Abstract
Video Capsule Endoscopy (VCE) is a pivotal technology in modern gastroenterology, offering a non-invasive method to visualize the entire small bowel. However, the clinical application of VCE is hampered by the extensive review time required, as specialists must manually analyze thousands of images from each procedure. This process is not only laborious and costly but also prone to diagnostic errors due to fatigue, subtle abnormalities, and variability in interpretation across clinicians. To address this challenge, deep learning methods have been explored to automate VCE image analysis. However, most existing approaches rely on a single model architecture, which often fails to generalize across the broad visual diversity found in gastrointestinal imagery. This limitation becomes especially pronounced in multiclass classification tasks, where the ability to distinguish between visually similar tissues and lesions is essential. Ensemble-based methods such as Mixture of Experts (MoE) have shown promising results in general computer vision by leveraging multiple specialized models for improved robustness. However, no prior work has investigated MoE or Hierarchical MoE (HMoE) architectures for multiclass classification of VCE or endoscopic images more broadly. To explore this opportunity, we present a comparative framework evaluating three deep learning strategies for VCE image classification: individual models, flat MoE systems, and Hierarchical MoE architectures. Using a subset of the Kvasir-Capsule dataset, which contains 12 gastrointestinal tissue and lesion classes, we first train and evaluate four backbone models (InceptionNeXt, EfficientViT, ConvNeXtV2, and DeiT3) to establish a performance baseline. The two best-performing architectures, ConvNeXtV2 and DeiT3, are then used as expert backbones within both MoE and HMoE systems. In the MoE configuration, a gating network assigns dynamic per-image weights to multiple expert instances. In contrast, the HMoE configuration constructs a learned binary tree that routes samples based on class similarity through increasingly specialized branches. In the HMoE models, ConvNeXtV2 outperformed DeiT3 in accuracy, whereas DeiT3 showed superior routing accuracy. These results indicate that expert-driven ensemble methods not only outperform standalone models but also offer complementary advantages depending on architecture and routing strategy. This study provides new evidence for the clinical potential of MoE and HMoE frameworks in scalable, accurate VCE image analysis.

Abstract
This article presents a real-time object detection and distance estimation system implemented on a low-cost platform. The system uses a Raspberry Pi 5 and two cameras in a stereoscopic configuration to capture pairs of images. Object detection is performed using YOLO neural networks and distance estimation is based on the disparity between the centers of the detected bounding boxes. The system is evaluated in terms of detection performance, inference speed and depth estimation accuracy. Three YOLO models (YOLOv8n, YOLO11n and YOLO12n) are tested at different resolutions. Among them, the YOLO11n with a resolution of 320x320 achieves the best balance between processing speed and detection quality in stereo-scopic operation. The system has a low error in depth estimation at close range, with absolute errors of less than 1.2 cm up to 60 cm. At greater distances, accuracy is affected by the reduction in the size of the bounding box, which limits the reliability of the disparity. Possible improvements include using segmentation-based localization and optimizing the stereo configuration. The proposed system is suitable for short-range applications in controlled environments and serves as a basis for future improvements in embedded vision systems.

Abstract
Background: One of the most common consequences in individuals with diabetes is the diabetic foot, which can cause foot ulcers and even lead to limb amputation. Since an increase of the temperature in the plantar region is directly correlated with an increased risk of ulceration, infrared thermography (IRT) has been used in multiple studies as an automatic tool for detecting problems in diabetic foot. Artificial intelligence-based computer-aided diagnosis systems are being more frequently used to improve decision-making and minimize errors. These technologies are designed to increase examination accuracy, consistency in image interpretation, prognosis evaluation support, and examination accuracy. They also have the ability to offer insightful information and help medical professionals to manage diabetic foot issues successfully.Methods: In this work, 37 papers that used thermography and artificial intelligence (AI) to identify diabetic foot complications and/or predict the risk of developing diabetic foot are analyzed.Results: The results demonstrate the potential of IRT imaging implementation with AI for the identification and prediction of diabetic foot complications.Conclusions: The combination of IRT and AI shows significant potential for diabetic foot assessment; however, the great majority of these studies show that the research is confined to classification of foot thermograms using pre-prepared data sets. In particular, there is limited research on segmentation methods and constraints in the use of deep learning due to the lack of large and diverse datasets.

Abstract
Background. Sample size estimation in Structural Equation Modeling (SEM) remains a debated methodological issue. Although minimum sample size rules are widely used, they often lack integration of theoretical, statistical, and practical considerations, particularly in complex research designs. Objectives. This study aims to provide a synthesis and comparative analysis of different approaches to sample size estimation in SEM, integrating theoretical foundations, statistical criteria, methodological limitations, and applied research contexts. Materials and Methods. A multi-method approach was employed, consisting of three components: a narrative review of sample size estimation methods, consideration of simulated scenarios reflecting realistic research conditions, and a comparative evaluation of method performance across these scenarios. Results. Findings show that rule-of-thumb approaches are useful for preliminary estimates but may misrepresent required sample sizes in complex models. Power analysis provides more precise and rigorous estimates, particularly for confirmatory research. Monte Carlo simulations offer robust guidance for complex, longitudinal, and multigroup models. Estimator-based recommendations highlight the importance of aligning sample size with data characteristics and estimation techniques. Model complexity emerged as a key determinant, with advanced SEM models often requiring 400–700+ participants. Conclusions. A systematic and context-sensitive approach to sample size estimation is essential for ensuring robustness and methodological rigor in SEM studies across disciplines such as management and education.

Abstract
As collaborative robots increasingly redefine industrial automation, understanding the factors that drive their adoption is essential to operations management. This study examines the main drivers of collaborative robot adoption in the Brazilian manufacturing sector by combining theory-driven framing with a machine learning classification approach. It was developed a Random Forest classifier to identify the strongest predictors of cobot adoption and to rank their relative importance. Data were collected from a sample of respondents-primarily managers and chief executive officers-representing 300 industrial companies. Grounded in the Technology-Organization-Environment (TOE) framework and complemented by Diffusion of Innovations (DoI) and Institutional (INT) perspectives, the analysis shows that technological advantages, namely space efficiency, cost reduction, and ease of integration, are critical drivers of adoption. Organizational factors, including proactive managerial involvement and alignment with an innovation-oriented culture, significantly increase the likelihood of collaborative robot uptake. The model demonstrated robust predictive performance and produced interpretable variable importance scores that confirm the relative influence of technological and managerial factors. These findings provide a structured lens for understanding and guiding managerial decision-making on cobot adoption and translate into practical recommendations for managers.

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.