Speech emotion recognition has been gaining importance for years, but most of the existing models are based on a single signal representation or conventional convolutional layers with a large number of parameters. In this study, we propose a compact multi-representation architecture that combines four images of the speech signal: spectrogram, MFCC features, wavelet scalogram, and fuzzy transform maps. Furthermore, the application of Kronecker convolution for efficient feature extraction with an extended receptive field is shown. Another novelty is cross-fusion, a mechanism that models interactions between branches without significantly increasing complexity. The core of the network is complemented by a transformer-based block and language-independent adversarial learning. The model is evaluated in a scenario of quadruple cross-lingual tests covering four data corpora for four languages: English, German, Polish and Danish. It is trained on three languages and tested on the fourth, achieving a weighted accuracy of 96.3%. In addition, the influence of selected activation functions on the classification quality is investigated. Ablation analysis shows that removing the Kronecker convolution reduces the efficiency by 5.6%, and removing the fuzzy transform representation by 4.7%. The obtained results indicate that the combination of Kronecker convolution, multi-channel fusion, and adversarial learning is a promising direction for building universal, language-independent emotion recognition systems.

The architectural design of deep learning models significantly influences their predictive capabilities in environmental monitoring tasks. This paper investigates the individual and collective effects of residual learning and feature fusion mechanism to improve the performance of soil moisture estimation on the designed architecture of the deep learning model. In this study, the data fusion mechanism was used to integrate Normalized Difference Water Index (NDWI), Synthetic Aperture Radar (SAR), and satellite imagery datasets containing Red, Green, and Blue (RGB) color channels, which consist of images or data collected by a radar system that uses microwaves to produce images of the Earth's surface. Three model variants were developed, each selectively omitting one or more of these architectural elements, and their performance was evaluated using three standard metrics, Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Coefficient of Determination (R2). The results of the final proposed model architecture showed that while each component contributes to accuracy improvements, the combination of residual learning and feature fusion yields the most significant gains. Improved results of RMSE = 0.0117, R²=0.814 and Mean Absolute Error=0.0148 were obtained. These performance indicators were superior to the results of most of the baseline models after comparative analysis. Thus, this study provides insights into model component selection for deep learning soil moisture prediction applications.

Accurate and interpretable arrhythmia detection is essential for timely diagnosis and intervention, particularly in Medical Decision Support Systems (MDSS). Fuzzy logic, known for its ability to handle uncertainty and enhance interpretability, has emerged as a promising approach. This systematic literature review (SLR) investigates the role of fuzzy logic in advancing arrhythmia detection, focusing on accuracy, interpretability, and integration with computational intelligence. Following the PRISMA guidelines, 13 studies published between 2019 and 2024 were analysed to address four key questions: (Q1) the accuracy and reliability of fuzzy logic systems, (Q2) the effectiveness of hybrid systems combining fuzzy logic with computational intelligence, (Q3) the challenges in developing multi-class fuzzy logic systems, and (Q4) the impact of fuzzy logic on interpretability in MDSS. Techniques such as Adaptive Neural Fuzzy Inference Systems (ANFIS) and hybrid models with neural networks and bio-inspired algorithms were evaluated. ANFIS demonstrated near-perfect accuracy, while hybrid systems enhanced scalability and addressed multi-class classification challenges. Limitations included reliance on benchmark datasets, limited real-world validation, and insufficient focus on explainable artificial intelligence (XAI). Fuzzy logic shows strong potential for developing interpretable and robust MDSS for arrhythmia detection. Future research should prioritise advancing XAI, incorporating diverse datasets, and addressing real-world challenges to improve clinical applicability.

Wireless Body Area Networks (WBANs) are one of the emerging technologies in the healthcare landscape. It enables the non-invasive collection of physiological data to continuously measure health indicators using a network of miniaturized sensors placed on or under the human body. This paper explores a comprehensive study of WBANs, covering all the basic concepts, including their background information and motivation for development, as well as requirements and issues related to their application scenarios and future directions. The paper elaborates on the exclusive characteristics of WBANs compared to Wireless Sensor Networks. It describes health monitoring requirements and energy efficiency challenges with security and biocompatibility as guidelines for comparison. In addition, the paper also highlights various WBAN communication technologies and their relevance in diverse medical and non-medical domains. This paper identifies the critical comprehensive analysis of interference dynamics and mitigation strategies that remain absent in the literature, along with an exhaustive review of the literature. The research shows that WBANs could have a significant impact on healthcare and other industries, while discussing the technical and ethical hurdles to their wider application.

One of the most important goals in image segmentation is the process of separating the object parts from the image background. Image segmentation is also a fundamental stage in the development of other image applications such as object recognition, target tracking, computer vision, and biomedical image processing. Interactive image segmentation methods with additional user interaction are still popular in research. Interactive image segmentation aims to provide additional information through simple interactions, especially in images with complex objects. Interactive image segmentation with region merging processes has drawbacks, one of which is suboptimal region splitting due to soft color shades, blurred contours, and uneven lighting, referred to in this study as ambiguous regions. However, in the fuzzy region initialization stage after obtaining values from the marker process, there is a possibility of missing or suboptimal determination of fuzzy regions. This is because it only takes the highest gray level value for the background marker and the lowest gray level value for the object marker. In this study, fuzzy region merging using hierarchical clustering is proposed to find optimal initialization for fuzzy regions in image segmentation. Based on the experimental results, the proposed method can achieve optimal segmentation with an average misclassification error value of 2.62% for Natural Images and 9.33% for Dental Images.

