Category Archives: Uncategorized

Authors: Nagender Yamsani

Abstract: Organizations that rely on enterprise master data platforms often encounter persistent limitations in metadata quality, particularly in areas such as semantic clarity, contextual relevance, and cross domain interpretability. This study examines the use of natural language processing to enable context aware metadata enrichment within EBX repositories, addressing the challenge of transforming fragmented descriptive fields into structured, meaningful knowledge assets. The purpose of this research is to design and evaluate a systematic enrichment approach that can interpret textual attributes, infer relationships, and enhance metadata usability for governance, integration, and analytics. A mixed research method was applied, combining architectural modeling, controlled prototype implementation, and qualitative assessment of stewardship workflows in simulated enterprise scenarios. Observed outcomes demonstrate measurable improvements in classification consistency, metadata coverage, and retrieval efficiency, while also reducing dependence on manual interpretation. The proposed framework introduces a scalable enrichment pipeline that integrates linguistic analysis, semantic mapping, and governance driven validation within the operational lifecycle of EBX master data. This study argues that embedding language aware intelligence into metadata management practices can significantly strengthen data reliability and transparency. The findings provide a foundation for future research on semantic infrastructure in enterprise data ecosystems and offer practical guidance for organizations seeking to modernize metadata governance in complex master data environments.

DOI: https://doi.org/10.5281/zenodo.19849787

Published by: vikaspatanker

Authors: Aviraj Sanjay zure, Tushar ravsaheb shingade , Vinay Vilas patil , Abhishek Mallinath Sutar , Sonali Mahadev Patil , vaishnavi Deepak Pawar , Anita Rangrao Pujari

Abstract: Current advancements in the treatment of Parkinson’s disease (PD) are shifting from purely symptomatic management to a dual approach: refining the delivery of existing dopaminergic therapies and developing experimental disease-modifying and neurorestorative interventions. While levodopa remains the gold standard, its long-term use is complicated by motor fluctuations and dyskinesia, prompting the development of novel delivery systems like continuous subcutaneous infusions (e.g., Vyalev and Onapgo) and inhaled levodopa to provide steadier symptom control. Simultaneously, emerging therapies including stem cell transplantation (e.g., bemdaneprocel), gene therapy (e.g., AB-1005), and immunotherapy targeting -synuclein are advancing through late-stage clinical trials with the goal of replacing lost neurons or halting disease progression.

Published by: vikaspatanker

Authors: Mohammed Afsal

Abstract: The COVID-19 crisis reshaped healthcare systems across the world in ways never seen before. As hospitals struggled to manage rising infection rates, traditional face-to-face consultations quickly became risky. In response, healthcare providers rapidly turned to telemedicine as a safer and more practical alternative. What initially began as an emergency response soon demonstrated long-term value. Virtual healthcare services have since proven effective in expanding access, improving chronic disease management, reducing operational costs, and maintaining continuity of care. This paper examines how telemedicine evolved during the pandemic, the technologies that support it, the benefits and limitations it presents, and its growing importance in shaping the future of global healthcare delivery.

