March 31 · Article · Bilim scientific and pedagogical jornal · Computer Vision and Pattern Recognition
To understand the role of introducing and improving the quality of education in higher education institutions using augmented reality (AR), the authors of the article tried to identify the following questions: What contribution can these technologies make to education? What are the results of research in the field of augmented reality? How do augmented reality technologies affect learning processes? In this article, we search the Scopus, Science Direct, and Web of Science databases for articles describing the use of augmented reality technologies in higher education and their impact on learning outcomes. We identified 150 articles, of which, after several stages of verification and selection, 29 articles were left at the extraction stage, from which 16 reviews and 13 empirical research articles containing a full review and presentation were extracted. The results of the research showed that 80% of the reviewed studies provide positive results in the field of STEM and physics, as there is a more improved visualization and representation of complex processes. Nevertheless, the effect of AR is poorly understood. The conducted research shows the potential for improving the quality of education through AR technology and presents opportunities for integrating them into the educational process.
DADariya AbykenovaOpen access
March 31 · Article · Informatyka Automatyka Pomiary w Gospodarce i Ochronie Środowiska · Developmental and Educational Psychology
The purpose of the article is development of a mobile application to test graphic skills and disorders of fine motor skills determination. Many techniques are used to test fine motor skills, including drawing, cutting, folding, creating compositions from various materials, and more. However, using digital devices to test fine motor skills will be automatic, useful, and helpful. Digital devices such as sensor and graphic tablets, sensors, digitizers, and smartphones can provide accurate measurements of reaction times and movement speed, and allow real-time data to be recorded and analyzed. A cross-platform tool was developed to test basic graphic skills and level of fine motor skills development. The algorithm for the determination of the graphic abilities of users is based on the Frechette discrete distance formula, which allows measuring the deviation of an experimental figure from the etalon figure. Experimental results were conducted at the laboratory of 3D biomedical technologies of the Department of Biomedical Engineering of Kharkiv National University of Radio Electronics. The application is designed to analyze graphic skills through a series of exercises that test various skills, such as drawing, shading, and coloring shapes.
OMOrken MamyrbayevOpen access
March 31 · Article · International Journal of Intelligent Information Systems · Hardware and Architecture
K-means clustering, a fundamental unsupervised machine learning technique, is widely used in anomaly detection, image recognition, and customer segmentation. Traditional Python implementations, especially those using NumPy, face performance challenges with large, high-dimensional datasets due to Python’s interpreted nature and dynamic typing. This paper introduces an innovative approach using the Mojo programming language, designed for AI development, to significantly improve the performance of the k-means clustering. Mojo combines Python’s usability with the performance of system programming languages by offering features like vectorization, parallelization, and strong typing. We compare a NumPy-based Python implementation with an optimized Mojo implementation, detailing the translation process and optimization techniques, including Mojo’s support for Single Instruction, Multiple Data (SIMD) operations, explicit memory management, and efficient data structures. These features significantly accelerate distance calculations crucial to the k-means algorithm. Benchmarks on synthetic datasets with varying sample sizes, feature counts, and cluster numbers demonstrate that the Mojo implementation consistently outperforms both the standard Python implementation and the highly optimized sci-kit-learn k-means, achieving speedups of 6x to 250x. These results highlight Mojo’s potential as a powerful tool for high-performance data analysis, particularly for computationally demanding algorithms like k-means clustering, and contribute to high-performance computing in machine learning. This research sets the stage for further exploration of Mojo’s applicability to other algorithms and hardware-specific optimizations for modern computing architectures.
MNMekhriddin NurmamatovOpen access
