Authors: Kavyansh Nath

Abstract: The exponential growth of data volume and complexity in the enterprise and healthcare sectors has rendered traditional data warehousing techniques insufficient for high-performance analytics. This review article investigates the emergence of AI-assisted data warehousing as a transformative paradigm for modern data management. We evaluate the integration of machine learning across the entire data lifecycle, specifically focusing on AI-driven ETL processes for automated schema mapping and the ingestion of unstructured clinical data. The study examines advanced performance optimization techniques, including reinforcement learning for autonomous query tuning and predictive resource scaling. In the context of healthcare, we analyze how these techniques facilitate longitudinal patient records, real-time clinical decision support, and accelerated drug discovery. Furthermore, we address the critical domains of security and compliance, highlighting AI-based data masking and anomaly detection for fraud prevention. By discussing emerging trends such as self-driving warehouses and generative AI interfaces, this article provides a strategic framework for organizations seeking to implement resilient, intelligent, and high-speed analytical cores. Ultimately, we demonstrate that AI-assisted warehousing is the essential foundation for turning massive datasets into actionable strategic and clinical intelligence.

DOI: http://doi.org/10.5281/zenodo.18229082

Published by: vikaspatanker

Authors: Reyvik Taluk

Abstract: The modern healthcare landscape is defined by the critical need to optimize operational efficiency while mitigating complex financial risks. Traditional on-premise systems are increasingly inadequate for handling the high-velocity data required for real-time institutional decision-making. This review article investigates the role of Cloud-Based Decision Support Systems (CDSS) as a transformative solution for managing healthcare operations and financial stability. We examine how cloud architectures, utilizing standards like HL7 and FHIR, enable the integration of disparate data sources—from electronic health records to supply chain logs. The study explores analytical models for patient flow optimization, staffing resource management, and revenue cycle enhancement, demonstrating their impact on institutional throughput and cash flow. Furthermore, we address the significant hurdles of data privacy (HIPAA/GDPR), cybersecurity, and the ethical requirement for Explainable AI. By synthesizing current research with emerging trends like digital twins and generative AI for executive briefings, this article provides a strategic roadmap for healthcare leaders. Ultimately, we demonstrate that the synergy between cloud scalability and proactive data analytics is the essential foundation for building resilient, sustainable, and patient-centric healthcare organizations in a digitally connected age.

DOI: http://doi.org/10.5281/zenodo.18229034

Published by: vikaspatanker

Authors: Ishvik Reddy

Abstract: Traditional credit scoring methods often fail to capture the multi-dimensional complexities of modern financial risks, particularly in volatile markets and for borrowers with limited credit histories. This review article investigates the integration of Machine Learning (ML)-based credit scoring models within the SAP financial and banking ecosystem. We evaluate the transition from legacy logistic regression scorecards to advanced ensemble methods like XGBoost and Random Forests, implemented through the SAP HANA Predictive Analytics Library (PAL) and SAP Business Technology Platform (BTP). The study highlights how the "embedded" and "side-by-side" architectural patterns in SAP S/4HANA enable real-time, data-driven credit decisioning by processing transactional data at the source. Furthermore, the article addresses the critical requirement for Explainable AI (XAI) using SHAP and LIME to meet regulatory standards like Basel IV and GDPR. We explore diverse use cases, including retail loan automation, dynamic corporate credit limit management, and SME financing via alternative data. The study concludes by discussing the future impact of Generative AI and Quantum Machine Learning on credit risk reporting and simulation. By synthesizing technical implementation strategies with financial risk theory, this paper provides a strategic roadmap for banks aiming to deploy transparent, accurate, and high-performance scoring systems within their enterprise landscape.

