Data-driven applications across healthcare, manufacturing, finance, transportation, cybersecurity, smart cities, and Industrial Internet of Things (IIoT) require intelligent predictive systems that are accurate, explainable, and capable of real-time decision-making. While conventional machine learning (ML) pipelines effectively automate tasks such as data preprocessing, feature engineering, model training, and deployment, they often lack contextual reasoning, adaptive intelligence, and explainability when handling heterogeneous and multimodal data. Recent advances in Large Language Models (LLMs) offer new opportunities to enhance ML pipelines through semantic reasoning, intelligent feature generation, automated model optimization, and explainable predictions. This research proposes a Large Language Model-Augmented Machine Learning Pipeline (LLM-MLP) that integrates data acquisition, intelligent preprocessing, semantic feature engineering, automated model selection, hyperparameter optimization, explainable AI, continuous monitoring, and feedback-driven refinement within a unified framework. By combining LLM-based reasoning with traditional ML techniques, the proposed architecture improves predictive accuracy, interpretability, scalability, and computational efficiency. The framework supports continuous learning through reinforcement-based optimization and is applicable to diverse domains, including healthcare diagnosis, predictive maintenance, financial risk assessment, cybersecurity, customer analytics, and smart infrastructure management. Overall, the proposed LLM-MLP provides an adaptive, trustworthy, and scalable predictive intelligence framework for next-generation AI-driven decision support systems.
Andrey Ershov· International Journal of Mac...· 0 citations
We focus on autonomous inspection robots operating in complex, dynamic, and GNSS-denied industrial environments dealing with critical problems related to real-time trajectory optimization, feature tracking and precise spatial localization. Remember that traditional control algorithms tend to not adapt well to difficult visual occlusions, non-Gaussian sensor noise, or unforeseen structural impediments. We propose a unified AI pipeline that fuses deep reinforcement learning with sensor data—by combining Light Detection and Ranging (LiDAR), Visual-Inertial Odometry (VIO), and thermal images—to discover flexible navigation strategies for autonomous inspection ground vehicles. In this work, we form 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. A series of experimental evaluations conducted on both simulated industrial plants and a physical mock-up facility show that the AI-based method achieves up to 51% relative reduction in localization error compared to traditional Simultaneous Localization and Mapping methods. The results show that the path deviation decrease by 38.15%, collision avoidance timeliness is significantly improved, and the accuracy of anomalies detection can reach more than 98%. These results 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
The rapid adoption of electric vehicles (EVs) has increased the need for intelligent charging infrastructure capable of addressing challenges such as charging congestion, uneven energy distribution, grid instability, and long waiting times. Conventional charging management approaches based on static scheduling are inadequate for dynamic charging environments. This paper proposes 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. The framework synchronizes physical charging stations with a virtual digital twin, enabling accurate simulation, charging demand prediction, occupancy forecasting, optimized scheduling, predictive maintenance, and adaptive energy management. By improving charging efficiency, resource utilization, grid reliability, and renewable energy integration, the proposed framework reduces operational costs, minimizes charging delays, and supports sustainable large-scale EV deployment while contributing to smart city and carbon-neutral transportation initiatives.
Andrey Ershov, Alexey Lyapunov· International Journal of Mod...· 0 citations
