graph neural networks

A DUAL-BRANCH NEURAL FORECASTING ARCHITECTURE WITH SESSION BEHAVIORAL PROFILING AND ELASTIC WEIGHT CONSOLIDATION FOR ADAPTIVE CLOUD RESOURCE ALLOCATION

The AI-driven Adaptive Resource Allocation Engine (AARAE) provides proactive resource control for multi-tenant cloud environments. Reactive autoscaling systems suffer from allocation lag: scaling actions trigger only after hypervisor metrics cross predefined thresholds. AARAE extracts early-warning behavioral signature...

AI-Augmented Logic Synthesis for Edge-Deployed Swimmer Detection Systems

Vision-based swimmer and drowning detection systems, built primarily on lightweight YOLO architectures, have achieved measurable gains in accuracy while shrinking model size for resource-constrained edge hardware. However, Field-Programmable Gate Array (FPGA) accelerators hosting these models continue to rely on conven...

FedTGNN-SS: leakage-controlled evaluation of federated semi-supervised graph neural networks for gestational and other diabetes prediction (code, protocol and results)

Code, prespecified analysis protocol, leakage unit tests and run-level results accompanying the article 'Federated Semi-Supervised Graph Neural Networks for the Prediction of Gestational and Other Diabetes from Tabular Records: A Leakage-Controlled Evaluation'. No patient data are included; the datasets are available f...

Knowledge Graph-Based Approaches in Scholarly Recommender Systems: A Comprehensive Analysis

Machine Learning in Industrial Logic Gate Synthesis: Operational Capabilities and Verification Constraints

AbstractProgrammable Logic Controllers (PLCs) rely on fixed-threshold comparators that frequently trigger false emergency trips when exposed to electromagnetic interference, thermal drift, and mechanical vibrations. This paper evaluates applying machine learning to industrial logic gate synthesis, using Graph Neural Ne...

Performance and Hardware Complexity Analysis of Ripple-Carry and Carry-Lookahead Adders for Logic Synthesis Optimization

As integrated circuit fabrication approaches physical limits, classical Electronic Design Automation (EDA) algorithms struggle with high-dimensional search spaces during multi-objective Power, Performance, and Area (PPA) optimization. Binary addition circuits form the core bottleneck of arithmetic processing units; thu...

Fagnet: an adaptive frequency-guided multi-scale graph network for financial market prediction

This work rethink financial risk contagion from the perspective of frequency domain analysis in signal processing and proposes an innovative Frequency-Guided Adaptive Graph Network (FAGNet) framework, proving the effectiveness of frequency domain decoupling.

Feature Augmented SuperHyperGraph Neural Networks for Hierarchical Epidemic Modeling, Environmental Perturbations, and Source Identifiability

Abstract: Infectious disease transmission involves interactions occurring at multiple organizational levels, including individuals,households, communities, and regions. Conventional graph and hypergraph neural networks represent pairwise and higher order interactions, but they do not directly provide a recursive repres...

Sensitive-aware graph neural network for privacy leakage traceability in scan-to-order systems

Abstract Scan-to-order systems route user data through merchants, payment gateways, cloud services, and third-party analytics providers in a single transaction flow. This multi-entity architecture makes privacy leakage difficult to trace: a sensitive record may travel five or six hops before reaching an unauthorised pa...

Autonomous AI-Based Cloud Security Monitoring and Attack Prediction System Using Deep Neural Networks

Autonomous AI-Based Cloud Security Monitoring and Attack Prediction System Using Deep Neural Networks presents a comprehensive approach to modern cloud cybersecurity by combining cloud monitoring, artificial intelligence, deep learning, anomaly detection, attack classification, threat prediction, risk assessment, and a...

Artificial Intelligence for MRI-Based Identification of Autism Spectrum Disorder: A Systematic Review of Methods, Performance, and Clinical Translation

Background Autism Spectrum Disorder (ASD) is a neurodevelopmental condition characterized by impairments in social communication and restricted or repetitive behaviours. Early diagnosis is important for timely intervention, motivating increasing interest in computer-aided diagnostic systems based on neuroimaging data....

Crystal Quotient Graph and Periodic Message Passing Enhancing Material Property Prediction