International Journal of Mobile and Cloud Systems Engineering (e-ISSN: 3108-3315)

Deep Learning-based Early Prediction of Heart Disease using Clinical Healthcare Data

2026-08-10T11:44:02+00:00

Cardiovascular Diseases (CVD) are the number one cause of death globally and are responsible for a significant proportion of all global deaths annually, and are particularly prevalent in LMICs where diagnostic resources are scarce. Accurate and early prediction of heart disease risk from routinely collected clinical information can enable early intervention, minimize diagnostic delay, and reduce long-term treatment. This article presents a hybrid deep learning model that processes one-dimensional Convolutional Neural Networks (CNNs) for local feature extraction, a Long Short-Term Memory (LSTM) network for temporal and sequential modeling of the longitudinal clinical measurements, and a fully connected classification head with an attention mechanism to attend to clinically salient features. The model is trained and tested using a combined dataset consisting of the Cleveland, Hungarian, Switzerland, and Long Beach VA subsets of the UCI Heart Disease repository, along with the Framingham and Z-Alizadeh Sani datasets to enhance the model's generalizability. The missing values are handled using multiple imputation; the Synthetic Minority Oversampling Technique (SMOTE) is used to combat class imbalance, and z-score normalization is applied to scale the features. Experimental results are then shown, which includes an accuracy of 94.6%, sensitivity of 93.8%, specificity of 95.1%, F1-score of 94.2% and an Area Under the Receiver Operating Characteristic Curve (AUC-ROC) of 0.978, outperforming the deep learning baselines (plain CNN, plain LSTM, deep neural network) and classical machine learning models (logistic regression, random forest, support vector machine, XGBoost) when tested under the same conditions. Using SHAP (SHapley Additive exPlanations) model interpretation, the most influential parameters are chest pain type, maximum heart rate achieved, number of major vessels colored by fluoroscopy, and thalassemia status, in accordance with known clinical knowledge. The outcomes indicate that the proposed framework can be a promising decision support tool in primary care and resource-constrained environments, and that it is interpretable and computationally efficient.

A Survey of Emerging Technologies in Cloud Enterprise Resource Planning: The Oracle Fusion Cloud ERP Ecosystem

2026-08-17T05:49:31+00:00

Enterprise Resource Planning (ERP) systems have evolved from monolithic, on-premises transaction engines into cloud-native, intelligent platforms that fuse artificial intelligence, distributed ledgers, the Internet of Things (IoT), and elastic edge-to-cloud infrastructure. Oracle Fusion Cloud ERP has emerged as a leading exemplar of this transformation, embedding machine learning, generative and agentic artificial intelligence, and pervasive analytics directly within core financial and operational workflows. This article presents a structured survey of the emerging technologies reshaping the Oracle ERP ecosystem and situates them within the broader research landscape of intelligent enterprise systems. The survey traces the architectural evolution from Oracle E-Business Suite to Fusion Cloud ERP; examines the cloud and edge computing foundations provided by Oracle Cloud Infrastructure and the Oracle Autonomous Database; analyzes embedded, generative, and agentic AI capabilities, including the AI Agent Studio and a suite of finance-oriented agents; and reviews the integration of IoT and sensor networks, blockchain-based track-and-trace, data science and soft-computing techniques, and cybersecurity mechanisms. Recurring design patterns and open research challenges are synthesized across trust, explainability, data governance, latency-sensitive edge processing, and the security of autonomous enterprise agents. The result is a technology map intended to serve both practitioners planning cloud ERP modernization and researchers seeking an application-grounded view of one of the most consequential domains for AI, IoT, blockchain, and secure distributed computing.

Decentralized Cephalopod-Inspired Intelligence: The 9-Brain Edge Architecture with Linearly Reversible Graph Topologies, Multi-Jurisdictional Data Sovereignty, and Federated CPU Economics

