federated learning

Foundations of Federated Learning

Security and Privacy‐Preserving Tiny Machine Learning

This work examines the privacy and security issues with tiny machine learning (TinyML) and proposes potential solutions to improve dependability and trust in practical applications. A thorough analysis of current security risks is conducted, including data leakage, model extraction, and adversarial assaults. Furthermor...

A Federated Agricultural Market Intelligence Framework for Distributed Price Discovery and Inflation Monitoring

Agricultural markets often experience considerable differences between the prices received by farmers and the prices paid by consumers. These disparities arise from fragmented supply chains, limited market transparency, transportation costs and the involvement of multiple intermediaries. As a result, farmers may receiv...

CAFA: Coverage-Adaptive Contribution-Aware Federated Aggregation for ECG Classification (code and reproducibility bundle)

Source code, experiment configurations, and a slim per-seed results bundle that reproduce every table and figure in the paper 'Coverage-Adaptive Contribution-Aware Federated Aggregation for ECG Classification under Heterogeneous Label Quality' (Biomedical Signal Processing and Control). CAFA is an aggregation-only fede...

Federated Fine-Tuning of Foundation Models (Fed-LLMs): Parameter-Efficient Adapters, Split Learning, and Gradient Privacy Bounds

Abstract—Fine-tuning Large Language Models (LLMs) and Vision Foundation Models on private, decentralized domain data is essential for specialized healthcare, legal, and financial enterprise applications. However, centralizing domain-specific text corpora triggers catastrophic data privacy violations under stringent reg...

THE EL-RAKHAWI COMPREHENSIVE BIOLOGICAL ARTIFICIAL INTELLIGENCE FRAMEWORK: UNIFIED MULTI-OMIC FOUNDATION MODELS FOR CAUSAL DISEASE MODELING AND PERSONALIZED THERAPEUTIC DISCOVERY

The El-Rakhawi Comprehensive Biological AI (ECB-AI) Framework revolutionizes medical research by transcending fragmented, correlational models. It introduces a Unified Multi-Omic Foundation Model mapping genomics, proteomics, and clinical data into a topologically protected Riemannian manifold. Its core innovation, the...

Blockchain–federated learning integration in the internet of vehicles: analysis, taxonomies, and future directions

Communication-efficient federated analytic class-incremental learning via orthogonal residual compensation

Study-level characteristics and quality scores of the 74 Tier-1 studies in a systematic review of federated learning for ECG-based cardiac monitoring

This deposit contains the study-level data supporting the systematic literature review “Federated Learning for ECG-Based Cardiac Monitoring: A Systematic Literature Review” (Bouayad, Ayache, Nasser), conducted following PRISMA 2020. The review covers publications from January 2020 to 7 March 2026, retrieved from IEEE X...

Supporting MSME Innovation: An Adviser’s Manual Developed for the Philippine Department of Science and Technology

This Productivity Insights publication outlines four practical AI strategies specifically crafted for small and medium-sized manufacturing enterprises: (1) predictive maintenance and AI-based visual inspection for quality control, (2) integration through digital twins and cyber-physical production systems, (3) human-in...

EduBot: Integrating Federated Learning and RAG for Educational Document Analysis

There is a growing demand for intelligent and secure document management systems in the education sector, driven by the exponential growth of digital content. Nevertheless, classic centralized machine learning methods pose major privacy challenges. In this study, we present EduBot, a decentralized intelligent framework...

Participation Bias Correction for Byzantine-Robust Federated Learning Under Heterogeneous Client Availability

Federated learning enables distributed clients to collaboratively train a global model without sharing their private data. However, Byzantine robustness becomes more challenging under heterogeneous client availability, since Byzantine clients with higher availability can participate more frequently than honest clients...