Category Archives: Uncategorized

Authors: Ummi Yusuf Adam, Habibu Yusuf Adamu

Abstract: The COVID-19 pandemic led to disruptions in global supply chains, exposing vulnerabilities in organizations that were not adequately prepared for digital operations. This study investigates how digital transformation in supply chain management has influenced the business performance of manufacturing companies in the Democratic Republic of Congo amid the pandemic. Utilizing organizational information processing theory and the dynamic capabilities perspective, a conceptual framework was created to connect the digital environment, digital capabilities, digital supply chain transformation, and business performance. Data were collected through a structured survey of 233 senior logistics managers and the model was tested using partial least squares structural equation modeling (PLS-SEM). Measurement validation confirmed reliability and discriminant validity of the constructs. The results reveal that both digital environment (β = 0.271, p = 0.005) and digital capabilities (β = 0.304, p = 0.003) significantly drive digital supply chain transformation, which in turn exerts a strong positive effect on business performance (β = 0.597, p < 0.001). Mediation analysis further shows that digital supply chain transformation significantly mediates the effects of digital environment on business performance. These findings emphasize the importance of developing robust internal digital capabilities alongside an enabling external digital environment to enhance supply-chain agility in turbulent contexts.

DOI: https://doi.org/10.5281/zenodo.19910152

Published by: vikaspatanker

Authors: Aniket Garg

Abstract: The rapid growth of the Indian digital payments ecosystem which is controlled mainly by the Unified Payments Interface (UPI) has improved financial inclusion whilst alleviating transaction friction. Meanwhile, the magnitude, speed, and functionality of UPI have increased vulnerability to phishing, impersonation, scams, and synthetic identities, mule accounts, and AI-enforced social engineering. The paper under consideration investigates the UPI fraud proliferation in India through the qualitative analysis of official circulars, payment data, cybersecurity reports, and the latest regulatory interventions. It has been shown in the analysis that user confusion, ineffective verification conduct, quick payment rails that cannot be reversed, and more advanced threat agents are the proximal factors influencing the rise in fraud. A multi-level framework of prevention that incorporates beneficiary authentication, concatenation of devices, behavioural danger rating, mule-account recognition, consumer knowledge, and amplified inter-institutional reports is proposed. The paper concludes that future achievements in minimizing fraud through the integration of scale-induced innovation with security-by-design and timely redress framework will be dependent on it. [1], [3], [4], [5].

DOI: https://doi.org/10.5281/zenodo.19910031

Published by: vikaspatanker

Authors: Keshav Mittal, Jobanpreet Singh, Kartik Kumar, Jasnoor Kaur

Abstract: The field of Artificial Intelligence (AI) has been launched at a rapid pace in many areas including health, finance, administration, and law. Despite the efficacy and automation of AI technologies that remain unexamined, such technologies are accompanied by grave ethical and legal concerns such as algorithmic prejudice, misinformation, abuse of deepfakes, and cybersecurity concerns. These concerns have brought about the realization that there exists a great need in structured governance instruments and mechanisms that regulate AI practices and require prudent application. The other recent concept of the field is AI bylaws that can be described as operational guidelines and regulations of governance to regulate the development of AI systems, their implementation, and their interactions with users. The discussed research paper examines the concept of AI bylaws and addresses the problem of ethical compliance of AI systems with reference to the experimental data consisting of ethically sensitive prompts, related to discrimination, cybercrime, deepfake abuse, and harmful behavior.. The experiment measures the responses of AI and compares them against pre-established measures of ethical compliance. The findings show that AI systems tend to reject dangerous instructions and follow security protocols, but the discrepancies in the detail of the explanation and context-specific logic can be observed. Judging by these results, the present paper suggests a system of AI bylaws that is based on transparency, accountability, fairness, and prevention of misuse. The study indicates that the evaluation through experimentation would be useful in determining what is weak in the current AI governance methods and direct the creation of stronger ethical principles of AI systems.

DOI: https://doi.org/10.5281/zenodo.19909649

Published by: vikaspatanker

Authors: Devang Sethi, Dr. Rajat Takkar

Abstract: Microservices architecture has gained significant attention as a dominant paradigm for building scalable and cloud- native applications by decomposing monolithic systems into independently deployable services with decentralized data ownership. However, this architectural approach introduces challenges related to distributed data management and system reliability. This paper presents a systematic literature review examining data consistency and fault tolerance mechanisms in microservices environments. The study analyzes research published between 2016 and 2026 collected from major academic databases including IEEE Xplore, ACM Digital Library, SpringerLink, ScienceDirect, Google Scholar, and arXiv. The findings indicate that strict consistency models often limit system scalability and availability, leading many architectures to adopt eventual consistency and BASE principles. Saga-based transaction management patterns are increasingly preferred over traditional Two-Phase Commit protocols due to improved resilience, although they introduce additional implementation complexity. The review also highlights the lack of standardized evaluation frameworks for benchmarking distributed resilience strategies. Overall, the study emphasizes the importance of balancing consistency, scalability, and fault tolerance when designing reliable microservices-based systems.

DOI: https://doi.org/10.5281/zenodo.19909639

Published by: vikaspatanker

Authors: Arghadeep Nath, Rajat Takkar

Abstract: Early-stage hiring processes continue to depend on resume-based and keyword-based filtering, which does not reliably capture a candidate’s actual abilities. This paper presents an AI-assisted skill evaluation system that prioritizes demonstrated performance over resume content. The system models candidate screening as a multi-stage pipeline: skill profiling, dynamic assessment delivery, automated rule-based and NLP evaluation, and weighted score aggregation. A competency model maps candidate skills to standardized assessment criteria, enabling objective cross-candidate comparison. Evaluation on simulated data (n=100) yields a Spearman rank correlation of 0.91, a false-positive shortlist rate of 12%, and a top-quintile precision of 78% — all substantially better than a conventional ATS baseline. The proposed framework is scalable, modular, and designed to reduce bias inherent in resume-centric screening.

