Abstract
Deep learning techniques have demonstrated significant potential in computer-assisted diagnosis based on medical imaging. However, their integration into clinical workflows remains limited, largely due to concerns about interpretability. To address this challenge, we propose Efficient-Proto-Caps, a lightweight and inherently interpretable model that combines capsule networks with prototype learning for lung nodule characterization. Additionally, an innovative Davies-Bouldin Index with multiple centroids per cluster is employed as a loss function to promote clustering of lung nodule visual attribute representations. When evaluated on the LIDC-IDRI dataset, the most widely recognized benchmark for lung cancer prediction, our model achieved an overall accuracy of 89.7 % in predicting lung nodule malignancy and associated visual attributes. This performance is statistically comparable to that of the baseline model, while utilizing a backbone with only approximately 2 % of the parameters of the baseline model’s backbone. State-of-the-art models achieved better performance in lung nodule malignancy prediction; however, our approach relies on multiclass malignancy predictions and provides a decision rationale aligned with globally accepted clinical guidelines. These results underscore the potential of our approach, as the integration of lightweight and less complex designs into accurate and inherently interpretable models represents a significant advancement toward more transparent and clinically viable computer-assisted diagnostic systems. Furthermore, these findings highlight the model’s potential for broader applicability, extending beyond medicine to other domains where final classifications are grounded in concept-based or example-based attributes. © 2013 IEEE.

Abstract
Medical image captioning is an essential tool to produce descriptive text reports of medical images. One of the central problems of medical image captioning is their poor domain description generation because large pre-trained language models are primarily trained in non-medical text domains with different semantics of medical text. To overcome this limitation, we explore improvements in contrastive learning for X-ray images complemented with soft prompt engineering for medical image captioning and conditional text decoding for caption generation. The main objective is to develop a softprompt model to improve the accuracy and clinical relevance of the automatically generated captions while guaranteeing their complete linguistic accuracy without corrupting the models’ performance. Experiments on the MIMIC-CXR and ROCO datasets showed that the inclusion of tailored soft-prompts improved accuracy and efficiency, while ensuring a more cohesive medical context for captions, aiding medical diagnosis and encouraging more accurate reporting. © 2025 Elsevier B.V., All rights reserved.

Abstract
Ensuring the security of Industrial Control Systems (ICS) is increasingly critical due to increasing connectivity and cyber threats. Traditional security measures often fail to detect evolving attacks, necessitating more effective solutions. This paper evaluates machine learning (ML) methods for ICS cybersecurity, using the ICS-Flow dataset and Optuna for hyperparameter tuning. The selected models, namely Random Forest (RF), AdaBoost, XGBoost, Deep Neural Networks, Artificial Neural Networks, ExtraTrees (ET), and Logistic Regression, are assessed using macro-averaged F1-score to handle class imbalance. Experimental results demonstrate that ensemble-based methods (RF, XGBoost, and ET) offer the highest overall detection performance, particularly in identifying commonly occurring attack types. However, minority classes, such as IP-Scan, remain difficult to detect accurately, indicating that hyperparameter tuning alone is insufficient to fully deal with imbalanced ICS data. These findings highlight the importance of complementary measures, such as focused feature selection, to enhance classification capabilities and protect industrial networks against a wider array of threats. © 2025 Elsevier B.V., All rights reserved.

Abstract
In online three-dimensional packing problems where items are received one by one and require immediate packing decisions without prior knowledge of upcoming items, considering the static stability constraint is crucial for safely packing each arriving item in real time. Unstable loading patterns can result in risks of potential damage to items, containers, and operators during loading/unloading operations. Nevertheless, static stability constraints have often been neglected or oversimplified in existing online heuristic methods in the literature, undermining the practical implementation of these methods in real-world scenarios. In this study, we analyze how different static stability constraints affect solutions' efficiency and cargo stability, aiming to provide valuable insights and develop heuristic algorithms for real-world online problems, thus increasing the applicability of this research field. To this end, we embedded four distinct static stability constraints in online heuristics, including full-base support, partial-base support, center-of-gravity polygon support, and novel partial-base polygon support. Evaluating the impact of these constraints on the efficiency of a wide range of heuristic methods on real instances showed that regarding the number of used bins, heuristics with polygon- based stabilities have superior performance against those under full-base and partial-base support stabilities. The static mechanical equilibriumapproach offers a necessary and sufficient condition for the cargo static stability, and we employed it as a benchmark in our study to assess the quality of the four studied stability constraints. Knowing the number of stable items under each of these constraints provides valuable managerial insight for decision-making in real-world online packing scenarios.

Abstract
With the huge amount of data that has been collected over time, many methods are being developed to allow better understanding and forecasting in several domains. Time series analysis is a powerful tool to achieve this goal. Despite being a well-established area, there are some gaps, and new methods are emerging to overcome these limitations, such as visibility graphs. Visibility graphs allow the analyses of times series as complex networks and make possible the use of more advanced techniques from another well-established area, network science. In this paper, we present two new efficient approaches for computing natural visibility graphs from times series, one for online scenarios in.O(n log n) and the other for offline scenarios in.O(nm), the latter taking advantage of the number of different values in the time series (m).

Abstract
Modulation instability (MI) of the continuous wave (cw) has been associated with the onset of stable solitons in conservative and dissipative systems. The cubic complex Ginzburg-Landau equation (CGLE) is a prototype of a damped, driven, nonlinear, and dispersive system. The inclusion of nonlinear gradients is essential to stabilize pulses whether stationary or oscillatory. The soliton solutions of this model have been reasonably studied; however, its cw solution characteristics and stability have not been reported yet. Here, we obtain the cw solutions of the cubic CGLE with nonlinear gradient terms and study its short- and long-term evolution under the effect of small perturbations. We have found that, for each admissible amplitude, there are two branches of cw solutions, and all of them are unstable. Then, through direct integration of the evolution equation, we study the evolution of those cw solutions, observing the emergence of plain and oscillatory solitons. Depending on whether the cw and/or its perturbation are sinusoidal, we can obtain a train of a finite number of pulses or bound states.