The proposed Explainable Graph Artificial Intelligence Framework for Financial Risk Forecasting (XGraph-FR) integrates Graph Neural Networks (GNNs) and Explainable AI (XAI) to deliver accurate and interpretable financial risk predictions. It models financial markets as a heterogeneous graph connecting companies, sectors, investors, and macroeconomic indicators through weighted relationships. Graph Attention Networks (GATs) capture dynamic dependencies using data from stock prices, financial statements, macroeconomic indicators, news, and social media sentiment. The framework employs preprocessing techniques such as normalization, missing-value imputation, graph construction, and temporal segmentation to improve data quality. Explainability is provided through attention visualization, feature attribution, graph saliency, and subgraph extraction, allowing stakeholders to understand prediction outcomes. Performance is evaluated using metrics including accuracy, precision, recall, F1-score, AUC, explainability, and computational efficiency, supporting transparent and reliable financial risk forecasting for portfolio management, fraud detection, market surveillance, and regulatory compliance.
Alexey Lyapunov· International Journal of Eme...· 0 citations
The transition from Industry 4.0 to Industry 5.0 emphasizes human-centric, sustainable, and intelligent manufacturing by integrating human expertise with advanced technologies such as Artificial Intelligence (AI), Industrial Internet of Things (IIoT), Cyber-Physical Systems (CPS), Digital Twins (DT), Edge Computing, Cloud Computing, Collaborative Robots (Cobots), and Explainable AI (XAI). This paper proposes an Intelligent Human-Centric Cyber-Physical System (HC-CPS) framework comprising six interconnected layers for real-time monitoring, predictive maintenance, adaptive production scheduling, quality optimization, and human-centered decision support. A multi-objective optimization model and AI-driven closed-loop decision-making algorithm enhance production efficiency, equipment reliability, energy utilization, product quality, and human–machine collaboration while reducing downtime and operational costs. Human operators remain actively involved through collaborative interfaces that validate or modify AI recommendations. Comparative evaluation demonstrates significant improvements over conventional Industry 4.0 systems in Overall Equipment Effectiveness (OEE), predictive maintenance, operational safety, and manufacturing flexibility, providing a scalable, resilient, and sustainable foundation for future Industry 5.0 smart factories.
Andrey Ershov, Alexey Lyapunov· International Journal of Mod...· 0 citations
The rapid advancement of artificial intelligence (AI), autonomous robotics, and distributed computing has significantly improved the capabilities of multi-robot systems (MRS) across applications such as warehouse automation, disaster response, healthcare, precision agriculture, intelligent transportation, and smart manufacturing. A key challenge in these systems is dynamic task allocation, where robots must efficiently assign and reassign tasks in response to changing environments, communication constraints, resource limitations, and robot failures. Conventional approaches often face limitations in scalability, computational efficiency, and adaptability.This paper proposes an AI-based dynamic task allocation framework that integrates machine learning, reinforcement learning, swarm intelligence, and optimization techniques to enable intelligent and adaptive decision-making in heterogeneous multi-robot systems. The framework considers robot capabilities, task priorities, battery levels, communication quality, travel distance, and workload balancing to optimize real-time task allocation. Reinforcement learning supports adaptive policy learning, while swarm intelligence enables decentralized cooperation. Graph-based task modeling and utility-based optimization further improve resource utilization and minimize execution time, energy consumption, and task conflicts.Experimental evaluation using metrics such as task completion rate, response time, energy efficiency, workload distribution, and scalability demonstrates that the proposed framework outperforms conventional scheduling methods by providing improved adaptability, fault tolerance, and operational efficiency. The proposed approach offers a scalable and intelligent solution for next-generation multi-robot collaboration in Industry 5.0 and cyber-physical systems.
Alexey Lyapunov· International Journal of Int...· 0 citations
This work forms a prior method based on Deep Deterministic Policy Gradient controller and a adaptive unscented Kalman filter which continuously providing constantly estimating robot states and improving the motion primitives in hazardous operating conditions to validate that end-to-end AI navigation architectures deliver the robust performance needed for next-gen automated industrial monitoring and non-destructive evaluation at scale.
Andrey Ershov, Alexey Lyapunov· International Journal of Int...· 0 citations
A Digital Twin-Assisted Optimization Framework for Electric Vehicle Charging Infrastructure (DTO-EVCI) that integrates IoT, cloud computing, artificial intelligence (AI), machine learning, and optimization techniques to enable real-time monitoring, predictive analytics, and intelligent charging management is proposed.
Andrey Ershov, Alexey Lyapunov· International Journal of Mod...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
