Abstract
Accurate retrieval of post-surgical images plays a critical role in surgical planning for breast cancer patients. However, current content-based image retrieval methods face challenges related to limited interpretability, poor robustness to image noise, and reduced generalization across clinical settings. To address these limitations, we propose a multistage retrieval pipeline integrating saliency-based explainability, noise-reducing image pre-processing, and ensemble learning. Evaluated on a dataset of post-operative breast cancer patient images, our approach achieves contrastive accuracy of 77.67% for Excellent/Good and 84.98% for Fair/Poor outcomes, surpassing prior studies by 8.37% and 11.80%, respectively. Explainability analysis provided essential insight by showing that feature extractors often attend to irrelevant regions, thereby motivating targeted input refinement. Ablations show that expanded bounding box inputs improve performance over original images, with gains of 0.78% and 0.65% contrastive accuracy for Excellent/Good and Fair/Poor, respectively. In contrast, the use of segmented images leads to a performance drop (1.33% and 1.65%) due to the loss of contextual cues. Furthermore, ensemble learning yielded additional gains of 0.89% and 3.60% over the best-performing single-model baselines. These findings underscore the importance of targeted input refinement and ensemble integration for robust and generalizable image retrieval systems.

Abstract
Driving safety under low-visibility or distracted conditions remains a critical challenge for intelligent transportation systems. This paper presents Edge-VisionGuard, a lightweight framework that integrates signal processing and edge artificial intelligence to enhance real-time driver monitoring and hazard detection. The system fuses multi-modal sensor data-including visual, inertial, and illumination cues-to jointly estimate driver attention and environmental visibility. A hybrid temporal-spatial feature extractor (TS-FE) is introduced, combining convolutional and B-spline reconstruction filters to improve robustness against illumination changes and sensor noise. To enable deployment on resource-constrained automotive hardware, a structured pruning and quantization pipeline is proposed. Experiments on synthetic VR-based driving scenes demonstrate that the full-precision model achieves 89.6% driver-state accuracy (F1 = 0.893) and 100% visibility accuracy, with an average inference latency of 16.5 ms. After 60% parameter reduction and short fine-tuning, the pruned model preserves 87.1% accuracy (F1 = 0.866) and <3 ms latency overhead. These results confirm that Edge-VisionGuard maintains near-baseline performance under strict computational constraints, advancing the integration of computer vision and Edge AI for next-generation safe and reliable driving assistance systems.

Abstract
Breast segmentation has a critical role for objective pre and postoperative aesthetic evaluation but challenged by limited data (privacy concerns), class imbalance, and anatomical variability. As a response to the noted obstacles, we introduce an encoderdecoder framework with a Segment Anything Model (SAM) backbone, enhanced with synthetic depth maps and a multiterm loss combining weighted crossentropy, convexity, and depth alignment constraints. Evaluated on a 120patient dataset split into 70% training, 10% validation, and 20% testing, our approach achieves a balanced test dice score of 98.75% a 4.5% improvement over prior methods with dice of 95.5% (breast) and 89.2% (nipple). Ablations show depth injection reduces noise and focuses on anatomical regions, yielding dice gains of 0.47% (body) and 1.04% (breast). Geometric alignment increases convexity by almost 3% up to 99.86%, enhancing geometric plausibility of the nipple masks. Lastly, crossdataset evaluation on CINDERELLA samples demonstrates robust generalization, with small performance gain primarily attributable to differences in annotation styles.

Abstract
The increasing reliance on Networked Microgrids (NMGs) for decentralized energy management introduces unprecedented cybersecurity risks, particularly in the context of False Data Injection Attacks (FDIA). While traditional FDIA studies have primarily focused on network-based intrusions, this work explores a novel cyber-physical attack vector leveraging Uncrewed Aerial Vehicles (UAVs) to execute sophisticated cyberattacks on microgrid operations. UAVs, equipped with communication jamming and data spoofing capabilities, can dynamically infiltrate microgrid communication networks, manipulate sensor data, and compromise power system stability. This paper presents a multi-objective optimization framework for UAV-assisted FDIA, incorporating Non-dominated Sorting Genetic Algorithm III (NSGA-III) to maximize attack duration, disruption impact, stealth, and energy efficiency. A comprehensive mathematical model is formulated to capture the intricate interplay between UAV operational constraints, cyberattack execution, and microgrid vulnerabilities. The model integrates flight path optimization, energy consumption constraints, signal interference effects, and adaptive attack strategies, ensuring that UAVs can sustain long-duration cyberattacks while minimizing detection risk. Results indicate that UAV-assisted cyberattacks can induce power imbalances of up to 15%, increase operational costs by 30%, and cause voltage deviations exceeding 0.10 p.u.. Furthermore, analysis of attack success rates vs. detection mechanisms highlights the limitations of conventional rule-based anomaly detection, reinforcing the need for adaptive AI-driven cybersecurity defenses. The findings underscore the urgent necessity for advanced intrusion detection systems, UAV tracking technologies, and resilient microgrid architectures to mitigate the risks posed by airborne cyber threats.

Abstract
Breast cancer patients often face difficulties when choosing among diverse surgeries. To aid patients, this paper proposes ACID-GAN (Anatomically and Clinically Informed Deep Generative Adversarial Network), a conditional generative model for predicting post-operative breast cancer outcomes using deep learning. Built on Pix2Pix, the model incorporates clinical metadata, such as surgery type and cancer laterality, by introducing a dedicated encoder for semantic supervision. Further improvements include colour preservation and anatomically informed losses, as well as clinical supervision via segmentation and classification modules. Experiments on a private dataset demonstrate that the model produces realistic, context-aware predictions. The results demonstrate that the model presents a meaningful trade-off between generating precise, anatomically defined results and maintaining patient-specific appearance, such as skin tone and shape.

Abstract
We study the optimal online service for grocery retailers operating both physical and online stores. The challenge lies in optimizing the size of the online assortment and the delivery fees to maximize profitability across channels, while considering customer, operational, and market dynamics. Using transaction data from a major grocery retailer, we employ an alternative-specific conditional logit model to investigate how delivery fees, assortment size, network characteristics, and customer needs influence store choice and spending across physical and online channels. We develop a profitability model that incorporates online service variables, customer behavior, and operational costs, enabling us to explore optimal strategies under various conditions. By identifying favorable conditions for the online store and analyzing optimal service variables, we provide actionable insights for retailers. Our findings challenge common practices in omnichannel retail. We show that delivery fees should not merely cover costs but can be strategically set higher, particularly for retailers with strong offline presence. Additionally, while reducing fulfillment costs improves profitability, its impact is smaller than expected. Multichannel retailers can offset these costs by passing them on to customers, with minimal overall demand loss, as some customers opt to shop in physical stores rather than abandoning the retailer entirely. Lastly, maximizing the online assortment may not always be optimal, particularly if the operational inefficiencies and costs outweigh the value customers place on variety. Our methodological framework provides retailers the opportunity to align their online services with customer preferences and operational constraints and to leverage customer data in shaping their omnichannel strategies. © 2026 The Author(s)