VOLUME 14, ISSUE 10, OCTOBER 2026

Abstract: Due to the reasons like insurance frauds, duplicate billing, identity theft, and professional misconduct, fraud in the healthcare sector leads to billions of losses. Fraud detection mechanisms that use static parameters cannot detect the highly advanced fraud patterns. Due to the inclusion of the autonomous reasoning, constant surveillance, adaptation, and collaborative decisions, Agentic Artificial Intelligence increases the fraud detection process and claims verification. In this research work, we provide an Agentic AI framework which includes intelligent agents related to policy compliance, provider verification, anomaly detection, claims verification, and automated decision-making. Several AI agents can cooperate with each other in order to detect the suspicious health care transaction process without generating too many false positives through machine learning, knowledge graph, explainable AI, and reinforcement learning. The proposed approach will be beneficial in increasing the performance and fraud prevention in the healthcare ecosystems. Simulation results show that the proposed framework outperforms existing fraud detection systems in terms of accuracy, processing time, and claim verification process. The proposed technique will be helpful in designing future intelligent healthcare infrastructures with safe and reliable health insurance management.

Keywords: Agentic AI, Healthcare Fraud Detection, Claims Verification, Medical Insurance, Explainable AI, Multi- Agent Systems, Machine Learning, Healthcare Analytics.

Abstract: This study developed a fortified bio‑liquid fertilizer from poultry manure and lignocellulosic biomass through anaerobic co‑digestion under mesophilic conditions (35–37 °C) for 14 days, followed by mineral fortification with urea, single superphosphate (SSP), and muriate of potash (MOP) to achieve an NPK 12:6:8 formulation. Physicochemical analyses confirmed improved nutrient balance, stability, and sustained release compared with unfortified bio‑liquid. Nitrogen release reached ~90% by day 20, phosphorus ~70%, and potassium ~50%, supporting gradual nutrient availability. The fortified product demonstrated potential as a cost‑effective and eco‑friendly alternative to synthetic NPK 15:15:15, while retaining organic carbon for soil health. These findings highlight agro‑waste valorization as a viable pathway for sustainable fertilizer production, aligning with circular economy principles and agricultural intensification.

Keywords: Agro-waste valorization, Fortified Bio-liquid Fertilizer, Anaerobic digestion, Circular Economy

Abstract: Indian Sign Language (ISL) is an important visual language used by deaf and hard-of-hearing people in India for communication. However, many people who do not understand sign language face difficulties in communicating with ISL users. In many situations, communication depends on another person who understands sign language, which may not always be available. Therefore, there is a need for a system that can automatically recognize Indian Sign Language gestures and convert them into understandable text and speech.

This research proposes an Indian Sign Language Text/Speech Translation System to make communication between ISL users and non-sign-language users easier and more accessible. The system provides a digital method to capture ISL gestures through a camera, process the input, identify the signs, and convert the recognized gestures into text. The generated text can then be converted into speech using a text-to-speech component. The proposed system can use computer vision, image processing, machine learning or deep learning techniques, and natural language processing for recognizing and translating ISL gestures. The system can support real-time communication and reduce the need for manual interpretation in basic communication situations. It can also provide a foundation for future development of multilingual translation and improved recognition of continuous signs.

Keywords: Indian Sign Language, ISL Translation, Sign Language Recognition, Text Translation, Speech Generation, Computer Vision, Deep Learning, Natural Language Processing.

Abstract: The rapid growth of smart phones, GPS technology, and location-based service as created new opportunities. or automating attendance management. Traditional attendance systems commonly depend on manual registers or conventional digital methods, which can require considerable time and may allow inaccurate or proxy attendance. This research presents a Geo-Location Based Attendance Tracking Mobile Application designed to record attendance by verifying the user's current geographical location.

The proposed system uses GPS-based location detection and a predefined geographical boundary, or geo-fence, to determine whether auseris present within an authorized attendance area. When the user's location satisfies the defined criteria, the application records attendance along with date and time. The system is intended to provide a simple, automated, anduser- friendly approach to attendance tracking while reducing manual work.

