Category Archives: Uncategorized

Authors: Prathibhavani P M, Pragathi S

Abstract: We propose a Custom GPT System that allows domain-specific adaptation of a large language model through a flexible, modular pipeline. The system uses a Python Flask REST API as the backend server, facilitating a microservices-style deployment of core components. A high performance Groq API endpoint executes inference on Meta’s LLaMA 3 model (available in 8B and 70B parameter sizes) to generate responses. Crucially, our pipeline integrates a Retrieval Augmented Generation (RAG) stage: incoming queries trigger semantic retrieval from a vector store of domain documents, and the returned context is combined with the user prompt to guide generation. Prompts and model settings are parameterized via human-readable YAML configuration files, enabling easy customization of system behaviour and personality. This architecture can be applied to sectors like healthcare, education, and customer support by supplying relevant documents and prompt templates. We describe the system architecture (see Fig. 1), implementation details, and an API-based deployment strategy. In evaluation, the Groq-accelerated LLaMA 3 achieves up to 18× throughput improvements versus a GPU baseline, and the RAG component markedly reduces hallucinations by grounding output in up-to-date knowledge.

DOI: http://doi.org/10.5281/zenodo.16444282

 

 

Published by: vikaspatanker

Authors: Ms. Sonia, Mr. Aditya Goel, Mr. Aneek Kumar, Mr. Kushagra, Ms. Chandni Kumari

Abstract: – This paper presented the development of a Smart Mirror, a device that integrates real- time information display with everyday utility. Designed by college students, the Smart Mirror was built entirely using Python libraries and provided functionalities such as news feeds, weather updates, calendar events, reminders, and basic time and date display. The project emphasized software development using Python and various APIs to create an interactive and user- friendly interface. The Smart Mirror aims to enhance daily routines by reducing the need for multiple devices while maintaining simplicity and efficiency.

DOI: http://doi.org/10.5281/zenodo.16608809

Published by: vikaspatanker

Authors: Dr. Saumendra Mohanty

Abstract: – Food wastage contributes significantly to global environmental degradation and economic inefficiencies, particularly in developing countries. This study investigates the trend and forecast of per capita food wastage in Nepal using a simple Linear Regression model applied to UNEP and FAO datasets (2015–2021). The findings assess the nation’s trajectory against the Sustainable Development Goal (SDG) 12.3, which aims to halve food waste by 2030. The analysis reveals that Nepal is not on track to meet this target unless intervention strategies are urgently adopted. We also discuss the potential of data-driven policymaking to guide national sustainability

Published by: vikaspatanker

Authors: Aliya Fulara

Abstract: Biophilic design is a powerful architectural and psychological approach that reconnects humans with nature. This study investigates the impact of biophilic elements in rehabilitation environments, particularly in centers aimed at treating various forms of addiction and psychological stress. Through the integration of natural materials, daylight, vegetation, water features, and views of nature, biophilic design can significantly improve patient recovery rates, reduce stress, and enhance emotional well-being. The paper explores how spatial design rooted in biophilic principles—such as natural ventilation, organic forms, and immersive landscapes—can promote healing. It also examines case studies and concludes with recommendations for designing restorative spaces that prioritize the human-nature connection. This research aims to guide architects, planners, and healthcare professionals in creating rehabilitation spaces that truly support holistic recovery. It explores global examples and proposes strategies to integrate these principles in future rehabilitation architecture. The results affirm the positive impact of nature on healing, mental restoration, and long-term patient engagement.

 

Published by: vikaspatanker

Authors: Sakshi Gajanan Jayale, Jayant Ingole, Saiyam.S. Chaturvedi, Saiyam.S. Chaturvedi, Dr. Sudhir V. Dhomane, Dr. P. V. Thorat

Abstract: In the wake of escalating climate change and environmental degradation, green building technologies have emerged as essential strategies in sustainable development. This seminar explores the relationship between built environments and the natural ecosystem, emphasizing the pivotal role of buildings in energy consumption, carbon emissions, and global warming. The study categorizes green technologies that enhance energy efficiency, occupant comfort, and environmental performance through passive and active systems such as thermal mass utilization, natural ventilation, stack effect, daylighting, and high-performance glazing. It also underlines adaptive strategies to respond to climate projections using mitigation and resilience-based approaches. The report introduces a structured methodology for integrating these technologies into new and existing buildings, highlighting key principles like integrated design, responsive planning, performance benchmarking, and climate adaptation. By bridging theoretical frameworks with practical design applications, this research reinforces the potential of green building strategies to minimize ecological footprints while ensuring productivity, health, and comfort within the built environment.

DOI:

 

 

Published by: vikaspatanker

Authors: Sharyu Chinchole

Abstract: As climate change continues to reshape coastlines and alter ecosystems, architecture stands at a crossroads—between crisis and creativity. This research explores the architectural response to rising sea levels through the lens of adaptive overwater villas. Traditionally associated with luxury, overwater villas are reimagined here as resilient, climate-responsive habitats that float, adapt, investigates and endure. The study floating systems, modular strategies, sustainable design tools, and precedents from across the globe, aiming to develop a contextual, feasible solution for future-ready living. The final proposition blends engineering and environmentalism into a design that is not only functional but poetic—an architecture that floats with the planet, not against it.

