Authors: Ira Chaturvedi

Abstract: The rapid digitization of corporate finance and the increasing complexity of global regulatory frameworks have necessitated a shift from manual oversight to intelligent automation. This review article investigates the integration of Machine Learning algorithms within the SAP S/4HANA ecosystem to enhance financial compliance and reporting efficiency. By leveraging the SAP Business Technology Platform, organizations can move beyond traditional rule-based systems to implement real-time anomaly detection, automated intercompany reconciliations, and predictive financial closing processes. The analysis explores the technical architecture required to bridge the gap between transactional data and autonomous governance, highlighting the role of the Universal Journal as a single source of truth. Furthermore, the article addresses the strategic challenges of data orchestration, the necessity of Explainable AI for auditability, and the emerging role of Natural Language Processing in interpreting unstructured regulatory documents. As financial reporting transitions toward a continuous monitoring model, the synergy between ERP robustness and machine intelligence becomes a critical factor in reducing operational risk and ensuring transparency. The findings suggest that while intelligent automation significantly reduces the manual burden of compliance, a human-in-the-loop approach remains essential for maintaining ethical oversight and professional judgment. Ultimately, this review provides a comprehensive framework for organizations seeking to leverage SAP and machine learning to transform the finance function into a proactive strategic asset.

DOI: http://doi.org/10.5281/zenodo.18159753

Published by: vikaspatanker

Authors: Kabir Sehgal

Abstract: The seamless integration of the Internet of Things (IoT) with Cloud Computing has revolutionized data-driven ecosystems, yet it has simultaneously birthed a sophisticated class of "Invisible Risks." Unlike traditional cyber threats that target known software vulnerabilities or hardware weaknesses, invisible risks emerge from the systemic complexity, algorithmic opacity, and "gray-zone" interactions inherent in distributed architectures. These risks including data shadowing, logic flaws in cross-protocol interoperability, and the silent propagation of algorithmic bias—often bypass conventional signature-based detection systems, remaining latent until they manifest as catastrophic failures. This review article proposes a comprehensive Conceptual Framework for Managing Invisible Risks by synthesizing multi-disciplinary research across cybersecurity, system engineering, and cognitive psychology. We categorize these risks across a four-tier architecture: the Perception, Network, Cloud, and Application layers. Each layer is analyzed to identify the "invisibility triggers" that obscure threat vectors from administrative oversight. Furthermore, the paper evaluates contemporary risk assessment methodologies, advocating for a transition from static monitoring to dynamic observability through the use of Bayesian Networks, Digital Twins, and Chaos Engineering. We propose a proactive management strategy anchored by three pillars: Zero Trust Architecture (ZTA), AI-driven Automated Governance, and Edge Intelligence. The framework aims to bridge the "transparency gap" in Cloud-IoT environments, providing researchers and practitioners with a structured roadmap to identify, quantify, and mitigate hidden threats. Finally, the article discusses future directions, including the role of blockchain for provenance and quantum-resistant cryptography, emphasizing that the future of Cloud-IoT security depends on our ability to make the invisible visible.

DOI: http://doi.org/10.5281/zenodo.18159648

Published by: vikaspatanker

Authors: Navya Kulshreshtha

Abstract: The rapid evolution of Industry 4.0 has necessitated a transition from traditional administrative Enterprise Resource Planning (ERP) to "Intelligent ERP" systems that leverage real-time operational data. This review article investigates the optimization of ERP performance through the integration of Machine Learning (ML)–based Predictive Maintenance (PdM) models. While traditional maintenance strategies within ERP namely reactive and preventive often lead to unplanned downtime or resource wastage, ML-based PdM offers a data-driven alternative that predicts equipment failure before it occurs. This study synthesizes current literature regarding the architectural integration of Industrial Internet of Things (IIoT) sensors with ERP modules, such as Asset Management, Production Planning, and Materials Management. We categorize the predominant ML methodologies including Supervised Learning for fault classification, Deep Learning (LSTM and GRU) for Remaining Useful Life (RUL) estimation, and Unsupervised Anomaly Detection evaluating their specific contributions to enterprise-level efficiency. The review highlights how PdM-driven insights directly optimize ERP Key Performance Indicators (KPIs) by reducing maintenance costs, streamlining spare parts inventory through Just-in-Time (JIT) procurement, and enhancing Overall Equipment Effectiveness (OEE). Furthermore, the article addresses critical implementation challenges, such as data silos, scalability, and the "black box" nature of AI models. By analyzing the synergy between predictive analytics and resource orchestration, this review provides a roadmap for researchers and practitioners to build resilient, self-optimizing industrial ecosystems. The findings suggest that the integration of ML-PdM is no longer a peripheral technical upgrade but a core strategic necessity for modern enterprise resource management, enabling a shift from descriptive reporting to prescriptive action.

