Volume 4, Issue 12 - 3 Articles
This issue presents three studies that address reliability, integration, and trust in modern digital and physical systems. The first paper proposes a vendor-agnostic integration framework for multi-cloud enterprise environments, enabling secure and resilient workflows across major cloud platforms while reducing cost and technical debt. The second provides an experimental analysis of metal oxide surge arresters under severe short-circuit conditions, offering real-world validation of their safety and performance in power systems. The third evaluates machine learning calibration methods in clinical prediction, showing how improved probability estimates can strengthen decision-making in healthcare. Together, these contributions emphasize transparency, validation, and practical resilience across complex infrastructures.
Front Cover
Journal of Engineering Research and Sciences, Volume 4, Issue 12, Page # i–i, 2025
Editorial Board
Journal of Engineering Research and Sciences, Volume 4, Issue 12, Page # ii–vi, 2025
Editorial
by Jinhua Xiao
Journal of Engineering Research and Sciences, Volume 4, Issue 12, Page # vii–viii, 2025
Table of Contents
Journal of Engineering Research and Sciences, Volume 4, Issue 12, Page # ix–ix, 2025
A Vendor-Agnostic Multi-Cloud Integration Framework Using Boomi and SAP BTP
by Padmanabhan Venkiteela
Journal of Engineering Research and Sciences, Volume 4, Issue 12, Page # 1-14, 2025; DOI: 10.55708/js0412001
Abstract: The shift toward multi-cloud strategies has made a vendor-agnostic integration framework indispensable for seamlessly orchestrating workflows across heterogeneous platforms. Modern enterprises increasingly rely on a mix of cloud ecosystems leveraging Amazon Web Services (AWS) for elasticity, Google Cloud Platform (GCP) for advanced AI/ML capabilities, Azure Cloud and Oracle Cloud Infrastructure (OCI) for critical enterprise workloads… Read More
(This article belongs to the Section Information Systems – Computer Science (ISC))
Experimental Study of the Short-Circuit Current Performance of \(10\,\mathrm{kA_{R.M.S}}\) and \(20\,\mathrm{kA_{R.M.S}}\) Polymer Surge Arrester
by Cristian-Eugeniu Sălceanu, Daniela Iovan and Daniel-Constantin Ocoleanu
Journal of Engineering Research and Sciences, Volume 4, Issue 12, Page # 15-24, 2025; DOI: 10.55708/js0412002
Abstract: To study the behavior of metal oxide surge arresters at short-circuit current, this paper presents an experimental study on four pieces of 36 kV, \(10\,\mathrm{kA_{R.M.S}}\) and \(20\,\mathrm{kA_{R.M.S}}\) surge arresters at different values of short-circuit current. Prior to the experiments, each surge arrester was electrically pre-faulted with a power frequency overvoltage without any physical modification. The tests… Read More
(This article belongs to the Special Issue on SP7 (Special Issue on Multidisciplinary Sciences and Advanced Technology (SI-MSAT 2025)) and the Section Electrical Engineering (ELE))
Model Uncertainty Quantification: A Post Hoc Calibration Approach for Heart Disease Prediction
by Peter Adebayo Odesola, Adewale Alex Adegoke and Idris Babalola
Journal of Engineering Research and Sciences, Volume 4, Issue 12, Page # 25-54, 2025; DOI: 10.55708/js0412003
Abstract: We investigated whether post-hoc calibration improves the trustworthiness of heart-disease risk predictions beyond discrimination metrics. Using a Kaggle heart-disease dataset (n = 1,025), we created a stratified 70/30 train-test split and evaluated six classifiers, Logistic Regression, Support Vector Machine, k-Nearest Neighbors, Naive Bayes, Random Forest, and XGBoost. Discrimination was quantified by stratified 5-fold cross-validation with… Read More
(This article belongs to the Section Artificial Intelligence – Computer Science (AIC))