This research investigates the enhancement of Artificial Immune Systems (AIS) for solving the Traveling Salesman Problem (TSP) through hybridization with Neighborhood Improvement (NI) and parameter fine-tuning. Two main experiments were conducted: Experiment A identified the optimal integration points for NI within AIS, revealing that position 2 (AIS+NIpos2) improved solution quality by an average of 27.78% compared to other positions. Experiment B benchmarked AIS performance with various enhancement techniques. Using symmetric and asymmetric TSP datasets, the results showed that integrating NI at strategic points and fine-tuning parameters boosted AIS performance by up to 46.27% in some cases. The hybrid and fine-tuned version of AIS (AIS-th) consistently provided the best solution quality, with up to a 50.36% improvement, though it required more computational time. These findings emphasize the importance of strategic combinations and fine-tuning for creating effective optimization algorithms.

This systematic literature review examines the role of ChatGPT in communication. ChatGPT's ability to imitate human-like interactions has broad implications in various sectors, such as education, healthcare, and customer service in the digital-based economy. The authors used a systematic and structured manuscript selection method in this research to collect and analyze literature on the use of ChatGPT in a communication context. A systematic literature review (SLR) method was used, involving an extensive search through the Scopus and Google Scholar databases with the keywords "ChatGPT" and "communication." Manuscript selection required strict inclusion and exclusion criteria. Of the 623 articles found, 30 were selected for further review. The research results show that using ChatGPT in communication has had both positive and negative impacts. Positive impacts involve increasing the efficiency and effectiveness of communications, especially in education, marketing, ethics, and health. However, challenges such as ethical considerations, the risk of plagiarism, and a limited understanding of context and emotional interactions were also identified. The use of ChatGPT in education, health, and various other fields has demonstrated great potential to improve communication processes, decision-making, and work efficiency. However, to ensure responsible and sustainable use, we must address specific ethical challenges and risks. This study provides a comprehensive overview of recent developments in using ChatGPT in communications, while also highlighting the practical and ethical implications that must be considered. With careful consideration of the advantages and limitations, ChatGPT in communications can significantly contribute to various fields.

Employing vision-based hand gesture recognition for the interaction and communication of disabled individuals is highly beneficial. The hands and gestures of this category of people have a distinctive aspect, requiring the adaptation of a deep learning vision-based system with a dedicated dataset for each individual. To achieve this objective, the paper presents a novel approach for training gesture classification using few-shot samples. More specifically, the gesture classifiers are fine-tuned segments of a pre-trained deep network. The global framework consists of two modules. The first one is a base feature learner and a hand detector trained with normal people hand’s images; this module results in a hand detector ad hoc model. The second module is a learner sub-classifier; it is the leverage of the convolution layers of the hand detector feature extractor. It builds a shallow CNN trained with few-shot samples for gesture classification. The proposed approach enables the reuse of segments of a pre-trained feature extractor to build a new sub-classification model. The results obtained by varying the size of the training dataset have demonstrated the efficiency of our method compared to the ones of the literature.

The article presents the so-called coin bag problem, which is modeled by linear Diophantine equations. The problem in question involves assessing the contents of a set of coins based on its weight. Since this type of problem is undecidable, a special variant of the problem was proposed for which effective problem-solving algorithms can be developed. In this paper, an original heuristic is presented (an algorithm based on problem decomposition) which allows to solve the coin bag problem in fewer steps compared to a brute force algorithm. The proposed approach was verified in a series of computational experiments. Additionally, an authentication scheme making use of the approach was proposed as an example of potential practical use.

One of the concepts of human-computer interaction is the usability of websites, consisting of features such as efficiency, satisfaction, memorability, and learnability. Usability is particularly important in the case of websites that the user is expected to learn on their own. The main aim of this study is to evaluate the usability of user interfaces of websites and, based on this, to find how this evaluation is affected by the application of universal design principles. The objects of the study are two websites, one complying with the principles of universal design - created for the purpose of the study, and the other – an existing commercial website operating in the market, which does not follow these principles. Three hypotheses are defined: 1) effectiveness and efficiency of analyzed websites are higher for a service that followed the principles of universal design than a website that did not comply with these rules; 2) the quality of the user interface is greater for the service fulfilling the principles of universal design; 3) the satisfaction with the interaction with the interface is greater in case of websites conformed to the principles of universal design. The study uses two methods: eye tracking and questionnaires. The experiment involves 10 participants who had to perform a scenario consisting of 10 instructions that involved locating various elements in each of the tested GUI interfaces. The eye activity is recorded using a Gazepoint GP3 HD desktop eye tracker, which makes it possible to determine the effectiveness and efficiency values of using the analyzed interfaces. Each participant was also asked to fill out two questionnaires: the Lublin University of Technology one and the Questionnaire for User Interaction Satisfaction. The study proves the truth of the hypotheses, that is, the positive impact of universal design on the usability evaluation of user interfaces.