Battery management systems (BMSs) are evolving from threshold-based supervisory units and isolated predictive modules toward intelligent, closed-loop decision architectures capable of diagnosis, prognosis, optimization, and autonomous control. This review examines how agentic artificial intelligence extends conventional AI-enabled BMS research by integrating state awareness, risk-informed reasoning, goal-driven planning, and safety-constrained action across cell-, pack-, and system-level operations. Rather than merely cataloguing prior studies, the review compares major groups of works spanning data-driven state estimation, degradation modeling, reinforcement learning-based control, hybrid physics-informed methods, digital twins, and emerging multi-agent strategies, highlighting their respective strengths, operational assumptions, scalability limits, interpretability, and deployment readiness. The analysis shows that prediction-oriented approaches remain dominant, while comparatively fewer studies achieve robust closed-loop autonomy under uncertainty, aging, thermal coupling, and heterogeneous usage conditions. To address this gap, the paper proposes the Agentic Battery Management Stack (A-BMS), a six-layer framework linking multimodal sensing, health inference, predictive risk assessment, decision intelligence, autonomous control execution, and human oversight. The review concludes by identifying key barriers and research priorities for trustworthy, adaptive, and certifiable autonomous battery management.
The increasing complexity of digital image manipulation has rendered content authentication a significant issue in multimedia forensics. To enhance detection systems, it is essential to go beyond just semantic-level clues and also identify subtle, low-level inconsistencies that can help distinguish between authentic and altered content. Traditional methods that combine manually designed features with CNN-based or hybrid models often lack the necessary flexibility or granularity. Convolutional neural networks focus on fundamental semantics, frequently overlooking sophisticated indicators of forgery, whereas manually crafted approaches require an understanding of manipulation styles, which limits their scalability. This study tackles this limitation by introducing an innovative multi-perspective detection framework that separates the image analysis process into three complementary visual pathways. The initial module examines high-frequency components, where manipulation artefacts are frequently observed. The second focuses on non-semantic cues, such as residuals and noise patterns, whereas the third investigates spatial context to enhance overall comprehension. Every branch utilizes ResNet18 for feature enhancement, supplemented by global-axis connections to achieve thorough representation learning. Furthermore, we implement edge supervision through a Sobel-based edge extraction module to improve the precision of boundary detection and manipulation localization. The proposed method attains an F1 score of up to 98.26
The rapid adoption of the Industrial Internet of Things (IIoT) in smart manufacturing and critical infrastructure has significantly increased the exposure of industrial networks to sophisticated cyber threats. Ensuring secure communication and reliable threat detection in IIoT environments has therefore become a critical challenge. This study proposes an intelligent Cyber Threat Detection and Response System that integrates a Hybrid Deep Neural Network with the Grey Wolf Optimizer to enhance security in IIoT networks. The proposed framework utilizes CyberTec IIoT Malware Dataset (CIMD‑2024) on Kaggle containing network traffic characteristics, device communication patterns, and anomaly indicators. A comprehensive data preprocessing phase is employed, including noise removal, normalization, and missing value handling, to improve data quality and model reliability. The hybrid deep learning architecture combines Convolutional Neural Networks for spatial feature extraction with Long Short-Term Memory networks to capture temporal dependencies in network behavior. Additionally, a dual-attention mechanism is incorporated to emphasize significant spatial and temporal features, thereby improving the accuracy of cyber threat classification. The Grey Wolf Optimizer is applied to optimize key hyperparameters such as learning rate, dropout rate, and batch size, leading to improved model performance. Experimental results demonstrate that the proposed model achieves an accuracy of 96.5
Chronic kidney disease (CKD) is a progressive medical condition with significant public health impact, where early detection is critical for effective intervention. This work presents a clearly defined and structured data-driven framework designed to improve CKD prediction through robust preprocessing and optimized ensemble learning. This study proposes a novel hybrid framework that combines Random Forest (RF)-based imputation for missing value handling, categorical feature encoding, and synthetic minority oversampling technique (SMOTE) for addressing class imbalance, integrated with a Grey wolf optimizer (GWO)-based weighted ensemble of top-performing classifiers (Decision Tree, Logistic Regression, and Gaussian Naïve Bayes). The ensemble weights are optimized using the Grey Wolf optimizer (GWO) to enhance predictive accuracy. We evaluate the proposed framework on the UCI CKD dataset, demonstrating that it outperforms individual classifiers and conventional ensemble methods, achieving an accuracy of 98.75%, precision of 98.8%, recall of 98.6%, and F1-score of 98.7%. Additionally, explainable AI (XAI) techniques including SHAP and LIME are employed to analyze feature contributions, providing interpretable insights and confirming the clinical relevance of the predictions. Overall, the proposed framework offers a transparent, reliable, and computationally efficient clinical decision support model that bridges the gap between data-driven AI and nephrology practice.
Respiratory infections such as pneumonia and tuberculosis remain the leading contributors to global morbidity and mortality, and early diagnosis is essential for effective treatment. Chest X-ray imaging is widely used for the detection of these conditions; however, reliable interpretation requires accurate delineation of lung fields. Manual annotation is time-consuming and prone to variability, underscoring the need for automated segmentation methods. In this study, we conducted a systematic evaluation of state-of-the-art deep learning architectures for binary lung segmentation, including U-Net, Attention U-Net, Double U-Net, U2-Net, VGG-UNet, UNet++, ResNet-UNet, Dense-UNet, Swin U-Net and HieraSeg Net. The performance of the model was compared using the dice coefficient, the intersection of the union (IoU), the mean absolute error (MAE), the Hausdorff distance and the average symmetric surface distance (ASSD). Among these models, Dense-UNet achieved the best results, yielding a Dice score of 0.9848 and an IoU of 0.9700, with the lowest surface error measures. These findings highlight the potential of Dense-UNet to serve as a robust backbone for AI-assisted diagnostic systems in infectious respiratory diseases, thereby supporting faster, more reliable, and scalable approaches to clinical decision-making.
