Authors: Husna Sultana, Irfan Ahmed, Shivani

Abstract: Interpreting the Urban Black Box, the proliferation of sensors and Internet of Things (IoT) infrastructure in Smart Cities has enabled the development of highly accurate Spatio-Temporal Data Mining models, often relying on deep learning architectures like Graph Neural Networks (GNNs), for tasks such as traffic prediction, crime forecasting, and resource management. Despite their high predictive performance, these models remain "black boxes," hindering their adoption by urban planners and emergency services who require transparency and justification for critical operational decisions. This lack of interpretability poses significant challenges to accountability, auditability, and public trust. This paper addresses the critical need for Explainable AI (XAI) in the urban domain by proposing a novel Spatio-Temporal XAI (ST-XAI) Framework designed for Causal Feature Attribution. Our framework leverages a modified version of SHapley Additive exPlanations (SHAP) combined with the inherent spatial and temporal structure of the data to provide granular, instance-based explanations. The proposed methodology focuses on Temporal Attribution: Quantifying the specific influence of various look-back time windows (e.g., data from the last hour vs. data from 24 hours ago) on the current prediction. Spatial Attribution: Identifying and weighting the contributing influence of specific geographic nodes, links, or neighboring zones within the network structure. Causal Inference: Moving beyond mere correlation by prioritizing features that exhibit a strong, temporally preceding impact, providing a more actionable justification for the prediction. We demonstrate the ST-XAI Framework on a smart traffic prediction model, showing how it successfully translates opaque deep learning outputs into clear, human-understandable narratives. The results illustrate that our framework not only validates model efficacy but also acts as a vital debugging tool for city engineers, transforming black-box predictions into accountable and actionable urban intelligence.

DOI: http://doi.org/10.5281/zenodo.17720787

Published by: vikaspatanker

Authors: Chidanandamurthy G

Abstract: This study compares productivity and carbon performance of organic agroforestry (ORG-AF) and conventional agroforestry (CON-AF) using paired plots under similar soil and climatic conditions. Six pairs of 0.25 ha plots were monitored for three years. System productivity was calculated as the sum of all marketable crop and tree products per hectare, while carbon stocks were derived from tree and crop biomass and soil organic carbon (0-30" " cm). Life cycle inventories of all inputs and field operations were compiled to estimate greenhouse gas emissions and carbon footprints per hectare and per kilogram of product. CON-AF achieved higher system yields (mean 5,808" " kgha^(-1)) than ORG-AF (mean 5,017 kgha^(-1)), a difference of about 16%. In contrast, tree biomass increment was greater in organic plots (3.55tha^(-1) yr^(-1)) than in conventional plots ( 2.55tha^(-1) yr^(-1)), and soil carbon increased faster in ORG-AF (0.43tCha-1yr^(-1)) than in CON-AF (0.16tCha^(-1) yr^(-1)). Total annual carbon stock change averaged 2.09tCha^(-1) yr^(-1) in ORG-AF and 1.36tCha^(-1) yr^(-1) in CON-AF. Area-based carbon footprints were 2,950 and 4,150" " kgCO_2-eq ha^(-1) yr^(-1) for organic and conventional systems, respectively, while product-based footprints were 0.59 and 0.71" " kgCO_2-eq kg^(-1). Both systems acted as net carbon sinks, but net carbon balance was much higher in ORG-AF (4.7vs.0.8tCO_2-eq ha^(-1) yr^(-1)). The results show that organic agroforestry can maintain high productivity while substantially improving carbon efficiency and climate mitigation potential.

DOI: http://doi.org/10.5281/zenodo.17720645

Published by: vikaspatanker

Authors: Dr. Latha H R

Abstract: Secure communication and computing is the vital requirement of the day as global networks and information systems are expanding like the big bang theory of the universe. People have started treating information as an asset. The information asset needs to be secured from attacks. Everything in the world is being upgraded to electronic communication and this requires protection against data fraud. Information has chosen different media like text, image, audio, video and multimedia for its existence. Cryptography is the science which provides techniques for securing information over network. Network security is the process of taking physical and software measures to protect underlying infrastructure. This paper introduces cryptography, chaotic cryptography, its computational power in image security. It proposes new sealion algorithm to increase the computational power of cryptographic algorithms. It also verifies the efficiency of proposed algorithm against benchmarks set for the security of images over network.

DOI: http://doi.org/10.5281/zenodo.17720340

Published by: vikaspatanker

Authors: Indu Shinde, Sarvada Anvekar, Purva Nargide, Shravni Shikhre, Shantu Pujari, Professor P.S.Pandhre

Abstract: Access to legal information and assistance remains a major challenge for many individuals due to high costs, lack of awareness, and geographical barriers. With the rapid growth of Artificial Intelligence (AI) and Natural Language Processing (NLP), chatbots have become an effective tool for improving access to information and services. This research paper presents the design, development, and evaluation of a Legal Aid Chatbot that provides preliminary legal guidance to users in a simple and accessible manner. The system uses NLP techniques, machine learning models, and a structured legal knowledge base to understand user queries and generate meaningful responses.

