Healthcare institutions and health registries often store patients’ health data. In order to ensure privacy, sensitive medical information is stored separately from the identifying information of the patient. Generally, institutions anonymize medical information while sharing it for external use. However, internal users may also use it for identifying inaccuracies or missing information. Even though internal users may be legally permitted to access sensitive medical information, such access may lead to the identification of the patient, which can be vulnerable to patient privacy. Ensuring the accountability and responsibility of the internal users may lead to tractability in case of adversarial access with malicious intentions. Therefore, a secure system must be developed for the storage and retrieval of health data. To this end, in this paper, we propose a ledger-based system that cryptographically ensures that all access to health data must be logged into a ledger. Nevertheless, the ledger entries must be protected against adversarial access, too. At the same time, the ledger must be traversable by the patients as well as internal users. To address these needs, we propose techniques for the construction of a ledger to permit both internal users and patients to securely traverse and view only the entries to which they are linked.

In modern digital infrastructure, cyber systems are foundational, making resilience against sophisticated attacks essential. Traditional cybersecurity defenses primarily address technical vulnerabilities; however, the human element, particularly decision-making during cyber attacks, adds complexities that current behavioral studies fail to capture adequately. Existing approaches, including theoretical models, game theory, and simulators, rely on retrospective data and static scenarios. These methods often miss the real-time, context-specific nature of user responses during cyber threats. To address these limitations, this work introduces a framework that combines Extended Reality (XR) and Generative Artificial Intelligence (Gen-AI) within a gamified platform. This framework enables continuous, high-fidelity data collection on user behavior in dynamic attack scenarios. It includes three core modules: the Player Behavior Module (PBM), Gamification Module (GM), and Simulation Module (SM). Together, these modules create an immersive, responsive environment for studying user interactions. A case study in a simulated critical infrastructure environment demonstrates the framework’s effectiveness in capturing realistic user behaviors under cyber attack, with potential applications for improving response strategies and resilience across critical sectors. This work lays the foundation for adaptive cybersecurity training and user-centered development across critical infrastructure.

Automatic speech recognition (ASR) and natural language processing (NLP) play key roles in advancing human–technology interactions, particularly in healthcare communications. This study aims to enhance French-language online mental health platforms through the adaptation of the QuartzNet 15 × 5 ASR model, selected for its robust performance across a variety of French accents as demonstrated on the Mozilla Common Voice dataset. The adaptation process involved tailoring the ASR model to accommodate various French dialects and idiomatic expressions, and integrating it with an NLP system to refine user interactions. The adapted QuartzNet 15 × 5 model achieved a baseline word error rate (WER) of 14%, and the accompanying NLP system displayed weighted averages of 64.24% in precision, 63.64% in recall, and an F1-score of 62.75%. Notably, critical functionalities such as ‘Prendre Rdv’ (schedule appointment) achieved precision, recall, and F1-scores above 90%. These improvements substantially enhance the functionality and management of user interactions on French-language digital therapy platforms, indicating that continuous adaptation and enhancement of these technologies are beneficial for improving digital mental health interventions, with a focus on linguistic accuracy and user satisfaction.

Humans often cross their legs unconsciously while sitting, which can lead to health problems such as shifts in the center of gravity, lower back pain, reduced blood circulation, and pelvic distortion. Detecting unconscious leg crossing is important for promoting correct posture. In this study, we investigated the detection of leg-crossing postures using machine learning algorithms applied to data from body pressure distribution sensors. Pressure data were collected over 180 s from four male subjects (25.8 ± 6.29 years old) under three conditions: no leg crossing, right-leg crossing, and left-leg crossing. Seven classifiers, including support vector machine (SVM), random forest (RF), and k-nearest neighbors (k-NN), were evaluated based on accuracy, recall, precision, and specificity. Among the tested methods, k-NN demonstrated the highest classification performance, suggesting it may be the most effective approach for identifying leg-crossing postures in this study.

This paper explores the problem of the security of unmanned aerial vehicles (UAV) by introducing the drone security scoring system (D3S). D3S is a security assessment method that analyzes the security of a UAV model by analyzing its components. Penetration tests were carried out to support D3S and identify potential vulnerabilities in UAVs. Specific cyber-attacks, such as deauthentication, flooding, and replay, were executed in an effort to take full control of the UAVs. Eight different UAV models were assessed using D3S, revealing notable variations in performance, both in control communications and video transmission. Security scores ranging from 0.9 to 4.5 out of 5 were obtained, showing significantly divergent security levels.

