The rapid expansion of artificial intelligence (AI) in digital education has transformed gamification from a motivational strategy into a data-driven, adaptive learning paradigm. This systematic review conceptualizes AI-supported gamification as an information-centered ecosystem integrating learning analytics, behavioral modeling, adaptive algorithms, and intelligent feedback mechanisms to enhance cognitive development and critical thinking. Following PRISMA 2020 guidelines, a systematic search was conducted across Scopus, Web of Science, ScienceDirect, Google Scholar, and ResearchGate. Peer-reviewed empirical studies published between 2020 and 2025 were considered. Studies were included if they examined gamification in educational contexts with AI-driven or adaptive system components, while non-educational contexts, duplicates, and non-English publications were excluded. After screening and eligibility assessment, 100 studies were included in the final synthesis. The review examines how AI-driven personalization, neurotechnology, predictive modeling, and generative systems reshape the design and effectiveness of gamified e-learning environments. Architectural patterns identified include recommender systems, real-time behavioral adaptation, affect-aware feedback loops, and algorithmic content generation. Across the reviewed studies, AI-supported gamified systems were frequently associated with increased engagement and moderate improvements in executive functions, higher-order reasoning, and adaptive learning pathways. However, challenges related to system transparency, data governance, algorithmic bias, cognitive load management, and equitable access remain significant. The review was not registered. By framing gamification as an adaptive information system rather than solely a pedagogical intervention, this study proposes a structured taxonomy of AI-driven gamified architectures—including data acquisition, user modeling, predictive analytics, and adaptive feedback layers—and outlines research priorities for scalable, ethically grounded, and data-informed e-learning ecosystems.

This study aims to improve the accuracy, speed, and safety of suicide risk assessment among adolescents in the digital ecosystems of smart cities. To achieve this goal, an integrated system architecture was developed that combines natural language processing methods, transformer models, and privacy-preserving computation. The methodological part includes large-scale textual data analysis, distributed processing in Apache Spark and Hadoop environments, and the use of federated learning, which allows models to be trained without transferring sensitive source information. The evaluation was conducted on open mental health datasets and supplemented by a series of experiments simulating the system's operation in real time, as well as surveys of specialists – psychologists, educators, and IT experts. The analysis showed that transformer models, particularly BERT, significantly outperform classical algorithms, achieving an AUC-ROC of 0.96 and an F1 score of 0.92 with an average response time of 2.4 seconds. Survey participants noted the importance of transparency and data protection, and the proposed architecture received high marks for reducing the risk of information leaks and providing robust audit mechanisms. The novelty of the work lies in the combination of predictive analytics, federated learning, differential privacy, and blockchain traceability in a single application-oriented system. The results show that ethically sound and rapid suicide risk detection can be implemented in schools, medical institutions, and municipal services, providing both practical benefits and contributing to methodological advancements.

This article presents a formal demonstration of a hybrid big data processing architecture that combines the fault tolerance and storage robustness of Hadoop with the speed and in-memory processing capabilities of Apache Spark. The proposed architecture is evaluated through test execution and performance benchmarking in real-world data centers across three regions in Kazakhstan. The model integrates distributed resource management components, Directed Acyclic Graph (DAG)-based scheduling mechanism, and Resilient Distributed Datasets (RDDs) to enable dynamic workload distribution and rapid failure recovery. The results demonstrate that the hybrid system consistently outperforms standalone Spark and Hadoop architectures under variable workloads, illustrating enhancements in execution time, task recovery, and resource utilization. Quantitative performance metrics allow for a structured comparison of architectures and help optimize deployments for diverse scenarios. The proposed hybrid architecture shows significant improvements, reducing average execution time by up to 38% and increasing resource efficiency by 25% compared to standalone Spark and Hadoop systems.

The analysis of the solution of the semi-empirical solution of turbulent diffusion in problems of polluting impurity transfer is carried out by Gauss approach. It is assumed that there is a certain occupied industrial point, which has one or several sources of the pollution, the arrangement of which is determined by coordinates x, y, z. For calculation of average impurity concentration from a point source the solution of semi-empirical equation by Gaussian function of impurity distribution, obtained by a method of Green's function was used. Furthermore, the normalization of the key parameters of the problem is carried out and the initial data are defined. By means of the obtained equation, the model of quantity assessment of the aerosol polluting substances arriving from a source with final and continuous duration of action is made. Thus, the considered computational and analytical model of methodology of assessing the concentration of polluting substances is applicable for applied problems of operational control of the condition of industrial region. Proposed model can be adapted to the air pollution monitoring robotic system

This article explores the challenges of integrating two deep learning neural networks, YOLOv5 and RT-DETR, to enhance the recognition of unmanned aerial vehicles (UAVs) within the optical-electronic channels of Sensor Fusion systems. The authors conducted an experimental study to test YOLOv5 and Faster RT-DETR in order to identify the average accuracy of UAV recognition. A dataset in the form of images of two classes of objects, UAVs, and birds, was prepared in advance. The total number of images, including augmentation, amounted to 6337. The authors implemented training, verification, and testing of the neural networks exploiting PyCharm 2024 IDE. Inference testing was conducted using six videos with UAV flights. On all test videos, RT-DETR-R50 was more accurate by an average of 18.7% in terms of average classification accuracy (Pc). In terms of operating speed, YOLOv5 was 3.4 ms more efficient. It has been established that the use of RT-DETR as the only module for UAV classification in optical-electronic detection channels is not effective due to the large volumes of calculations, which is due to the relatively large number of parameters. Based on the obtained results, an algorithm for combining two neural networks is proposed, which allows for increasing the accuracy of UAV and bird classification without significant losses in speed.