Published by: vikaspatanker

Authors: Girish Kishor Ingavale

Abstract: The substantial expansion of hyperscale data centers, driven by exponential growth in cloud computing, artificial intelligence, and distributed computing architectures, has created a critical energy crisis characterized by unsustainable power consumption patterns and substantial carbon emissions. Conventional energy infrastructure, encompassing fossil fuel generation and intermittent renewable sources, demonstrates fundamental inadequacies in satisfying the stringent requirements for continuous baseload power, grid stability, and cost predictability demanded by contemporary data center operations. These deficiencies manifest through supply volatility, carbon intensity concerns, escalating transmission costs, and the inherent inability of renewable portfolios to guarantee uninterrupted power delivery without extensive energy storage systems. Nuclear energy presents a strategically viable solution, characterized by exceptional capacity factors exceeding 90%, negligible greenhouse gas emissions during operation, and energy density several orders of magnitude superior to alternative generation technologies. This article provides a rigorous examination of nuclear power integration strategies for data center infrastructure optimization, emphasizing quantitative improvements in energy efficiency metrics, decarbonization outcomes, and operational resilience. Through systematic comparative analysis employing established performance indicators and lifecycle assessment methodologies, this investigation substantiates the transformative potential of nuclear power adoption in enterprise-scale computing facilities. Principal findings demonstrate that nuclear-powered data centers achieve carbon emission reductions of 92-98% relative to coal-fired generation and 85-90% compared to natural gas combined-cycle plants. Economic analysis reveals levelized cost of energy (LCOE) reductions of 25-40% over 30-year operational horizons, accounting for capital expenditure amortization, fuel costs, and decommissioning provisions. Operational metrics indicate sustained power availability factors of 99.97%, representing a 15-20% improvement over grid-dependent configurations subject to transmission constraints and generation intermittency. Integration of nuclear baseload capacity with advanced power distribution architectures yields Power Usage Effectiveness (PUE) improvements of 35-45%, attributable to elimination of redundant uninterruptible power supply (UPS) systems and optimization of thermal management infrastructure. Small Modular Reactor (SMR) technologies and fourth-generation microreactor designs demonstrate applicability to distributed data center architectures, offering scalable deployment models ranging from 1 MWe to 300 MWe capacity with enhanced passive safety systems and reduced physical footprints. The substantial capital requirements for nuclear infrastructure development, estimated at $5,000-$8,000 per installed kilowatt for SMR deployments, are economically justified through comprehensive total cost of ownership (TCO) analysis incorporating energy price stability, carbon compliance costs, and operational expenditure reductions over multi-decade asset lifecycles. Regulatory frameworks governing nuclear facility licensing, operational oversight, and decommissioning obligations are examined within the context of data center deployment scenarios, identifying pathways for streamlined approval processes and public-private partnership structures. This research advances the academic discourse on sustainable computing infrastructure by providing evidence supporting nuclear power adoption as an essential component of decarbonization strategies for the information technology sector.

DOI: http://doi.org/10.5281/zenodo.17711318

Published by: vikaspatanker

Authors: Priya Deshpande

Abstract: Generative Artificial Intelligence (AI) has emerged as a revolutionary force in transforming IT operations through adaptive automation. This advancement is reshaping traditional IT frameworks by enabling systems to dynamically learn, adapt, and optimize processes autonomously. Adaptive automation in IT focuses on the seamless integration of human decision-making and machine-driven responses, improving efficiency, reducing human error, and enhancing predictive maintenance capabilities. Generative AI models, powered by deep learning and advanced neural networks, contribute significantly by generating innovative solutions, automating complex workflows, and providing real-time actionable insights. The incorporation of generative AI enhances the agility and resilience of IT operations, allowing faster incident response, proactive problem resolution, and intelligent resource allocation. This article explores the intersection of generative AI and adaptive automation in IT operations, highlighting the evolution, benefits, challenges, and future directions. The synergy of these technologies promises to address the increasing complexity of modern IT environments while supporting continuous improvement and scalability. With the critical role IT plays in business continuity and innovation, generative AI-driven adaptive automation stands as a key enabler for the next generation of operational excellence. The discussion encompasses the technological underpinnings, practical applications, and strategic implications for organizations aiming to leverage AI to its fullest potential in their IT operations.

