Dynamic analysis is economical as compared to static analysis.

DOI: http://doi.org/10.5281/zenodo.20817202

Published by: vikaspatanker

Authors: Research Scholar Namrata Ramrao Pawar, Dr. Ganesh R. Teltumbade

Abstract: Precise stock prediction and efficient portfolio optimization are still problematic in practice because of the non-stationarity, volatility, and complexity of the financial time series. In this study, we present a Hybrid Artificial Intelligence Framework (HAIF), which is the combination of three different frameworks: (1) a Graph Neural Network (GNN) with an attention layer for modelling relationships between stock prices; (2) a Transformer with convolutional layers for predicting price movements in different periods ahead; and (3) a Deep Reinforcement Learning (DRL) model called Proximal Policy Optimization for managing transactions and balancing the portfolio in different conditions. Based on 5 years of daily S&P 500 time series from 2020 to 2025 with 50 constituent stocks, our model obtains Sharpe ratio = 1.84, annual return = 28.4%, and maximum drawdown = -11.2% while outperforming

DOI: https://doi.org/10.5281/zenodo.20811838

Published by: vikaspatanker