Today, various interactive tools or partially available artificial intelligence applications are actively used in educational processes to solve multiple problems for resource-rich languages, such as English, Spanish, French, etc. Unfortunately, the situation is different and more complex for low-resource languages, like Kazakh, Uzbek, Mongolian, and others, due to the lack of qualitative and accessible resources, morphological complexity, and the semantics of agglutinative languages. This article presents research on early childhood learning resources for the low-resource Kazakh language. Generally, a dictionary for children differs from classical educational dictionaries. The difference between dictionaries for children and adults lies in their purpose and methods of presenting information. A themed dictionary will make learning and remembering new words easier for children because they will be presented in a specific context. This article discusses developing an approach to creating a thematic children’s dictionary of the low-resource Kazakh language using artificial intelligence. The proposed approach is based on several important stages: the initial formation of a list of English words with the use of ChatGPT; identification of their semantic weights; generation of phrases and sentences with the use of the list of semantically related words; translation of obtained phrases and sentences from English to Kazakh, dividing them into bigrams and trigrams; and processing with Kazakh language POS pattern tag templates to adapt them for children. When the dictionary was formed, the semantic proximity of words and phrases to the given theme and age restrictions for children were taken into account. The formed dictionary phrases were evaluated using the cosine similarity, Euclidean similarity, and Manhattan distance metrics. Moreover, the dictionary was extended with video and audio data by implementing models like DALL-E 3, Midjourney, and Stable Diffusion to illustrate the dictionary data and TTS (Text to Speech) technology for the Kazakh language for voice synthesis. The developed thematic dictionary approach was tested, and a SUS (System Usability Scale) assessment of the application was conducted. The experimental results demonstrate the proposed approach’s high efficiency and its potential for wide use in educational purposes.

This study focuses on the development and evaluation of automatic speech recognition (ASR) systems for Kazakh child speech, an underexplored domain in both linguistic and computational research. A specialized acoustic corpus was constructed for children aged 2 to 8 years, incorporating age-related vocabulary stratification and gender variation to capture phonetic and prosodic diversity. The data were collected from three sources: a custom-designed Telegram bot, high-quality Dictaphone recordings, and naturalistic speech samples recorded in home and preschool environments. Four ASR models, Whisper, DeepSpeech, ESPnet, and Vosk, were evaluated. Whisper, ESPnet, and DeepSpeech were fine-tuned on the curated corpus, while Vosk was applied in its standard pretrained configuration. Performance was measured using five evaluation metrics: Word Error Rate (WER), BLEU, Translation Edit Rate (TER), Character Similarity Rate (CSRF2), and Accuracy. The results indicate that ESPnet achieved the highest accuracy (32%) and the lowest WER (0.242) for sentences, while Whisper performed well in semantically rich utterances (Accuracy = 33%; WER = 0.416). Vosk demonstrated the best performance on short words (Accuracy = 68%) and yielded the highest BLEU score (0.600) for short words. DeepSpeech showed moderate improvements in accuracy, particularly for short words (Accuracy = 60%), but faced challenges with longer utterances, achieving an Accuracy of 25% for sentences. These findings emphasize the critical importance of age-appropriate corpora and domain-specific adaptation when developing ASR systems for low-resource child speech, particularly in educational and therapeutic contexts.

The timely detection of psycho-emotional risks has become increasingly important due to the rapid growth of social media platforms. This study examines user-generated text as a potential source of early indicators of psychological vulnerability. The proposed NLP-based framework incorporates behavioral features to improve the interpretation of users’ psycho-emotional states. In addition to text classification, the study considers structured behavioral indicators to support psycho-emotional risk analysis. Particular attention is given to interpretability. SHAP-based techniques are applied to reveal the contribution of individual features and to provide a clearer explanation of model predictions. The evaluation was conducted on publicly available datasets containing textual data and aggregated behavioral/physiological indicators. No raw physiological streams, wearable sensor data, or biometric recordings were used. The two datasets were employed in complementary experimental settings and were not aligned at the individual-sample level; accordingly, the broader analytical perspective explored in this study should not be interpreted as a single end-to-end or fully aligned multimodal learning framework. The proposed BERT-based model with SHAP interpretability achieved an accuracy of 96.3%, an F1-score of 0.96, and a ROC–AUC score of 0.98, showing consistent improvement over baseline models, including Random Forests and Support Vector Machines.

This study addresses the problem of optimal resource allocation in nonlinear multi-module dynamic systems arising in complex computational and techno-economic processes, where numerical stability and strict enforcement of structural constraints are critical. The objective is to develop a computationally efficient optimal control algorithm capable of handling bilateral control constraints and external balance conditions without resorting to large-scale nonlinear programming or boundary-value shooting. The proposed method is based on a modified Lagrangian formulation, in which bilateral Karush–Kuhn–Tucker (KKT) conditions are analytically embedded into the optimality system. The resulting computational scheme consists of a coupled system of matrix and vector differential equations solved through a non-iterative backward–forward integration procedure. Numerical experiments conducted on a nonlinear model with Cobb–Douglas-type operators demonstrate the stable convergence of the trajectories toward a stationary regime, strict satisfaction of bilateral constraints, and consistent enforcement of balance relations throughout the planning horizon. Empirical scalability analysis indicates approximately cubic computational complexity with respect to the state dimension, while sensitivity tests confirm the numerical robustness across different integration tolerances and ODE solvers. These results demonstrate that the proposed structure-preserving framework provides a computationally stable and practically implementable approach to constrained optimal control in nonlinear multi-module systems.

Viral and fungal diseases of greenhouse strawberries lead to significant crop losses, while traditional uniform spraying schemes do not account for the actual distribution of infection foci or changes in the microclimate. This paper proposes an integrated system for greenhouse farms that combines a stochastic SIRS model of the epidemic process with a microclimate-dependent infection coefficient β_eff(t), a computer vision module based on a lightweight YOLOv10n detector, and a mobile sprayer robot. For three sets of parameters corresponding to moderate infection, outbreak, and suppression scenarios, ensemble simulations are performed (100 realizations per scenario). The results show that the maximum number of infected plants reaches approximately 690 out of 1000 in the outbreak scenario and only about 28 out of 1000 in the suppression scenario, reflecting the effect of timely microclimate correction and local spraying. The YOLOv10n detector is used as a sensor to determine the proportion of affected plants I(0)/N and provides automatic formation of the initial conditions of the population model. The resulting forecasts then serve as the basis for selecting one of three operating modes for the spraying robot (observation, microclimate correction, local treatment). Unlike existing works that consider disease detection, epidemiological models, or robotic spraying separately, this paper proposes a unified closed-loop scheme of “computer vision—stochastic model—mobile robot,” linking detection quality with epidemic process forecasting and treatment strategy. In this study, the feasibility of the proposed system was examined through numerical simulations, detector-level performance evaluation, and offline image-based integrated validation of the detector-to-decision workflow. Full closed-loop experiments in a real greenhouse environment are planned for future work.