Nowadays, with the rapid evolution of information technologies, new teaching and learning methods and tools develop in the educational system. Virtual laboratories are one of those new tools that are now being increasingly used for teaching various disciplines in institutes and universities. In this paper, we outline the advantages of virtual laboratories over traditional ones and present a survey of existing solutions in the field of virtual laboratory development. Moreover, a virtual physical laboratory is described that was developed by authors of this paper taking into account both requirements imposed by the educational system of Kazakhstan and shortcomings of presently-available solutions.

The article is devoted to application of information technologies in e-Learning; usage of infocommunication technologies in higher education for implementation of e-Learning training technology. A brief review of international experience in the field of virtual laboratories is provided. The virtual computer laboratory on physics with 3D elements of computer modeling and its benefits in learning process are provided. Features of configuration and representation of theoretical and experimental materials in the virtual computer laboratory are presented.

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder characterized by cognitive and motor decline. Early detection remains challenging, as traditional neuroimaging and neuropsychological assessments often fail to capture subtle, preclinical changes. Recent advances in digital health and artificial intelligence (AI) offer new opportunities to identify non-invasive biomarkers of cognitive impairment. In this study, we propose an AI-driven framework for early AD based on handwriting motion data captured using a sensor-integrated Smart Pen. The system employs an inertial measurement unit (MPU-9250) to record fine-grained kinematic and dynamic signals during handwriting and drawing tasks. Multiple machine learning (ML) algorithms—Logistic Regression, Support Vector Machine (SVM), Random Forest (RF), and k-Nearest Neighbors (kNN)—and deep learning (DL) architectures, including one-dimensional Convolutional Neural Networks (1D-CNN), Long Short-Term Memory (LSTM), and a hybrid CNN-BiLSTM network, were systematically evaluated. To address data scarcity, we implemented a Sim-to-Real Domain Adaptation strategy, augmenting the training set with physics-based synthetic samples. Results show that classical ML models achieved moderate diagnostic performance (AUC: 0.62–0.76), while the proposed hybrid DL model demonstrated superior predictive capability (accuracy: 0.91, AUC: 0.96). These findings underscore the potential of motion-based digital biomarkers for the automated, non-invasive detection of AD. The proposed framework represents a cost-effective and clinically scalable informatics solution for digital cognitive assessment.