There is a strong correlation between the like/dislike responses to audio–visual stimuli and the emotional arousal and valence reactions of a person. In the present work, our attention is focused on the automated detection of dislike responses based on EEG activity when music videos are used as audio–visual stimuli. Specifically, we investigate the discriminative capacity of the Logarithmic Energy (LogE), Linear Frequency Cepstral Coefficients (LFCC), Power Spectral Density (PSD) and Discrete Wavelet Transform (DWT)-based EEG features, computed with and without segmentation of the EEG signal, on the dislike detection task. We carried out a comparative evaluation with eighteen modifications of the above-mentioned EEG features that cover different frequency bands and use different energy decomposition methods and spectral resolutions. For that purpose, we made use of Naïve Bayes classifier (NB), Classification and regression trees (CART), k-Nearest Neighbors (kNN) classifier, and support vector machines (SVM) classifier with a radial basis function (RBF) kernel trained with the Sequential Minimal Optimization (SMO) method. The experimental evaluation was performed on the well-known and widely used DEAP dataset. A classification accuracy of up to 98.6% was observed for the best performing combination of pre-processing, EEG features and classifier. These results support that the automated detection of like/dislike reactions based on EEG activity is feasible in a personalized setup. This opens opportunities for the incorporation of such functionality in entertainment, healthcare and security applications.

Prolonged computer-related work can be linked to musculoskeletal disorders (MSD) in the upper limbs and improper posture. In this regard, we report on developing resources supporting improper posture studies based on motion capture sensors. These resources were used to create a baseline detector for the automated detection of improper sitting postures, which was next used to evaluate the applicability of Hjorth’s parameters—Activity, Mobility and Complexity—on the specific classification task. Specifically, based on accelerometer data, we computed Hjorth’s time-domain parameters, which we stacked as feature vectors and fed to a binary classifier (kNN, decision tree, linear SVM and Gaussian SVM). The experimental evaluation in a setup involving two different keyboard types (standard and ergonomic) validated the practical worth of the proposed sitting posture detection method, and we reported an average classification accuracy of up to 98.4%. We deem that this research contributes toward creating an automated system for improper posture monitoring for people working on a computer for prolonged periods.

The presented work provides a comprehensive evaluation of the current availability of education programs and courses related to of AI the field of Information Technologies and Computer Science in higher education institutions (HIEs) in the Republic of Bulgaria. More specifically, this study examines 163 bachelor’s and 239 master’s degree programs from 28 HEIs available during the 2023/24 academic year in four professional fields: (1) Electrical Engineering, Electronics, and Automation; (2) Communication and Computer Technologies; (3) Informatics and Computer Science; and (4) Mathematics. The conducted evaluation shows that 41.1% of evaluated BSc programs and 26.4% of MSc programs include at least one AI-dedicated course. Results indicate a significant presence of AI-focused education, particularly in degrees related to Informatics and Computer Science, where 47.8% of AI courses are concentrated. However, a notable disparity exists in the inclusion of AI subjects across other technical fields, particularly in Electrical Engineering and related degrees, which contain only 8% of the identified AI courses for BSc degree programs. The findings highlight the need for a broader and more accelerated integration of AI education to meet the evolving demands of both students and the labor market. This work underscores the importance of strategic curriculum adaptation to enhance the readiness of Bulgarian HEIs to support the development and application of AI technologies, addressing the skills gap and fostering a workforce capable of navigating the AI-driven future.

Battery-powered Internet of Things (IoT) sensor nodes for environmental monitoring face strict energy constraints, particularly when employing high-consumption sensors such as particulate matter sensors or gas analyzers. Extending operational lifetime without sacrificing measurement reliability remains a key challenge for large-scale air-quality monitoring deployments. This paper proposes a digital-twin-assisted adaptive sensing algorithm for reducing energy consumption by dynamically optimizing sensor usage for Indoor Air Quality (IAQ) monitoring system. The system consists of distributed sensing nodes and a central station that maintains digital twins to evaluate candidate sensing strategies based on historical data and environmental patterns. Strategies are assessed in terms of energy consumption and measurement fidelity and deployed only when a measurable improvement is achieved. The approach is evaluated across mobile and stationary sensor configurations used for monitoring indoor air quality in university laboratories while educational and research activities are carried out. For stationary nodes, clustering-based scheduling reduces the activation of high-power sensors, while for mobile nodes, variation-based triggering exploits correlations between equivalent and reference CO₂ measurements to limit energy-intensive sensing. Results demonstrate energy savings of up to approximately 70% while maintaining acceptable measurement fidelity. The findings show that reduced sensing can be used for system initialization, while digital twin evaluation enables reliable transition to adaptive sensing under suitable conditions.

This article analyses various approaches to teaching linear regression using Python and Excel. The inductive and deductive methods, as well as problem-based learning, are examined. Examples of using the scikit-learn library or Excel functionalities for building linear regression models are described. Practical tasks are presented to support the understanding of regression analysis concepts.