DOI: http://doi.org/10.5281/zenodo.18229000

Published by: vikaspatanker

Authors: Aarush Naidu

Abstract: The burgeoning growth of the Internet of Things (IoT) in healthcare has created a massive influx of data that traditional cloud-based architectures struggle to process with the required speed. Latency in medical monitoring can be catastrophic, leading to delayed responses in life-critical situations such as cardiac events or falls. This exploratory study investigates fog computing as a decentralized solution for reducing latency in IoT-based healthcare systems. We evaluate a three-tier architecture that positions a fog layer between medical sensors and the cloud to enable real-time data filtering, anomaly detection, and immediate localized alerting. The article explores key latency-reduction strategies, including dynamic resource allocation and intelligent computation offloading, which prioritize emergency traffic and minimize network congestion. Furthermore, we address the critical domains of security and privacy, highlighting the use of mutual authentication and local data anonymization to protect sensitive patient records. Through various case studies, we demonstrate that fog architectures can reduce response times by up to 95% compared to cloud-only models. The study concludes by identifying open research challenges in mobility management and interoperability, providing a strategic vision for the future of low-latency, resilient healthcare infrastructures.

DOI: http://doi.org/10.5281/zenodo.18228957

Published by: vikaspatanker

Authors: Charvik Konda

Abstract: The rapid transformation of the global healthcare industry from a reactive, hospital-centric model to a proactive, continuous, and patient-centered paradigm is driven by the convergence of wearable technology, artificial intelligence, and enterprise-grade data management. This review article explores the development and implementation of smart monitoring systems that utilize AI-driven analytics integrated within the SAP ecosystem to provide high-fidelity, real-time patient care. By bridging the technical gap between medical-grade biosensors and the SAP Business Technology Platform, healthcare providers can now harness the in-memory computing power of SAP HANA to process massive streams of physiological data. The study investigates how advanced machine learning algorithms, including deep learning for predictive modeling and anomaly detection, transform raw sensor data into actionable clinical insights. These capabilities enable early detection of critical conditions such as sepsis or cardiac distress while minimizing false alerts through intelligent context-aware filtering. We examine diverse clinical applications ranging from post-operative recovery and chronic disease management to elderly care and clinical trials demonstrating significant improvements in patient outcomes and institutional resource optimization. Furthermore, the article addresses the multifaceted challenges of large-scale deployment, specifically focusing on data privacy under HIPAA and GDPR, the technical complexity of ERP integration, and the necessity of explainable AI for clinical trust. By discussing emerging trends such as edge intelligence and the integration of generative AI for enhanced patient engagement, this review provides a strategic framework for health systems. Ultimately, the synergy between wearable hardware and SAP-integrated analytics represents a cornerstone for a more accessible, personalized, and resilient digital healthcare infrastructure.

DOI: http://doi.org/10.5281/zenodo.18228874

Published by: vikaspatanker

Authors: Narasimhamurthy K N, Ashok G V, Ashwini S

Abstract: In view of this, Indoor as well as outdoor radon concentration measurement has been carried out in specific residential and schools located in Mandya, Karnataka using well known SSNTD technique. The indoor radon level is predicted in the same selected dwellings using the suitable model which is based on the mass balance equation and the results are compared with the measured values. Annual mean values of 222Rn in selected houses and schools were found to be 19.68 Bq m-3 respectively. Annual mean values in some other survey for 222Rn and 220Rn concentrations was found to be 22.4 and 24.1 Bq m-3 respectively. The total annual effective dose received by the general public due to radon and thoron is found to be 1.1 mSv y-1, which is close to the Indian average value of 1.11 mSv y-1. The doses to different organs and tissues were calculated using the ICRP model of the respiratory tract and inter comparison was discussed.

DOI: https://doi.org/10.5281/zenodo.18228616

 

Published by: vikaspatanker

Authors: Pranesh Mudiraj

Abstract: The integration of advanced machine learning models into SAP ERP systems has revolutionized the traditional landscape of financial planning and analysis by shifting organizational focus from reactive reporting to proactive forecasting. This review article evaluates the transition from manual, spreadsheet-based accounting toward automated predictive frameworks that leverage the in-memory computing power of SAP S/4HANA. We examine a diverse taxonomy of algorithms, ranging from classical time-series analysis and ensemble methods to sophisticated deep learning architectures, and their specific applications in revenue projection, cash flow management, and risk mitigation. The study details the technical synergy between the SAP Business Technology Platform and embedded analytical engines, emphasizing the importance of data preprocessing and feature engineering in a complex enterprise environment. Furthermore, we provide a comparative analysis between traditional and machine-learning-based forecasting, highlighting improvements in accuracy, cycle time, and scalability. The paper concludes by discussing emerging trends such as generative AI and real-time predictive accounting, offering a strategic roadmap for financial leaders aiming to implement data-driven decision-making processes. By synthesizing current methodologies and practical use cases, this study demonstrates how predictive analytics serves as a cornerstone for the modern intelligent enterprise.