Published by: vikaspatanker

Authors: Rishi Raghav Singh, Rohan Singh, Rajat Takkar

Abstract: More than 30% of worldwide deaths involve diseases caused by cardiovascular and lifestyle factors (WHO, 2023) As awareness of early risk identification advances, accessible practical screening tools for use in primary care continue to be either very expensive, reliant on specialists or both. In this paper, we propose a Multi-Modal AI-Based Health Intelligence Framework with an explicit focus on two interrelated concepts encapsulated in the form of two specialized individual modules: Disease Risk Assessment (DRA) module and Lifestyle Analysis (LSA) module. After systematic preprocessing and class-balancing, the DRA module trains LR, SVM, and RF on the Cleveland Heart Disease dataset (303 patients). The LSA module takes user-reported behavioral behaviors — BMI, physical activity, sleep, dietary quality, and stress — to calculate a composite Lifestyle Risk Index (LRI). Both modules are provided through a Streamlit web application that provides real time predictions with SHAP-based explanation. Amongst all the classifiers we evaluated, Random Forest performed best with a 91.8% accuracy, AUC-ROC = 0.956 It powers a sub 60 ms response time for the system and is deployable in the cloud.

Published by: vikaspatanker

Authors: Kasarla Vanitha, B.Archana

Abstract: Cloud computing has transformed the IT landscape by providing scalable, flexible, and cost-effective services. However, its multi-tenant infrastructure introduces significant security and privacy challenges due to shared resources and virtualized environments. This paper examines established security and privacy frameworks, threat models, and protective architectures designed to address these concerns. Through a comparative analysis of existing literature and technical frameworks, the study identifies key vulnerabilities and effective mitigation strategies in multi-tenant cloud environments. Additionally, graphical models and charts are included to demonstrate how shared resource access and virtualization can be secured using encryption, tenant isolation, and dynamic authentication mechanisms.

DOI: https://doi.org/10.5281/zenodo.19909008

Published by: vikaspatanker

Authors: Wasim Riyajoddin Kazi, Om Vitthal Devakate, Vishal Popatrao Jagadale, Kavita Shinde

Abstract: In recent years, the issues related to public safety and security have increased significantly, which resulted in a surge of demand for automated surveillance systems. However, traditional monitoring systems based on CCTV require constant human surveillance, which is not only wasteful but also error- prone. This paper proposes a deep learning-based surveillance system that can automatically detect suspicious activities in videos. The proposed model utilizes CNNs to classify video frames into normal and suspicious categories. Upon detection of suspicious activity, the system captures the frame and sends an automated email notification to the registered system administrator using the SMTP protocol. The proposed system utilizes OpenCV for video processing, TensorFlow/Keras for training and predicting the models, and SQLite to securely store administrator information within a database.

Published by: vikaspatanker

Authors: Prudvi Saisaran Ponduru

Abstract: Recent advances in foundation models, multimodal learning, reasoning-oriented large language models, agentic workflows, and edge AI have expanded the capabilities of artificial intelligence systems. However, practical decision-making remains brittle because many systems optimize prediction quality while under-modeling intervention effects, uncertainty, safety constraints, latency budgets, and human accountability. This paper introduces AEGIS-DM, an adaptive, edge-aware, governed, interventional, and safe decision-making framework designed for AI systems deployed across emerging technology settings including agentic assistants, cyber-physical systems, healthcare decision support, and enterprise automation. The framework combines five layers: multimodal state representation, predictive scoring, causal effect estimation, simulator- or planner-based long-horizon optimization, and a governance layer for calibration, fairness, policy checks, logging, and human override. We further propose a cross-domain evaluation protocol using public resources such as Adult, D4RL, WebShop, ALFWorld, MIMIC-IV Demo, NASA CMAPSS, and M5, together with open-source tooling including OpenAI Evals, Responsible AI Toolbox, OpenSpiel, RecSim NG, Stable-Baselines3, and RLlib. Because this manuscript is a methods-and-benchmark contribution, the quantitative section reports deterministic scenario-based simulation results under the stated protocol rather than production deployment measurements. Under the reference protocol, the proposed hybrid approach is expected to outperform rule-based, supervised-only, offline-RL-only, and prompt-only agent baselines in composite decision quality and robustness while maintaining substantially better latency and cost than cloud-only frontier-model pipelines.

DOI: https://doi.org/10.5281/zenodo.19968793

Published by: vikaspatanker

Authors: Rajat Srivastava, Mr. Ankit Singh, Sneha Mehrotra, Shaifali Singh, Shreyansh Srivastav

Abstract: There’s a lot more to student performance than just marks. Some kids barely pass written exams but shine in group projects or sports. The problem is, most colleges still judge students almost entirely by their test scores. That’s like judging a fish by its ability to climb a tree. By the time a teacher realizes someone’s struggling, that student might already be failing or even thinking of dropping out. So what if we could spot trouble earlier — way before the report card says it all? That’s what this paper is about. We used machine learning to sift through student data — attendance, past grades, even family background — and predict who might fall behind. Not just for the sake of prediction, but to actually give teachers a heads-up so they can step in and help. The results were pretty solid. Our model caught most at-risk students with over 90% accuracy. Not perfect, but a lot better than waiting till the end of the semester.

Published by: vikaspatanker