DOI: https://doi.org/10.5281/zenodo.19845945

Published by: vikaspatanker

Authors: P. Hemeshwar Chary, Akula Nikhila, Balusuguri Navya, Kotaraviteja

Abstract: This paper is about building hardware for a machine learning system that forecasts wind energy and ties it into an energy management setup for microgrids. It seems like the main idea is to use this optimized thing called Variational Mode Decomposition along with CNN-LSTM for the predictions, and then a Deep Reinforcement Learning approach for handling the energy side. What stands out is how they actually built a real prototype to test it, not just simulations like a lot of other studies do. The setup includes emulating wind data, some microcontroller to control things, a battery for storage, loads that can be adjusted, and a way to connect to the grid. I think that makes it more practical, you know. They ran experiments and got better accuracy in forecasting, plus the energy dispatch worked efficiently in real time. It feels like this could help make microgrids more reliable, cut down on costs, and keep everything running stable. Some parts of the implementation might still need tweaking, but overall it shows promise. The forecasting part with VMD and the neural nets seems key to why it performs well. Index Terms—Wind energy is something thats getting a lot more attention these days, especially with all the push for renewable stuff. Forecasting how much power the wind will give is tricky because wind changes so much, right. I think using models like CNN and LSTM can help predict it better. CNN is good for spotting patterns in data, like images but here its time series from wind speeds. Then LSTM handles the sequences over time, remembering past stuff to guess future outputs. It seems like combining them makes the forecasts more accurate, at least from what Ive read. VMD comes in too, which I believe stands for Variational Mode Decomposition. Its a way to break down the noisy wind data into smoother parts, so the model doesnt get confused by all the ups and downs. Without that, predictions might be off. I might be oversimplifying this, but it feels like preprocessing the signal with VMD first improves everything. For energy management systems, once you have a good forecast, you can plan better. Like deciding when to store extra power or switch sources. In a microgrid, thats super important because its small scale, maybe for a community or island. Hardware implementation is the next step, turning the software models into real devices. Ive seen papers on using FPGAs or something for that, to make it fast and efficient on actual turbines. Microgrid applications tie it all together. Wind forecasting with these tools helps balance the grid, reduces waste. Some people say its not perfect yet, others think its ready for more use. That part stands out to me, how it could really change things but still has challenges like cost. Overall, this approach seems promising, though Im not totally sure about the hardware side yet.

Published by: vikaspatanker

Authors: Shweta Patnaik, Stanli Jena

Abstract: Now a days Plant diseases significantly affect agricultural productivity and food security by reducing crop yield and quality. Traditional methods of disease detection rely on manual inspection, which is time-consuming, labour intensive, and often prone to human error. To overcome these limitations, automated approaches based on computer vision and deep learning have been developed for accurate plant disease detection. This study presents a method for identifying and classifying plant diseases using leaf image analysis. The proposed system utilizes computational models to analyse visual features of leaf images and detect disease patterns with improved accuracy. Image preprocessing techniques, including noise removal, resizing, and normalization, are applied to enhance image quality and ensure consistency in model input. The performance of the system is evaluated using standard metrics such as accuracy and precision. The results demonstrate that the proposed approach provides more reliable and efficient disease detection compared to conventional methods. Furthermore, the system offers a cost-effective solution that can assist farmers in early diagnosis and management of plant diseases. This approach highlights the potential of image- based automated systems in supporting precision agriculture and improving crop health monitoring.

DOI: https://doi.org/10.5281/zenodo.19844732

Published by: vikaspatanker

Authors: Dhyanesh M, Dharshini S, Deepak P, Aisha Amna A

Abstract: Indian engineering institutions face significant administrative bottlenecks, ranging from repetitive circular drafting to manual, error-prone data entry for university mark sheets. CLARA.AI (Comprehensive LLM-powered Academic Resource Administrator) is a full-stack, AI-driven platform designed to automate and augment these critical workflows. Operating entirely on-premise to ensure data privacy, the system integrates a local Large Language Model (Llama 3.1 and 3.2 via Ollama) with a Django-based Model-View-Template architecture. Key innovations include an AI Circular Generator that overlays dynamically drafted text onto institutional letterheads, and an Intelligent Academic Analytics engine that utilizes coordinate-based table extraction and LLM metadata enrichment to parse complex PDF mark sheets. Furthermore, CLARA.AI features a hybrid Natural Language Query (NLPQ) pipeline and a robust four-tier Role-Based Access Control (RBAC) system. By seamlessly unifying data management and generative AI without relying on external cloud APIs, CLARA.AI represents a paradigm shift in secure, intelligent educational administration.

Published by: vikaspatanker

Authors: Ms.M.Devika, Mandyam Rohith Reddy, Kale Umamaheshwara Rao, Tamilarasan

Abstract: To maximize patient safety and comfort during medical procedures, effective anesthesia management requires closely monitoring and administering anesthesia for every procedure performed. If medications are not given to the appropriate degree of sedation, there could be potential complications or issues with correctly and efficiently completing the procedure. This paper will cover the development of an AI-based system using machine learning algorithms, including support vector regression (SVR), extreme gradient boosting (XGBoost), and transformer-based (Txb) models, to predict dosage(s) of anesthesia based on clinical information from the patient (demographics/vital signs/medical history) as well as characteristics associated with the procedure. Previous experiments have shown that the advanced machine learning methods discussed above yield greater accuracy and reliability than established methodology currently employed in anesthesia practice to estimate ideal anesthesia dosages. The proposed system will allow anesthesiologists to determine the appropriate dosage(s) of anesthesia to reduce exposure to risk and improve healthcare delivery efficiency through quality data to support better informed decisions.

