Daily Archives: April 3, 2026

Authors: Mr. V. Gopinath, V. Aasritha Devi, P. Deekshitha, V. Pragna, P. Siva Sankara Rao

Abstract: Global food security is currently challenged by a dual-front crisis: a non-linear surge in the global population and the concurrent, unpredictable degradation of arable land, as highlighted by the United Nations [18]. Traditional agricultural methodologies frequently depend on generalized fertilizer applications that fail to account for site-specific soil chemistry, leading to nutrient runoff or stunted growth (Wolfert et al. [19]). Building upon the foundational web-based and mobile frameworks established by Agri Vision Pro [1] and AgroVision et al. [2], this research introduces AgroVision Pro. AgroVision Pro is a high-fidelity, multi-stage machine learning framework designed to eliminate guesswork by integrating classification and regression pipelines into a cohesive decision-support ecosystem. Utilizing state-of-the-art algorithms, including XGBoost (Chen et al. [9]) and Random Forest (Breiman [10]), the platform achieves a 93.2% accuracy in crop selection and an R^2 score of 0.89 in yield quantification. This research demonstrates how localized soil data, processed through an innovative "Feature-Chaining" architecture, transitions agriculture from a reactive industry to a proactive, precision-driven powerhouse.

DOI:

 

 

Published by: vikaspatanker

Authors: Kushal B D, Kirankumar B, Hani Firdous, Priyanka H S, Dr. M J Anand

Abstract: This project presents the development of an autonomous line-following and obstacle-avoidance robot using the ESP32 microcontroller. Infrared sensors detect and follow the predefined path, while an ultrasonic sensor measures distance and identifies obstacles to prevent collisions. The ESP32 processes real-time sensor data to control the motor driver, ensuring smooth and stable navigation. A GSM module is integrated to send alerts during critical situations. The system is designed to be low-cost, scalable, and suitable for educational and automation applications. The prototype demonstrates consistent path tracking and efficient obstacle avoidance, making it adaptable for real-world industrial logistics and warehouse environments. The overall design highlights the importance of combining multi-sensor integration with wireless communication to enhance the robustness and usability of autonomous robotic systems.

Published by: vikaspatanker

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

Abstract: Microfinance institutions (MFIs) play a crucial role in promoting financial inclusion in developing economies such as Nepal. However, the increasing rate of non-performing loans (NPLs) threatens the sustainability of the microfinance sector. Traditional credit monitoring methods are often reactive and lack predictive capabilities for early detection of loan defaults. MThis study proposes an Agentic AI-based Early Warning System (EWS) for predicting non-performing loans in Nepalese microfinance institutions. The proposed framework integrates machine learning algorithms, autonomous AI agents, and explainable AI mechanisms to analyze borrower data and generate real-time risk alerts The system utilizes financial transaction data, borrower demographic profiles, repayment histories, and behavioral indicators to predict loan default probability. Experimental evaluation using ensemble machine learning models demonstrates improved predictive accuracy compared to traditional credit scoring approaches. The proposed framework contributes to FinTech innovation by enabling proactive credit risk management, improving loan portfolio quality, and supporting regulatory oversight within Nepal’s microfinance ecosystem.

DOI:

 

 

Published by: vikaspatanker

Authors: Ms. Lungsanghungle Newme, Dr. Arup Barman

Abstract: Artificial Intelligence is fundamentally transforming the discipline of data engineering. This paper examines how AI is reshaping core data engineering functions including relational and cloud database management, data warehousing, enterprise analytics, digital analytics platforms such as Adobe Analytics, and cloud-native platforms such as Snowflake. Drawing on current industry practices and emerging platform capabilities, this paper analyzes the impact of AI on pipeline development, data quality management, automated metadata governance, and real-time analytics. This paper further discusses how the role of the data engineer is evolving from manual code writing to strategic architecture and AI-assisted orchestration. The paper also addresses key challenges including data privacy in regulated financial environments, skill evolution requirements, and the governance of AI-generated outputs. Paper findings indicate that organizations which invest in AI-ready data infrastructure, establish strong governance frameworks, and upskill their engineering teams will gain significant competitive advantages in the next decade.

DOI: https://doi.org/10.5281/zenodo.19396647

Published by: vikaspatanker

Authors: Akanksha Vishwasrao, Nikita Shinde, Apeksha Vishwasrao

Abstract: The Expense Tracker Web Application is designed to simplify and enhance personal financial management through automation, intelligent analysis, and user-friendly interaction. Traditional expense tracking systems require manual data entry and provide limited insights, making them inefficient for modern users. This system overcomes those limitations by integrating a conversational chatbot, automated financial summaries, and AI-powered insights. The application is developed using Flask (Python) for backend processing, SQLite for data storage, and HTML, CSS, JavaScript for frontend interaction. A key feature of the system is its Natural Language Processing-based chatbot, which allows users to add, update, delete, and view expenses using simple human language instead of complex forms. Additionally, the system incorporates an AI Insights module powered by Groq API, which analyzes user spending history and generates personalized financial advice, budget planning, and savings strategies. The application also provides professional reporting features such as CSV and PDF exports, interactive dashboards, and visual tools like calendar heatmaps. This system transforms expense tracking from a passive activity into an intelligent financial assistant that actively helps users improve their spending habits and achieve financial goals.

Published by: vikaspatanker

Authors: Ekiyor, L. P, Amadi, H. N., Wokoma, B. A., Uwho, K. O

Abstract: The study examines power quality improvement in Rumuomoi distribution network addressing issues such as harmonic distortion and voltage sags which degrade system efficiency and affect sensitive loads by implementing an Adaptive Neuro-fuzzy Inference System (ANFIS)-controlled Unified Power Quality Conditioner (UPQC). The challenge (harmonic distortion and voltage sag) arise due to the increasing penetration of nonlinear loads, such as variable frequency drives, rectifiers, and industrial machinery, which introduce significant current and voltage harmonics into the distribution network, leading to excessive Total Harmonic Distortion (THD), voltage instability, and inefficient power distribution. Conventional PID controllers often exhibit limitations in dynamic compensation, adaptability, and optimal performance under varying load conditions, necessitating an intelligent control approach that can effectively mitigate power quality disturbances in real-time. Fast Fourier Transformation analysis in MATLAB/Simulink software was used to evaluate performance of the network before and after UPQC( series APF and shunt APF) installation comparing total harmonic distortion and voltage sag. The result obtained from base case simulation shows that the nonlinear load injected harmonic distortion at PCC (point common coupling) that violates the statutory limit of 5% IHD (individual harmonic distortion) and 8% VTHD (voltage total harmonic distortion) according to IEEE 519-2022 standard for low and medium voltage system. The highest harmonic current distortion consists of 5th order resulting to a total harmonic distortion of 12.59%. However, the performance of the ANFIS-controlled UPQC demonstrates significant improvements, with a reduction of total harmonic distortion from 12.59% to 0.15% which is below 5% ensuring compliance with IEEE 519 harmonic standards. Furthermore, the ANFIS-controlled UPQC effectively mitigates voltage sag conditions, restoring voltage deviations within ±5% of nominal values, which is critical for ensuring the stability and reliability of sensitive electrical loads. The practical implications of this study highlight the feasibility of deploying ANFIS-controlled UPQC in distribution networks to achieve IEEE 519 power quality standards, ensuring efficient, reliable, and high-quality power delivery for industrial, commercial, and residential applications.

DOI: https://doi.org/10.5281/zenodo.19400815

 

Published by: vikaspatanker