Štefan Gubo

Lithium-ion batteries are widely used in electric vehicles, portable electronics, and grid energy systems. The constant current–constant voltage (CC–CV) method shows clear limits at high state of charge when polarization increases, temperature rises, and charging time is extended. These effects become stronger in the high SOC region, where the charging rate decreases. Consequently, to address this challenge, in this study we presents a hybrid charging method that combines physics-informed deep learning with an auxiliary hardware circuit. The circuit is placed between the charger and the battery without changes to the charger structure. It enables real-time control of pulse frequency and duty cycle. A one-dimensional convolutional neural network is applied during short relaxation periods for SOC estimation. The proposed method reduces polarization and thermal stress and improves charging efficiency at high SOC. It also improves open-circuit voltage estimation accuracy. Experimental tests are conducted on lithium-ion cells under controlled temperature conditions. The results confirm improved performance in fast charging applications.

This paper presents a short description of an automated proximal aerial image-based vine disease detection approach, developed specifically for the region of the Carpathian Basin. Particular focus is given to the description of the applied Convolutional Neural Network architecture. Several experimental results are shown comparing results obtained from data collected in different geographical regions.

The article analysed the main reflections presented by experts from different countries in the area of AI in education, who participated in the round table debate “E-Learning and Enhancing soft skills: Contemporary Models of Education in the era of Artificial Intelligence”. The agenda included three topics: 1) E-learning and enhancing soft skills: contemporary models of education in the era of artificial intelligence; 2) Good practice examples using AI in education for soft skills development; 3) AI – perspectives and challenges of its use in education. The conclusions of the round table lead to the reflection that integrating AI and robots can enhance soft skills development and revolutionize education by creating personalized, efficient, and inclusive learning environments. AI offers benefits like task automation, real-time feedback, and support for diverse needs. However, challenges such as equity, privacy, bias, and ethical concerns must be addressed. Success requires adequate teacher training, a focus on equity and accessibility, ethical considerations, strong data protection, and maintaining human interaction and creativity. By addressing these challenges thoughtfully, education systems can fully harness AI’s potential to improve learning outcomes.

In recent decades, the sedentary lifestyle has become more and more widespread, both in home life and office work. During the COVID-19 pandemic, working from home became the norm for long months in many countries around the world due to lockdowns, and though home office work can be beneficial in certain aspects, unfortunately it more often than not comes with an inactive lifestyle. The potential negative health effects of spending lengthy time periods sitting or lying down with little to no exercise (such as chronic diseases and mental health problems) has been extensively researched and documented. Numerous studies have shown that introducing breaks is important to reduce the chance of negative health effects at some degree, but when the task at hand requires focus and undivided attention, watching time for breaks can be quite difficult. Furthermore, insufficient water-intake and an unhealthy diet are also often negative side effects of a sedentary lifestyle.In this paper, a novel Intelligent Space-based application framework is proposed that aims to help users with a sedentary work-and lifestyle in improving their health: helping the user with time management (notifying them about breaks, scheduled water-intake, etc.); providing information about dietary intake and providing recommendations about introducing small, incremental changes in their diet; and finding patterns in the observed behavior of the user in order to inform them about unconscious (and potentially harmful) habits.