DOI: http://doi.org/10.5281/zenodo.18159637

Published by: vikaspatanker

Authors: Shaurya Tomar

Abstract: The integration of Artificial Intelligence (AI) with the Internet of Medical Things (IoMT) has birthed a new generation of Clinical Decision Support Systems (CDSS) capable of real-time physiological monitoring. This review article examines the architectural and methodological shift from rule-based alerts to predictive AI engines that process high-frequency data from connected medical devices. We investigate the core pipeline of these systems—from signal denoising at the Edge to deep learning-based feature extraction in the Cloud—and evaluate how these technologies address the "data deluge" currently overwhelming clinical staff. The article provides a detailed taxonomy of AI methodologies, including Supervised Learning for diagnosis, Reinforcement Learning for treatment optimization, and the rising role of Explainable AI (XAI) in fostering clinician trust. Key clinical use cases are explored, ranging from early sepsis detection in the ICU to the management of chronic conditions like diabetes through closed-loop artificial pancreas systems. Furthermore, we address the critical barriers to adoption, specifically focusing on data quality, clinical alarm fatigue, and the "interoperability gap" between siloed medical systems. Finally, the review analyzes the 2025 regulatory landscape, including the impact of the EU AI Act and the FDA's evolving SaMD guidelines. We conclude that while AI-powered CDSS offers unprecedented potential for proactive care, its success depends on maintaining a "Human-in-the-Loop" approach, ensuring that AI augments rather than replaces clinical expertise.

DOI: http://doi.org/10.5281/zenodo.18159591

Published by: vikaspatanker

Authors: Prisha Malviya

Abstract: The rapid proliferation of Internet of Things (IoT) devices, coupled with the high-performance analytical capabilities of Cloud Computing, has created an interdependent ecosystem that relies heavily on wireless network infrastructures. However, this integration introduces significant security vulnerabilities, as the broadcast nature of wireless communication leaves data susceptible to jamming, eavesdropping, and sophisticated man-in-the-middle attacks. This review article systematically investigates the current landscape of Risk-Aware Cloud Computing Frameworks designed to secure IoT communications. We propose a multi-dimensional taxonomy that categorizes these frameworks based on their architectural distribution (Cloud-to-Edge), their risk-assessment methodologies (Probabilistic vs. AI-driven), and their decision-making logic (Reactive vs. Proactive). The article provides a deep dive into the "Resource-Security Paradox," analyzing how risk-aware models optimize the trade-off between cryptographic overhead and device longevity. Furthermore, we provide a comparative analysis of state-of-the-art frameworks, evaluating them against key performance metrics such as detection accuracy, latency, and energy efficiency. Significant attention is given to the role of Software-Defined Networking (SDN) and Trust Management Systems in providing real-time mitigation of wireless threats. Finally, the article identifies critical research gaps and discusses emerging trends, including Zero Trust Architectures (ZTA), Quantum-Resistant Cryptography, and the impact of 6G on IoT security. This review aims to provide a comprehensive reference for researchers and practitioners working to build resilient, self-adaptive security infrastructures for the future of the interconnected world.

DOI: http://doi.org/10.5281/zenodo.18159497

Published by: vikaspatanker

Authors: Rudra Narayan

Abstract: The exponential growth of data in healthcare and financial sectors presents unique challenges in storage, processing, and real-time analytics. High-velocity data streams—originating from electronic health records (EHRs), IoT medical devices, stock trading systems, and payment networks require sophisticated frameworks capable of handling large volumes with minimal latency. SAP HANA, an in-memory, columnar database platform, offers real-time processing capabilities that allow organizations to integrate advanced analytics and machine learning (ML) directly into transactional and operational data environments. By leveraging AI and ML, healthcare institutions can predict patient outcomes, optimize treatment plans, and enhance diagnostic accuracy, while financial organizations can detect fraud, assess risk, and execute high-frequency trading strategies efficiently. This review article explores the convergence of AI/ML techniques with SAP HANA for high-velocity data analytics, emphasizing both technical implementation and domain-specific applications. We provide an overview of SAP HANA’s architecture, predictive analytics libraries, and integration approaches with external ML frameworks such as Python, R, TensorFlow, and PyTorch. The article also examines real-time data pipelines, model deployment strategies, and key challenges, including data privacy, scalability, and model interpretability. Case studies in healthcare demonstrate predictive modeling for patient management, disease diagnosis, and imaging analytics, while financial applications highlight fraud detection, real-time risk assessment, and market analytics. Furthermore, the review discusses benefits such as reduced latency, improved decision-making, and operational efficiency, alongside limitations that include heterogeneous data integration, regulatory compliance, and model transparency. Finally, future research directions are outlined, including deep learning integration, edge computing for real-time analytics, hybrid cloud deployments, and explainable AI methodologies. This review serves as a comprehensive resource for researchers, practitioners, and decision-makers seeking to understand the potential of AI and ML integration within SAP HANA for processing and analyzing high-velocity healthcare and financial data efficiently and effectively.