Published by: vikaspatanker

Authors: Uzair Aman Syed, Prof. Sangeeta Vhatkar

Abstract: Water pollution poses significant threats to human health and the environment. The existing approaches to water quality measurement through hand sampling and the use of chemicals have two significant weaknesses: they are slow in delivery and do not cover all fields. According to the researchers, the AI based system that combines sensor networks with machine learning algorithms and real-time predictive models was designed to accomplish the following objectives: The system ensures continuous monitoring of the indicators of water quality. The system applies the correct techniques to estimate the concentra- tions of water pollutants. The system creates helpful measures that are used to deal with cases of water contamination. The experimental results have shown that the method proposed is very accurate in detection and response time is better than those of the conventional methods therefore making optimal decisions regarding environmental agencies and policymakers.

DOI: https://doi.org/10.5281/zenodo.19836127

Published by: vikaspatanker

Authors: Jag Pratap Singh Yadav

Abstract: Mathematical reasoning is now essential in the making of environmental decisions and policies in that it offers a means by which environmental dynamics can be modeled in order to identify uncertainties and evaluate policy alternatives. Mathematics not only serves to assist institutions in making sound environmental decisions; it defines for such institutions what constitutes an environmental problem and what can be done about it legally. The current essay explores the use of mathematical reasoning in the development of environmental policy. Specifically, it will examine the mathematical methodological basis of dynamical system theory, probability theory, optimization theory, and game theory in order to explore their implementation into regulatory regimes through integrated assessment models, cost-benefit analysis, and threshold regulation. With references to the development of cap-and-trade programs, management of fish stocks by targeting maximum sustainable yield, and carbon valuation through the social cost of carbon, the article shows how mathematical modeling can result in extremely successful policy frameworks when used in combination with institutional coherence and ecological sensibility, but also how false precision, biased assumption and value-laden ethical considerations can be concealed behind formal mathematical modeling. At the same time, the limitations of the conventional approach to the use of mathematical models in environmental policy making are discussed in relation to uncertainties and political tensions, as well as the dangers associated with excessive formalization and optimization, which can lead to indecision or to the depoliticization of value disputes. The key thesis developed in the paper is the need to recognize that mathematical models have power and must be subjected to reflection, criticism and democratic debate because they form the mediating language for making sense of the world and cannot remain apolitical and value-free.

DOI: https://doi.org/10.5281/zenodo.19835245

Published by: vikaspatanker

Authors: Jag Pratap Singh Yadav

Abstract: The increasingly urgent need for action under the 2020 Agenda has shown weaknesses in traditional environmental planning methods that view Sustainable Development Goals (SDGs) as independent and linearly achievable targets. In this paper, we establish a model that uses mathematics to reconfigure environmental planning into a nonlinear process, driven by interactions and bound by ecological principles. Considering biosphere-centered SDGs, the research formulates sustainability as a human-environment system where the dimensions of goals are shaped by inherent dynamics, intergoal linkages, and optimal policies. The suggested model framework employs a network of interactions to model the contextual dependency among the SDGs, state dynamics characterized by non-linearities to account for threshold and feedback effects, and planetary boundary restrictions for ecological plausibility. The environmental decision-making process is designed as a dynamic optimization model under uncertainty, where the total accomplishment of the SDGs is traded off against costs and the ecological bounds imposed by the planetary boundaries. To make use of the model, a database structure based on multiple sources of information, including earth observation systems, development indicators, and SDG databases, is created. The example of the Amazon basin application shows the importance of the framework both analytically and practically. The comparison between the Business-as-Usual scenarios and the mathematically optimal interventions shows that traditional methods result in fragmented progress and growing pressure on ecosystems, while the use of optimization improves system integration and leads to better results. The sensitivity analysis performed via Monte Carlo methods proves that this effect remains even under conditions of high uncertainty and worsened climatic conditions. The results will help advance the field of sustainability science because they will provide a replicable and policy-relevant structure to study the interaction between the SDGs. The research concludes that meeting the objectives of the SDGs would require an approach that moves away from optimizing individual sectors and goals independently towards using more holistic and dynamic approaches to planning that incorporate interactions between goals and constraints imposed by natural boundaries.

DOI: https://doi.org/10.5281/zenodo.19835078

Published by: vikaspatanker