The study focuses on system design, location verification, attendance recording, and application evaluation. The proposed application can be useful in educational institutions and organizations where attendance needs to be associated with physical presence at a specified location. Future extensions may include face verification, cloud synchronization, analytics, and stronger location-spoofing protection.

Keywords: Geo-Location, GPS, Attendance Tracking, Mobile Application, Geo-Fencing, Location-Based Services, Automated Attendance.

Abstract: Artificial Intelligence (AI) has become an important part of modern higher education. Postgraduate students increasingly encounter AI-based tools for searching information, understanding difficult concepts, writing and improving text, coding, summarising content, preparing presentations, generating ideas, and supporting research. This research studies the awareness and adoption of AI tools among postgraduate students, with emphasis on knowledge of AI tools, frequency of use, academic purposes, perceived benefits, challenges, trust, privacy, accuracy, academic integrity, and responsible use. The study follows a descriptive quantitative survey design using a structured questionnaire. The target population is postgraduate students, and the proposed data collection method is a questionnaire-based survey using convenience or purposive sampling. The literature review includes studies on student use of Generative AI, technology acceptance, trust, and learning outcomes. The paper presents a research framework, questionnaire, proposed analysis plan, and responsible-use recommendations. Numerical findings are intentionally not fabricated; final percentages and statistical results should be inserted after actual questionnaire data are collected.

Keywords: Artificial Intelligence, Generative AI, AI Awareness, AI Adoption, Postgraduate Students, Higher Education, AI Literacy, Academic Integrity.

Abstract: The enterprise software landscape has experienced a monumental shift towards natural language interfaces, driven largely by the advent of Large Language Models (LLMs). However, generic LLMs frequently suffer from domain hallucination, data privacy vulnerabilities, and an inability to interface with proprietary corporate knowledge. This research presents the architecture and implementation of a Conversational Chatbot Builder designed specifically to construct smarter, domain-specified virtual assistants. The proposed system employs a Retrieval-Augmented Generation (RAG) framework, seamlessly integrating pre-trained foundation models with specialized vector databases. By transforming institutional datasets into high-dimensional semantic embeddings, the system grounds the virtual assistant's responses entirely in verified, contextually relevant data. The platform abstracts the complexities of NLP orchestration, offering a dynamic pipeline for query ingestion, intent classification, semantic search, and prompt injection. Furthermore, the architecture implements rigorous security guardrails, including real-time Personally Identifiable Information (PII) redaction and strict Role-Based Access Control (RBAC). Extensive empirical evaluations demonstrate that this domain-specified approach significantly reduces response latency compared to heavy generalized inference, while entirely mitigating factual hallucinations. The resulting conversational interface achieves human-like fluency combined with deterministic accuracy, representing a paradigm shift in how organizations deploy secure, intelligent virtual agents.

Keywords: Conversational AI, Chatbots, Retrieval-Augmented Generation, RAG, Natural Language Processing, LLMs, Vector Databases, Domain-Specific AI.

Abstract: Agriculture is an important source of livelihood and income for rural communities, yet farmers often face uncertainty while selling their produce. Price fluctuations, limited access to reliable buyers, weak bargaining positions, inadequate market information, quality requirements, and dependence on intermediaries can affect the stability of agricultural marketing. Contract farming provides a structured arrangement in which farmers and buyers agree on production and marketing conditions before or during production. This research studies an Assured Contract Farming System for Stable Market Access and proposes a technology-supported approach for improving transparency,

based research design. Relevant research papers, systematic reviews and published studies on contract farming, farmer participation, income, risk management and market access are reviewed. Existing practices are analysed to identify farmer and buyer requirements, implementation challenges and opportunities for digital support. Based on the literature findings, a conceptual framework is proposed in which farmer registration, buyer requirements, contract creation, production monitoring, quality verification, delivery, payment records and alerts are connected through a structured system. The expected contribution is a practical conceptual model that can support more reliable market relationships and reduce uncertainty in agricultural marketing.

Keywords: Contract Farming, Market Access, Farmers, Buyers, Digital Agriculture, Risk Management, Transparency, Stable Market Access.