DOI: https://doi.org/10.5281/zenodo.17709327

 

Published by: vikaspatanker

Authors: Dev Malik

Abstract: Cognitive automation, an advanced form of artificial intelligence (AI) that integrates machine learning, natural language processing, and robotic process automation, is transforming enterprise compliance operations. Enterprises today face intensifying regulatory scrutiny, increasing the complexity and volume of compliance requirements. Cognitive automation helps address these challenges by automating complex tasks, reducing human error, accelerating compliance processes, and improving overall coverage. Unlike traditional rule-based automation, cognitive automation can learn from data, understand context, and adapt to new situations, making it highly suitable for the dynamic regulatory environment businesses operate in today. This article explores how cognitive automation influences enterprise compliance operations, focusing on its capabilities to enhance data handling, risk management, regulatory reporting, and audit readiness. It also discusses practical implementation approaches, benefits, and challenges encountered by enterprises adopting this technology. Furthermore, the article examines real-world use cases that demonstrate cognitive automation's effectiveness in improving compliance efficiency and accuracy. As regulatory landscapes continue to evolve and expand, cognitive automation emerges as a vital tool for enterprises seeking to maintain compliance while optimizing operational costs and minimizing risks. This article provides a comprehensive overview for business leaders, compliance officers, and IT professionals interested in leveraging cognitive automation to strengthen their compliance frameworks, improve decision-making, and support sustainable enterprise governance.

DOI: https://doi.org/10.5281/zenodo.17709139

Published by: vikaspatanker

Authors: Sanjana Rao

Abstract: Sustainable energy consumption in data centers has emerged as an urgent global priority as digital transformation accelerates and the demand for cloud computing, data storage, and processing escalates dramatically. Data centers, pivotal infrastructure for the digital economy, are also substantial consumers of electricity and significant sources of greenhouse gas emissions. The integration of artificial intelligence (AI) technologies introduces promising avenues to enhance energy efficiency, optimize resource management, and ultimately contribute to sustainability goals. AI-driven systems can analyze vast amounts of operational data in real-time, enabling predictive maintenance, smart cooling, dynamic workload management, and energy-aware orchestration of resources. These capabilities reduce energy waste and minimize carbon footprints while ensuring robust performance. This article explores the multitude of ways AI influences energy consumption patterns in data centers, including machine learning techniques for demand forecasting, innovative cooling solutions, renewable energy integration, and automated control systems. It also examines challenges such as the energy demands of AI itself and the need for transparent, ethical AI governance. Through the lens of case studies and emerging technologies, this synthesis underlines the transformational potential of AI in promoting sustainable data center operations, offering insights valuable for industry stakeholders, researchers, and policymakers. Ultimately, embracing AI as a core component of data center management aligns with broader objectives of climate responsibility and operational resilience in the digital age.

DOI: https://doi.org/10.5281/zenodo.17708969

Published by: vikaspatanker

Authors: Aditya Bhandari

Abstract: Artificial Intelligence (AI) has emerged as a transformative force in IT infrastructure management, particularly in optimizing workload balancing across multi-cloud environments. Multi-cloud infrastructures, which involve the utilization of multiple cloud services from different providers, present a complex landscape for businesses seeking high availability, scalability, and cost efficiency. The dynamic nature of workloads, variability in service level agreements (SLAs), and diverse cloud resource characteristics necessitate intelligent automation to optimize performance. AI-driven approaches leverage machine learning algorithms, predictive analytics, and autonomous decision-making to manage workload distribution effectively, ensuring optimal utilization of resources while minimizing latency and operational costs. This article delves into the integration of AI in multi-cloud workload balancing, exploring how it addresses challenges such as resource heterogeneity, network latency, and fluctuating demand patterns. We discuss various AI techniques, including reinforcement learning, neural networks, and evolutionary algorithms, that are employed to predict workload behavior and automate deployment decisions. Additionally, the article examines real-world case studies highlighting successful AI implementations and outlines the future trajectory of this synergy. By adopting AI-driven workload optimization, organizations can enhance resilience, improve user experience, and achieve sustainable cloud operations amid the rapidly evolving digital ecosystem.

DOI: https://doi.org/10.5281/zenodo.17708834

Published by: vikaspatanker

Authors: Yash Pratap Singh, Tanya Dwivedi

Abstract: Agriculture plays a major role in the economy and livelihood of many people, especially in developing countries. Farmers often face difficulties in choosing the correct crop because soil nutrients, weather conditions, and rainfall vary from place to place. Choosing the wrong crop can reduce yield and lead to financial loss. To solve this problem, a machine learning based crop recommendation system can be used. This system analyzes soil features such as Nitrogen (N), Phosphorus (P), Potassium (K), pH value, and environmental factors like temperature, rainfall, and humidity. Based on these inputs, the system suggests the most suitable crop for cultivation. In this research, different machine learning algorithms are studied, and Random Forest is selected theoretically because it provides high accuracy and stable performance. The main aim of this study is to support farmers in making better decisions, reduce risk, and improve productivity. The proposed approach is simple, understandable, and can be further developed into a mobile or web application for real-world use.

DOI: http://doi.org/10.5281/zenodo.17708787

Published by: vikaspatanker