DOI: http://doi.org/10.5281/zenodo.18159474

Published by: vikaspatanker

Authors: Anvi Saxena

Abstract: The rapid growth of cloud computing has transformed the way organizations deploy, manage, and scale their IT infrastructure. Traditional single-cloud deployments often face limitations such as vendor lock-in, scalability bottlenecks, reliability issues, and security vulnerabilities. To address these challenges, multi-cloud strategies have emerged as a viable solution, enabling organizations to leverage multiple cloud service providers simultaneously. This review article presents an analytical study of multi-cloud strategies, emphasizing their impact on scalability, reliability, and data security. Scalability is a critical requirement in modern IT ecosystems, allowing dynamic resource allocation based on workload demands. Multi-cloud strategies enhance scalability by distributing workloads across several providers, enabling organizations to optimize performance and reduce latency. Reliability, or the ability of a system to maintain continuous service despite failures, is also improved in multi-cloud environments. By implementing redundancy and failover mechanisms across multiple clouds, organizations can achieve high availability and disaster recovery capabilities that are difficult with single-cloud architectures. Data security is another crucial consideration, as storing sensitive information across multiple platforms introduces potential vulnerabilities. Multi-cloud strategies can mitigate security risks through encryption, identity and access management, compliance adherence, and robust monitoring practices. This review systematically examines recent literature and case studies, highlighting different multi-cloud approaches, their benefits, and associated challenges. Additionally, it identifies gaps in current research, particularly in areas such as interoperability, orchestration, and automated management. The article also explores emerging trends, including AI-assisted cloud management, edge computing integration, and serverless architectures, which can further enhance multi-cloud effectiveness. Ultimately, this review provides a holistic understanding of how multi-cloud strategies contribute to improved scalability, reliability, and data security, offering valuable insights for researchers, IT architects, and organizational decision-makers aiming to optimize cloud infrastructure for the evolving digital landscape.

DOI: http://doi.org/10.5281/zenodo.18159410

Published by: vikaspatanker

Authors: Dr. Pranav Mulaokar

Abstract: When interviewing the first year engineering students, it was observed that there is the urgent need to empower them with communication skills. This research paper focuses on the importance of communication, proficiency in English, concepts of LSRW, common mistakes, soft skills and global relevance. During the survey, the observations and recommendations were noted. English communication comes into light for international collaboration, technical documentation, workplace situations, etc. Real-life application of communication should be taught from the beginning of the learning process. The challenges which students face are discussed and solutions provided. The global scope of being a good communicator is noted in the paper.

Published by: vikaspatanker

Authors: Dr. Bangarappa L, Dr. Danappa G.T

Abstract: This present study has provided the fabrication of Mg/MWCNT nano composites, Mg/FA and Mg/MWCNT/FAhybrid nano composites with powder metallurgy processing techniques. The specimens prepared were characterized for mechanical properties like density of the materials, Vickers hardness, elastic modulus, and tensile properties. Nanocomposites are versatile material or multi-functional materials achieved by the unnatural mixture of verities of materials in turn to attain the characteristics in separate components by it that can’t be overcome. The extraordinary attention on carbon nano tubes were due to their unique structure and characteristics, they have a very tiny size of about 0.42nm and less than in diameter & the mechanical properties they exhibit. Carbon nanotubes have been expected to be one of the best reinforced materials to enhance the mechanical characterization as they possess good young’s modulus along with material strength and aspect ratios.

DOI:

Published by: vikaspatanker

Authors: Sukanya, G.Bharath Kumar, Karthik.D, Nikhil Reddy, ChannaKeshwa

Abstract: Crop diseases pose a major global threat to agricultural productivity, farmer income, and overall food security. Widespread disease outbreaks reduce crop quality, decrease yield, and contribute to economic instability—especially in regions dependent on agriculture for livelihood. The complexity of crop diseases arises from diverse environmental conditions, varying plant species, and the presence of multiple visually similar infections. Addressing these challenges requires a systematic, data-driven approach capable of identifying hidden patterns and supporting farmers and agricultural experts with timely, actionable insights. This project presents the design and development of an AI- Driven Crop Disease Prediction and Monitoring Dashboard, an interactive platform built using Streamlit. The dashboard enables visualization, prediction, and analysis of plant disease data using a trained Convolutional Neural Network (CNN). The system architecture is organized into three primary layers: the Presentation Layer, the Logic Layer, and the Data Layer. The Presentation Layer provides a user-friendly web interface developed in Streamlit, integrating dynamic components such as real-time prediction panels, probability bars, and comparative disease charts generated with Plotly Express. It also includes essential UI elements such as an image upload section and model output visualization to ensure smooth user interaction. The Logic Layer performs core analytical and computational tasks. It preprocesses leaf images, applies the CNN model for classification, generates confidence scores, and provides diseasespecific treatment recommendations. Pandas handles metadata processing, while session-state management ensures efficient handling of user inputs and outputs. The Data Layer consists of a structured plant disease dataset derived from sources such as PlantVillage, supplemented with augmented images to improve model robustness across lighting and environmental variations.

Published by: vikaspatanker