The rapid adoption of electric vehicles (EVs) has intensified the demand for intelligent, scalable, and interoperable charging infrastructure. Traditional EV charging networks based on the Open Charge Point Protocol (OCPP) face challenges related to dynamic load management, cybersecurity, and efficient integration with renewable energy sources. This paper presents a novel AI-driven framework that integrates federated learning, predictive analytics, and real-time control within OCPP-compliant networks to enhance performance and sustainability. The proposed system utilizes edge AI modules at charging stations, supported by a central aggregator that employs federated learning to preserve data privacy while enabling network-wide optimization. A case study involving simulated smart charging stations demonstrates significant improvements, including an 18% reduction in peak load demand, a 29% increase in forecasting accuracy (MAPE of 8.5%), a 10% decrease in average charging wait times, and a 12% increase in on-site solar energy utilization. The framework’s compatibility with OCPP and related standards (e.g., IEC 61851, ISO 15118) ensures ease of deployment on existing infrastructure. These results indicate that the proposed AI-OCPP integration provides a scalable and intelligent foundation for next-generation EV charging networks that align with the goals of sustainable transportation and smart grid evolution.
Background: Progesterone receptor (PR) status plays an important role in guiding hormone therapy decisions in breast cancer. In current practice, PR expression is assessed manually from immunohistochemistry (IHC) slides, which can be time-consuming and may vary between pathologists. This study aims to develop an automated and interpretable framework for PR-IHC analysis to improve consistency and efficiency. Methods: In this work, we developed an AI-assisted pipeline that combines nuclei segmentation, classification, and scoring for PR-IHC images. A fine-tuned Cellpose model was used to segment individual nuclei. The segmented nuclei were then analyzed using a DAB intensity-based approach to classify them into four categories: negative, weak, moderate, and strong. These results were further combined to generate Allred scores. The system was evaluated on 250 PR-IHC images with annotations provided by expert pathologists. Results: The framework achieved strong segmentation performance (F1-score = 0.85, IoU = 0.74) and high classification accuracy (macro F1-score = 0.95). The method also performed well when applied to ER-IHC images without additional retraining. Conclusions: The proposed framework provides a reliable and interpretable approach for automated PR-IHC scoring. It helps reduce manual effort, improves consistency in evaluation, and shows potential for practical use in digital pathology settings.
Background: Accurate differentiation of kidney diseases such as cysts, tumors, stones, and normal tissue from computed tomography (CT) images remains challenging due to overlapping visual characteristics and variability in data distributions. While deep learning approaches have shown promising results, many existing studies rely on image-level data splitting and focus primarily on accuracy, which may lead to overly optimistic performance and limited clinical reliability. Methods: This study proposes KDH-Net (Kidney Disease Hybrid Network), a hybrid deep learning framework for multiclass kidney disease characterization that integrates EfficientNetB0, ResNet50, and MobileNetV2 through feature-level fusion. A two-stage training strategy is adopted to enhance optimization stability. To ensure realistic performance assessment, experiments on the primary dataset are conducted under a patient-level evaluation protocol, eliminating potential data leakage. The framework further incorporates calibration analysis, statistical validation, and explainable artificial intelligence to evaluate prediction reliability and interpretability. Results: On the patient-level dataset, KDH-Net achieves an overall accuracy of 0.93 with a macro-average F1-score of 0.91, demonstrating balanced performance across all classes. Confidence analysis indicates meaningful alignment between prediction confidence and correctness, while Grad-CAM visualizations highlight anatomically relevant regions associated with each class. Conclusions: The results demonstrate that KDH-Net provides a stable, reliable, and interpretable framework for kidney CT characterization. The proposed system is designed to support clinical decision-making by offering trustworthy predictions under realistic evaluation conditions, rather than replacing clinical expertise.
The Travelling Salesman Problem (TSP) asks for the shortest tour that visits each city once and returns to the start. It is a classic NP-hard problem and a benchmark for optimization, logistics, and network design. This paper surveys classical, quantum, and hybrid algorithms for the TSP using clear, step-by-step explanations. We summarize how each method works, what it guarantees, and how it scales with the number of cities. We also discuss practical limits of current quantum hardware and outline open problems and promising research directions. While quantum techniques can speed up certain subroutines or offer strong heuristics, no known method solves general TSP in polynomial time. Our goal is to offer a readable yet rigorous map of the landscape for students and practitioners.
The PR-IHC-40X dataset comprises a high-resolution collection of region-of-interest (ROI) images and corresponding ground-truth (GT) annotations for progesterone receptor (PR) immunohistochemistry (IHC) analysis in breast cancer pathology. We obtained 50 glass slides from the University of Malaya Medical Centre (UMMC) and digitized them into whole-slide images (WSIs) at 40× magnification using a 3DHistech Pannoramic DESK scanner. Pathologists annotated ROIs on the collaborative Cytomine platform, which formed the basis of dataset extraction. Ground-truth masks were generated in a multi-stage process: binary nuclei masks for segmentation were first created with a StarDist deep learning model and refined by manual correction, while the classification ground truth was first determined using a CNN-based approach and then modified by diaminobenzidine (DAB) intensity thresholding into four expression classes: Strong (red), Moderate (yellow), Weak (green), and Negative (blue). The classification outputs were re-corrected in a loop against the pathologists’ feedback and the manually checked results. There were approximately 32,000 nuclei within 250 ROI images that were manually checked and validated by senior pathologists individually. Each ROI comes with its binary segmentation mask and four-class color annotations, which make it a reliable dataset for deep learning research on nuclei segmentation, PR expression classification, and Allred scoring. To ensure a fair and reproducible evaluation, the dataset is released with a predefined slide-level (patient-wise) partition into training, testing, and evaluation subsets so that no slide contributes regions of interest to more than one subset and data leakage across subsets is avoided.
A central question in hybrid quantum–classical learning is whether variational quantum circuits (VQCs) preserve task-relevant information more efficiently than classical nonlinearities of equal output dimension. We study this question for drug–target interaction prediction in Alzheimer’s disease drug-repurposing workflows using a Hybrid Quantum–Classical Graph Neural Network (HQGNN). The model compresses 512-dimensional GNN embeddings into a four-qubit VQC (128\(\times \) compression) before a classical prediction head. On the DAVIS kinase benchmark, HQGNN achieves concordance index (CI) \(=0.527\) and root mean squared error (RMSE) \(=0.850\), outperforming a dimension-matched classical bottleneck baseline (CI \(=0.500\); random ranking). Under the same compression, the quantum layer recovers 51% of the ranking signal lost by compression relative to the full classical model and yields a 5.4% relative CI gain over the classical bottleneck. This effect is obtained with 24 trainable quantum parameters (representational yield \(\Delta \)CI/parameter \(\approx 1.13\times 10^{-3}\)). Under depolarizing noise, RMSE degradation remains below 3.3% at realistic noisy intermediate-scale quantum (NISQ) levels (\(p \le 0.01\)). Because the present benchmark is evaluated on a single transductive split, these results are interpreted as controlled proof-of-concept evidence of representational efficiency rather than definitive deployment-level generalization.