The transition of cities towards a smarter approach significantly benefits from citizen participation in the development and implementation of innovative information and communication technology (ICT) products and services. Despite the emergence of various initiatives in recent years aimed at guiding the development of smart cities, there is still a lack of effective strategies to actively engage citizens, businesses, and educational institutions during the creation of these products and services. This study describes a set of practices that includes four co-creation techniques to facilitate the effort of software system development in collaboration with citizens and other stakeholders. The SEMAT standard is used to create and represent a method in which these practices are distributed across four stages: focus, definition, development, and validation. In each stage, a practice is proposed that incorporates a co-creation technique and complementary activities from various software engineering disciplines to promote active citizen participation; stimulate idea generation; and facilitate the creation of necessary documents and components for the development of the desired software system, including design systems, code files, conceptual representations, and technical diagrams, among others. Finally, the applicability and completeness of the method are validated through expert consultation in the fields of software engineering and smart cities. Recognized procedures are followed to obtain qualitative and quantitative results, such as improvement actions (addition or removal of elements), levels of consensus or acceptance, and opportunities for future work.

In tasks such as wood defect repair and the production of high-end wooden furniture, ensuring the consistency of the texture in repaired or jointed areas is crucial. This paper proposes the WTSM-SiameseNet model for wood-texture-similarity matching and introduces several improvements to address the issues present in traditional methods. First, to address the issue that fixed receptive fields cannot adapt to textures of different sizes, a multi-receptive field fusion feature extraction network was designed. This allows the model to autonomously select the optimal receptive field, enhancing its flexibility and accuracy when handling wood textures at different scales. Secondly, the interdependencies between layers in traditional serial attention mechanisms limit performance. To address this, a concurrent attention mechanism was designed, which reduces interlayer interference by using a dual-stream parallel structure that enhances the ability to capture features. Furthermore, to overcome the issues of existing feature fusion methods that disrupt spatial structure and lack interpretability, this study proposes a feature fusion method based on feature correlation. This approach not only preserves the spatial structure of texture features but also improves the interpretability and stability of the fused features and the model. Finally, by introducing depthwise separable convolutions, the issue of a large number of model parameters is addressed, significantly improving training efficiency while maintaining model performance. Experiments were conducted using a wood texture similarity dataset consisting of 7588 image pairs. The results show that WTSM-SiameseNet achieved an accuracy of 96.67% on the test set, representing a 12.91% improvement in accuracy and a 14.21% improvement in precision compared to the pre-improved SiameseNet. Compared to CS-SiameseNet, accuracy increased by 2.86%, and precision improved by 6.58%.

Mathematical models are designed to assist decision-making processes across various scientific fields. These models typically contain numerous parameters, the values’ estimation of which often comes under analysis when evaluating the strength of these models as management tools. Advanced artificial intelligence software has proven to be highly effective in estimating these parameters. In this research work, we use the Lotka–Volterra model to describe the dynamics of a telecommunication sector in Greece, and then we propose a methodology that employs a feed-forward neural network (NN). The NN is used to estimate the parameter’s values of the Lotka–Volterra system, which are later applied to solve the system using a fourth-algebraic-order Runge–Kutta method. The application of the proposed architecture to the specific case study reveals that the model fits well to the experiential data. Furthermore, the results of our method surpassed the other three methods used for comparison, demonstrating its higher accuracy and effectiveness. The implementation of the proposed feed-forward neural network and the fourth-algebraic-order Runge–Kutta method was accomplished using MATLAB.

The functional nature of cognitive systems is outlined as a general conceptual model where typical notions of cognition are analyzed apart from the physical realization (biological or artificial) of such systems. The notion of function, one of the main logical bases of mathematics, logic, linguistics, physics, and computer science, is shown to be a unifying concept in analyzing cognition components: learning, meaning, comprehension, language, knowledge, and consciousness are related to increasing levels in the functional organization of cognition.

Convolutional Neural Networks (CNNs) are the prevalent technology in computer vision and have become increasingly popular for medical imaging data classification and analysis. In this field, due to the scarcity of medical data, pretrained ResNets on ImageNet can be considered a suitable first approach. This paper examines the medical imaging classification accuracy of conventional basic custom CNNs compared to ImageNet pretrained ResNets on various medical datasets in an effort to give more information about the importance of medical data and its preprocessing techniques for disease studies. Microscope-extracted cytological images were examined along with chest X-rays, MRI brain scans, and melanoma photographs. The medical images were examined in various sets, class combinations, and resolutions. Augmented image datasets and asymmetrical training and validation splits among the classes were also examined. Models were developed after they were tested and fine-tuned with respect to their network size, parameter values and network methods, image resolution, size of dataset, multitude, and genre of class. Overfitting was also examined, and comparative studies regarding the computational cost of different models were performed. The models achieved high accuracy in image classification that varies depending on the dataset and can be easily incorporated in future over-the-internet medical decision-supporting (telemedicine) environments. In addition, it appeared that conventional basic custom CNN overperformed ImageNet pretrained ResNets. The obtained results indicate the importance of utilizing medical image data as a testbed for improvements in CNN classification performance and the possibility of using CNNs and data preprocessing techniques for disease studies.