Abstract: Regression inference and many machine-learning loss functions assume, or at least work best with, errors that are not extremely fat-tailed or asymmetric. Emerging-market series are widely believed to violate this, and the belief is rarely tested carefully. This paper documents the distributional properties of ten Nigerian macroeconomic indicators over 67 quarters from 2008Q2 to 2024Q4, and finds a more mixed picture than the folklore suggests. Three of the ten do not reject normality at the 5% level: FDI itself (Jarque-Bera 2.11, p = 0.348), GDP (0.24, p = 0.885) and oil price (3.63, p = 0.163). Seven do reject, with exchange-rate volatility the most extreme (skewness 3.21, excess kurtosis 10.14). The result for FDI matters most, because FDI is the dependent variable in most Nigerian FDI research and is routinely assumed to be severely non-normal. An earlier version of this analysis, run on a longer sample in which everything before 2008 was interpolated from annual figures, found all ten variables rejecting normality and reported FDI with excess kurtosis of 7.95. On genuine data FDI has excess kurtosis of -0.17. The apparent fat tails were an artefact of splicing a smoothed series onto a noisy one.

Keywords: Non-Normality; Skewness; Kurtosis; Jarque-Bera; Nigerian Macroeconomic Data.

Abstract: The rapid urbanization and infrastructural development globally necessitate accurate, up-to-date cartographic data. Traditional road extraction methods relying on manual digitization of satellite imagery are time- consuming, expensive, and prone to human error. This research paper presents a fully automated system for road extraction and alert generation designed to detect newly constructed roads in high-resolution satellite imagery using deep Convolutional Neural Networks (CNNs). The proposed architecture leverages a modified U-Net model with a ResNet backbone to perform pixel-wise semantic segmentation of road networks. Extracted binary masks are subjected to morphological post-processing and vectorization to generate GeoJSON representations. A spatial intersection engine then cross-references these newly vectorized roads against existing baseline databases (such as OpenStreetMap or proprietary governmental GIS databases). Upon detecting unregistered or novel infrastructural additions, the system triggers automated webhook alerts and dashboard notifications to relevant authorities. Extensive evaluation on the Massachusetts Roads Dataset and custom temporal satellite data demonstrates that our model achieves a Dice Coefficient of 0.89 and an Intersection over Union (IoU) of 0.81, significantly outperforming legacy threshold-based GIS algorithms. Furthermore, the implemented event-driven architecture ensures low-latency alert distribution, enabling near real-time urban monitoring. This paper details the mathematical loss functions, topological vectorization constraints, and secure communication protocols that comprise the system.

Keywords: Deep Learning, Road Extraction, U-Net, Semantic Segmentation, Remote Sensing, GIS, Alert Systems, Webhooks.

Abstract: Existing farming practices rely mainly on diesel-powered tractors, resulting in high operational costs, health impacts from pollution, carbon emissions, and a dependence on fossil fuels.even though the Electric tractors are used it is having limited battery range, high upfront costs, lack of charging infrastructure,This slow down the widespread adoption of electric tractors in remote areas and as well as rural areas. These technical and socioeconomic obstacles must be considered and design Smart Electric Vehicle (EV) Tractor for sustainable agricultural practices. The primary objective of this research is to design a model a zero-emission electric tractor tailored for sustainable farming, aiming to reduce carbon footprints with-same endurance.this study encompasses the integration of a high-torque electric power-train, a modular battery architecture, and an Io T-driven sensor framework designed for real-time field telemetry, automated path planning, and remote monitoring.Comparative field operational trials were conducted against standard diesel/ petrol tractors across typical farming operations, including tillage, seeding, and crop transport.smart electric tractors offer a viable, cost-effective, and environmentally sustainable compared to traditional internal combustion engine tractors. the integration of autonomous navigation and real-time soil sensing reduced field overlap Smart electric tractors serve as a superior alternative to traditional diesel tractors. By eliminating diesel exhaust and also minimize environmental pollution while significantly lowering operational expenses. Integrating electric power with advanced precision technology allows farmers to optimize resource use and substantially cut down overall farming costs

Keywords: Smart EV Tractor, Sustainable Farming, Photovoltaic Solar Charging, Internet of Things (IoT), Embedded Microcontrollers, Precision Agriculture, Motor Drivers, Zero-Emission Machinery.