DOI:

 

 

Published by: vikaspatanker

Authors: Shreyash Akole, Mansi Rakhonde, Saish Desai

Abstract: The rapid growth of online news and digital media has significantly impacted financial markets, where even a single headline can influence investor behavior. With this increasing dependence on news, ensuring the authenticity and sentiment of financial information has become more important than ever. This research presents a dual-purpose system that combines stock market news sentiment analysis with fake news detection. Our model aims to solve this by using Natural Language Processing (NLP) techniques and Machine Learning (ML) algorithms to analyze financial news, detect fake information, and suggest investment actions such as Buy, Sell, or Hold. This system uses Bidirectional Encoder Representations from Transformers (BERT) and Long Short-Term Memory (LSTM) models for sentiment and authenticity analysis, ensuring reliability and accuracy. The framework empowers traders, investors, and institutions to make smarter, safer financial decisions by combining sentiment analysis and fake news detection into a single platform. Most systems only do either sentiment analysis or fake news detection. Our system does both in one place, making it more reliable. It reached 93% accuracy in sentiment analysis and 96% in fake news detection, helping users make better and safer financial decisions.

DOI:

 

 

Published by: vikaspatanker

Authors: P Prakash, Aakash K, Amizhdhan L, Pragathesh Kumar, L. Kannagi

Abstract: This autonomous agricultural vehicle, equipped with a camera and GPS, is designed to optimize farming efficiency by automating critical tasks such as harvesting, weed removal, and pest control. The vehicle autonomously navigates through fields, reducing the reliance on manual labor while ensuring precise and timely execution of agricultural operations. For harvesting, the vehicle identifies and collects ripe crops efficiently, minimizing losses and enhancing overall productivity. In weed removal, it detects and eliminates unwanted plants, ensuring crops have access to nutrients without competition. For pest control, the vehicle monitors plant health and identifies areas affected by pests, applying treatments only where necessary. This targeted approach reduces pesticide use, contributing to eco-friendly and sustainable farming practices. With smart navigation and obstacle avoidance, the vehicle operates seamlessly in large and complex agricultural environments. By integrating automation into farming practices, this vehicle not only enhances productivity but also reduces costs, making it an essential component of modern precision agriculture.

DOI: http://doi.org/10.5281/zenodo.16607776

Published by: vikaspatanker

Authors: Ms. Usha Dhankar, Ms. Srishty Goswami, Himanshu Sharma, Nikhil Tiwari, Vansh Gupta

Abstract: – As networks become more complex and expansive, traditional security monitoring methods often fall short in detecting and responding to fast-evolving threats. This is where visualization steps in—turning overwhelming amounts of raw data into clear, intuitive visuals that help security teams spot anomalies, recognize attack patterns, and make faster, more informed decisions. In this paper, we explore how visualization techniques are revolutionizing network security, from analysing traffic and detecting intrusions to correlating security events. We also address real-world challenges, such as information overload, false alarms, and the difficulties of integrating these tools into large-scale systems. Looking ahead, we examine the future of security visualization—AI-driven insights, immersive environments like VR, and dynamic dashboards that make threat detection more interactive. By shedding light on these advancements, we highlight how visualization isn’t just a helpful tool but a critical component of modern, proactive cybersecurity.

DOI: http://doi.org/10.5281/zenodo.16607552

Published by: vikaspatanker

Authors: Ms. Gurpreet Kaur, Mayank Gupta, Kanak Sharma, Sarthak Goel

Abstract: The use of artificial intelligence (AI) in medicine has created medical Chat – bots that supports real -time patients, symptom assessment, early diagnosis and supportive patient training. However, traditional Chat – bot models based on static database or pre-influensing reactions have problems with chronic information, reference upheaval and the possibility of incorrect information. Recovery-sized generation (RAG) is a sophisticated AI model that supports the chat bot capacity by integrating a recovery system with generative AI, and ensures that reactions are relevant sounds and most infected with today's medical knowledge. This article emphasizes the main elements of the theoretical base and the real application of Raga-based medical chat bots that enable better accuracy, flexibility and user interactions. We discuss architecture, recycling process and response generation mechanisms that distinguish rag from traditional NLP – based chat-bots. In addition, we explain in detail about the significant strength of Rag, such as medical accuracy, real -time flexibility and adapted patient interaction. While the possibilities are very good, the implementation of carpet -based medical chat-bots is accompanied by computational overhead, data security and difficulties with regulatory requirements. We discuss these boundaries in adding possible solutions to make chat bot more reliable and effective. Case studies of real implementation also give us a picture of how effective they are and practically how they are used in modern health care. Finally, we identify future research directions by integrating RAG-based medical chat bot with new techniques such as IOT, Block chain and Multi-model AI to further change the digital health service. By addressing these main areas, this research tries to contribute to continuous progress of AI-driven medical chat bot, so that they can become an integral part of both health care professionals and patients.

DOI: http://doi.org/10.5281/zenodo.16608602

Published by: vikaspatanker