System Informatics, 25.04.2025, # 26
This paper focuses on the problems of adaptivity realization in intelligent tutoring systems, namely the adaptive courseware generation. There has been presented some intelligent tutoring systems with adaptive courseware generation that provide individualized instructional content for each student and select dynamically the optimal teaching method at every step of the learning process, as well as the methods and techniques of adaptation used in them.
E-learning, intelligent e-learning tutoring systems, adaptive learning systems, adaptive educational hypermedia systems, adaptive courseware generation, adaptive hypermedia, adaptive presentation, adaptive navigation support, concept path graphs, learning path graphs, learning activity graphs, concept maps, ontologies, Bayesian networks
This paper is devoted to the development of a prototype electrocardiogram (ECG) monitoring system based on the ESP8266 microcontroller. The system uses the AD8232 sensor to collect ECG data, which is transmitted to the server via the Wi-Fi protocol. On the server side, the data is processed using the PyTorch framework and the LSTM model for real-time analysis. The main focus is on the design of the prototype system, the details of data collection and preprocessing, and the application of the LSTM model. The results of testing the system show that it is able to effectively monitor ECG signals and detect anomalies with high accuracy and in real time.
This paper proposes new algorithms for linking scientific terms to entities in Wikipedia and MeSH (Medical Subject Headings), designed to work in low-resource settings. The algorithm for linking to Wikipedia, developed for a subset of Russian-language texts, uses the Wikipedia search engine to generate candidates and the spaCy library to obtain vector representations of the text. Semantic similarity between a Wikipedia entity description and a scientific term is calculated based not only on the term itself, but also on its surrounding context. For the medical subset of the collection, which includes Russian-to-English translations, an algorithm was developed and implemented for linking terms using the MeSH vocabulary. Experimental results show F1 scores of 50.77% for Wikipedia and 40.05% for MeSH, which are promising given the limited amount of annotated data. The study highlights the need to develop specialized Russian-language knowledge bases analogous to MeSH. A promising direction for future work is the use of multilingual models for cross-lingual linking, which is particularly important for rare terms. The results can be applied in the development of intelligent systems for scientific text analysis and automated scientific assistants, which is especially relevant for specialized domains.
This paper examines the issues of constructing a Global AI strategy, emphasizing the critical role of achieving Strong Artificial Intelligence (Strong AI or AGI) as a key world asset. The pursuit of Strong AI represents a transformative frontier in science and governance. However, its development demands a coordinated global strategy to address ethical, technical, and geopolitical challenges. The International Artificial Intelligence Committee (IAIC) has proposed a strategic plan aimed at promoting international cooperation in the development of reliable and equitable AI solutions. By integrating hybrid AI architectures, multi-agent systems, metaverse and multi-blockchain transparency we outline a framework for advancing Strong AI while mitigating risks such as catastrophic forgetting, geopolitical fragmentation, and ethical misuse. The IAIC’s phased implementation plan-from foundational research (2025) to interplanetary standards (2050)-aims to position AI as a catalyst for sustainable development, national competitiveness, and global stability.