DOI: http://doi.org/10.5281/zenodo.18221566

Published by: vikaspatanker

Authors: Nivaan Varma

Abstract: As global business environments become increasingly volatile, traditional enterprise risk management frameworks struggle to keep pace with high-velocity, interconnected disruptions. This review article investigates the integration of artificial intelligence into risk management lifecycles to enhance business resilience. We examine how machine learning, natural language processing, and predictive analytics transform the stages of risk identification, assessment, and mitigation from reactive to proactive processes. The study highlights the role of AI in critical domains such as cybersecurity, supply chain elasticity, and financial stability, while also addressing the theoretical shift toward the anticipate-absorb-recover-adapt cycle of resilience. Furthermore, the article explores the significant challenges associated with AI adoption, including model opacity, data bias, and the urgent need for explainable AI and human-in-the-loop governance. By synthesizing current research with emerging trends like generative AI and quantum-resistant modeling, we provide a strategic roadmap for organizations aiming to build antifragile systems. This study concludes that the synergy between human strategic judgment and machine intelligence is the fundamental requirement for maintaining long-term survivability in the digital age.

DOI: http://doi.org/10.5281/zenodo.18221560

Published by: vikaspatanker

Authors: Omkar Walunj, Pranav Hole, Sarthak Thigale, Sohan SandbhorD

Abstract: With the rapid advancement of Artificial Intelligence (AI), healthcare systems are shifting from reactive to proactive models capable of predicting, diagnosing, and preventing diseases. This paper presents Smarthealth, a cloud-based predictive healthcare system that utilizes machine learning algorithms to analyze patient data, anticipate potential health issues, and generate timely alerts. The system integrates AI models for disease prediction and employs Firebase for real-time synchronization and secure data storage. The objective of this work is to develop an efficient, scalable, and secure AI-driven healthcare prediction platform that assists doctors and patients in early diagnosis and informed medical decision-making.

Published by: vikaspatanker

Authors: Gayathri S, Varshameena. M

Abstract: Cloud computing has emerged as a revolutionary technology that enables on-demand access to shared computing resources such as storage, applications, and processing power through the internet. In recent years, educational institutions have increasingly adopted cloud computing to modernize teaching, learning, and administrative processes. This shift is driven by the growing demand for flexible learning environments, digital collaboration, remote accessibility, and cost-effective infrastructure management. Traditional educational systems rely heavily on physical hardware and locally installed software, which often leads to high maintenance costs, limited scalability, and restricted access to learning resources. Cloud computing overcomes these limitations by offering scalable, reliable, and affordable solutions tailored to academic needs. This paper explores the adoption of cloud computing in educational institutions, focusing on its architecture, service models, and practical applications. Cloud-based platforms such as Learning Management Systems (LMS), virtual classrooms, digital libraries, and online assessment tools have transformed the educational ecosystem by enabling anytime-anywhere learning. The study highlights key benefits of cloud adoption, including reduced operational costs, improved collaboration among students and faculty, enhanced data storage and backup capabilities, and increased institutional efficiency. Additionally, cloud computing supports innovation in education by integrating emerging technologies such as artificial intelligence, big data analytics, and smart learning environments. Despite its advantages, the adoption of cloud computing in education also presents challenges such as data security, privacy concerns, internet dependency, and vendor lock-in. This paper discusses these challenges and emphasizes the importance of implementing strong security policies, data protection mechanisms, and regulatory compliance to ensure safe and effective cloud usage. The study concludes that cloud computing plays a vital role in the digital transformation of educational institutions and has the potential to significantly improve the quality, accessibility, and sustainability of education. With proper planning and governance, cloud computing can serve as a powerful enabler for the future of education.

Published by: vikaspatanker