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

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)