2026-09-11T09:32:11+00:00

The centralized deployment of monolithic large language models (LLMs) at the network edge introduces irreconcilable tensions between inference latency, bandwidth economics, and multi-jurisdictional data governance. Raw continuous sensor streams transmitted to cloud clusters impose round-trip latencies of 500 to 1,500 ms, upstream bandwidth demands approaching 2,400 KB/s per deployment cluster, and unacceptable multi-jurisdictional compliance exposure under the General Data Protection Regulation (GDPR), Health Insurance Portability and Accountability Act (HIPAA), China’s Personal Information Protection Law (PIPL), and Brazil’s Lei Geral de Proteção de Dados (LGPD). This paper introduces the Cephalopod Decentralized Architecture (CDA), an edge-first computational paradigm directly modelled on the nine-brain nervous system of Octopus vulgaris: one central AWS S3 (as an example) Single Source of Truth (SSOT) brain and eight geo-regional peripheral sub-brain edge nodes. Each sub-brain is implemented on parallelized commodity multi-core CPUs running 1–3 billion parameter models under 8-bit and 4-bit quantisation, equipped with a local Redis in-memory cache for microsecond-latency state management and transactional saga rollback. A formal Linearly Reversible Graph Topology (LRGT) replaces cyclic state graph orchestration, eliminating recursive re-entry hazards and enabling localized failure recovery without global re-planning. Empirical evaluation conducted on a synthetically generated multi-region testbed demonstrates that CDA reduces mean edge reflex latency to 13.8 ms (97.8% reduction), upstream bandwidth to 11.3 KB/s (99.5% reduction), and token consumption by 98.4%, while achieving a 99.8% fault recovery rate and full structural compliance with all applicable data residency mandates. Federated CPU infrastructure reduces estimated monthly operational expenditure by approximately 75% compared to equivalent GPU cluster deployments. These findings establish a biologically grounded, legally defensible, and economically optimised paradigm for next-generation distributed edge AI.

Edge Computing Security for Real-Time Online Musical Performances

2026-09-17T09:45:57+00:00

The work investigates the role of secure edge computing architectures in enhancing real-time online musical performances and collaborative Networked Music Performance (NMP) systems. The emergence of edge computing has significantly transformed digital musical interactions by enabling ultra-low-latency communication, distributed audio processing, and immersive collaborative experiences. Traditional cloud-based infrastructures often fail to satisfy the stringent latency, synchronization, and reliability requirements necessary for high-quality online musical performances. To address these limitations, edge computing relocates computational and networking resources closer to performers and audiences, thereby minimizing transmission delays and improving real-time responsiveness. Despite these advantages, the decentralized and distributed nature of edge infrastructures introduces substantial cybersecurity challenges, including Distributed Denial-of-Service (DDoS) attacks, packet interception, unauthorized access, data leakage, synchronization manipulation, and malicious traffic injection. These threats can severely disrupt timing-sensitive musical interactions and degrade user experience in Internet of Musical Things (IoMusT) ecosystems. This research proposes a hybrid edge-cloud security framework that integrates lightweight encryption mechanisms, AI-based anomaly detection, blockchain-assisted authentication, and Software-Defined Networking (SDN) for secure orchestration and traffic management. The framework is designed to maintain low latency while simultaneously strengthening security, scalability, and reliability in distributed musical collaboration environments. Experimental simulations and performance evaluations demonstrate that the proposed secure edge framework reduces average latency by 38%, packet loss by 29%, and cyber-attack vulnerability by 46% compared to conventional cloud-centric architectures. The results indicate that integrating security-aware edge intelligence significantly improves synchronization stability, communication efficiency, and overall Quality of Experience (QoE) for performers and audiences. The findings further emphasize the importance of secure edge computing as a foundational technology for future IoMusT ecosystems, immersive virtual concerts, metaverse-based performances, and geographically distributed music collaboration platforms.

Edge–Cloud Intelligence for Scalable AI Applications: A Review of Model Deployment, Resource Orchestration, Privacy, and Energy Efficiency

2026-11-03T10:18:28+00:00

AI workloads increasingly span devices, gateways, edge servers, and centralized clouds, coupling model placement with transfer time, compute energy, prediction quality, cost, and security boundaries. This structured critical review synthesizes 54 selected studies across deployment placement, model compression, orchestration, federated privacy, industrial monitoring, and environmental accounting. It provides explicit inclusion criteria and replicable database search strings, as well as an audited, non-exclusive thematic map of the cited bibliography; an exhaustive database search and PRISMA-ScR screening flow were not performed. Source-specific evidence includes handheld inference latencies, reported compression and energy gains, a mobile–cloud layer-partitioning study, and an industrial compressor deployment. To connect these results, the study formulated a constrained route- and model-selection problem accounting for shared model memory, split inference, tail-latency deadlines, energy, and trust boundaries. A formal (epsilon, delta)-differential privacy definition and threat-model matrix distinguish verifiable safeguards from locality-based assumptions. The study concludes that end-to-end evaluation under matched workloads is necessary before claiming device-, edge-, or cloud-tier superiority. The review provides an analytical evaluation framework, not a newly validated system or complete systematic evidence census.