Abstract

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
Illicit activities in the waste management network, such as waste laundering, misreporting, or trade of stolen waste pose serious environmental and regulatory challenges. Detecting these behaviours is challenging, because they often emerge from higher-order interactions among multiple entities, and are not continuous over time. Furthermore, these activities often manifest as triangles in the network, and the participation of individuals in these waste transfer structures is additionally suspicious. Traditional anomaly detection methods, which rely on first-order relationships or static analyses, struggle to capture these complex, temporally dynamic patterns. To address this challenge, we propose a Conditional Motif-Based Graph Convolutional Network (CM-GCN) that integrates condition-driven triangular motifs directly into the GCN message-passing mechanism. The CM–GCN learns structural embeddings that encode both local graph topology and node attributes–based connectivity to triangular motifs. To detect sudden or sporadic changes, these weekly embeddings are processed by a Long Short–Term Memory Variational Autoencoder (LSTM–VAE), which models temporal behaviour and identifies anomalies through spikes in reconstruction error. Experiments on one year of Portuguese waste transport data demonstrate that the proposed approach effectively highlights companies with known illicit behaviour. The CM–GCN–LSTM–VAE outperformed a standard GCN–LSTM–VAE that ignores motif structure. Results are comparable to, and slightly improve upon, an LSTM–VAE trained on a manually engineered triangle–based feature. This demonstrates that higher–order structural representations learned by the model provide a more informative signal, while simple pairwise relationships contribute little to the detection of complex behaviours. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

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
Cutting and packing problems have been widely studied because of their potential to improve industrial processes economically and environmentally. While many variants have been studied, some, particularly those with practical features necessary for industrial adoption, remain poorly addressed by exact methods. One such variant is the irregular packing (or nesting) problem, where pieces and/or stock materials have irregular shapes. A key industrial requirement - guillotinable cutting patterns - has rarely been studied and only with heuristic methods. This paper proposes a branch-and-cut approach based on the dotted board model to address guillotinability in irregular packing. The method iteratively identifies and eliminates non-guillotinable patterns by introducing specific cuts. These are derived using D-functions and formed by cliques in an incompatibility graph of piece placements. The approach is adapted to four variants of the problem: Irregular Strip Packing, Irregular Placement, Irregular Knapsack, and Irregular Identical Item Packing. Computational experiments were conducted using benchmark instances across the four problem variants. The method found optimal solutions for most instances. Those instances that remained unsolved or for which optimality was not confirmed indicate areas for further research. A limitation of the method is that the nesting model restricts piece placement to discrete points. Extending the model to continuous domains is a significant but promising challenge for future work. © 2026 The Authors