This paper presents a large-scale empirical study aimed at identifying the optimal local deep learning model and data volume for deploying intrusion detection systems (IDS) on resource-constrained IoT devices using federated learning (FL). While previous studies on FL-based IDS for IoT have primarily focused on maximizing accuracy, they often overlook the computational limitations of IoT hardware and the feasibility of local model deployment. In this work, three deep learning architectures—a deep neural network (DNN), a convolutional neural network (CNN), and a hybrid CNN+BiLSTM—are trained using the CICIoT2023 dataset within a federated learning environment simulating up to 150 IoT devices. The study evaluates how detection accuracy, convergence speed, and inference costs (latency and model size) vary across different local data scales and model complexities. Results demonstrate that CNN achieves the best trade-off between detection performance and computational efficiency, reaching ~98% accuracy with low latency and a compact model footprint. The more complex CNN+BiLSTM architecture yields slightly higher accuracy (~99%) at a significantly greater computational cost. Deployment tests on Raspberry Pi 5 devices confirm that all three models can be effectively implemented on real-world IoT edge hardware. These findings offer practical guidance for researchers and practitioners in selecting scalable and lightweight IDS models suitable for real-world federated IoT deployments, supporting secure and efficient anomaly detection in urban IoT networks.

Background: The modern credit card system is critical, but it has not been fully examined to meet the unique financial needs of a constantly changing number of manufacturers and importers. Methods: An intelligent credit card system integrates the features of artificial intelligence and blockchain technology. The decentralized and unchangeable ledger of the Blockchain technology significantly reduces the risk of fraud while maintaining real-time transaction recording. On the other hand, the capabilities of AI-driven credit assessment algorithms enable more precise, effective, and customized credit choices that are specifically tailored to meet the unique financial profiles of manufacturers and importers. Results: Several metrics, including predictive credit risk, fraud detection, credit assessment accuracy, default rate comparison, loan approval rate comparison, and other important metrics affecting the credit card system, have been investigated to determine the effectiveness of modern credit card systems when using Blockchain technology and AI. Conclusion: The study of developing an intelligent scoring system for crediting manufacturers and importers of goods in Industry 4.0 can be enhanced by incorporating user adoption. The changing legislation and increasing security threats necessitate ongoing monitoring. Scalability difficulties can be handled by detailed planning that focuses on integration, data migration, and change management. The research may potentially increase operational efficiency in the manufacturing and importing industries.

A log data analysis plays an important role in the uranium mining process. Automating this analysis using machine learning methods improves the results and reduces the influence of the human factor. In particular, the identification of reservoir oxidation zones (ROZs) using machine learning allows a more accurate determination of ore reserves, and correct lithological classification allows the optimization of the mining process. However, training and tuning machine learning models requires labeled datasets, which are hardly available for uranium deposits. In addition, in problems of interpreting logging data using machine learning, data preprocessing is of great importance, in other words, a transformation of the original dataset that allows improving the classification or prediction result. This paper describes a uranium well log (UWL) dataset generated with the employment of floating data windows and designed to solve the problems of identifying ROZ and lithological classification (LC) on sandstone-type uranium deposits. Comparative results of the ways of solving these problems using classical machine learning methods and ensembles of machine learning algorithms are presented. It has been shown that an increase in the size of the floating data window can improve the quality of ROZ classification by 7–9% and LC by 6–12%. As a result, the best-quality indicators for solving these problems were obtained, f1_score_macro = 0.744 (ROZ) and accuracy = 0.694 (LC), using the light gradient boosting machine and extreme gradient boosting, respectively.

This article presents a comparative analysis of international benchmarking systems and their application to assessing urban livability and citizen engagement. The research examines key global indices – Economist Intelligence Unit (EIU), Mercer, PwC, TUWIEN Smart City Model, MIT Treepedia, and the National League of Cities (NLC) – to identify dominant trends and classification models of city benchmarking. Four major types of benchmarking practices were defined: multi-factor indices, single-indicator rankings, thematic analytical reviews, and diagnostic metrics. An empirical case study of Almaty, Kazakhstan, demonstrates the adaptation of international practices to the local context. Between 2020 and 2023, over 1,500 participatory projects were implemented under the Participatory Budget program, primarily in urban greening, infrastructure, and public safety. The findings show that digital governance platforms (Open Almaty, iKomek, Almaty Urban Center) enhance civic participation but remain limited by unequal digital access. The study concludes that benchmarking serves as an effective governance and evaluation tool for improving urban livability and inclusiveness. The Almaty case illustrates the potential of combining global best practices, data-driven governance, and participatory approaches to foster sustainable urban transformation.

Unlike reactive systems, mechanical ventilation controlled by CO₂ concentration operates at a target efficiency that dynamically increases whenever the target CO₂ level is exceeded. This approach eliminates the typical ‘dead-time’ and prevents air quality degradation by ensuring the system adjusts its performance immediately in response to concentration changes. In this work, the study focuses on the development and evaluation of data-driven predictive models for near-term indoor CO₂ forecasting that can be integrated into pre-occupancy ventilation strategies, rather than designing a complete control scheme. Experimental data were collected over four months in a 48 m² smart laboratory configured as an open-plan office, where a heterogeneous IoT sensing architecture logged synchronized time-series measurements of CO₂ and microclimate variables (temperature, relative humidity, PM_2.5, TVOCs), together with acoustic noise levels and appliance-level energy consumption used as indirect occupancy-related signals. Raw telemetry was transformed into a 22-feature state vector using a structured feature engineering method incorporating z-score standardization, cyclic time encodings, multi-horizon CO₂ lags, rolling statistics, momentum features, and non-linear interactions to represent temporal autocorrelation and daily periodicity. The study benchmarks multiple regression paradigms, including simple baselines and ensemble methods, and found that an automated multi-level stacked ensemble achieved the highest predictive fidelity for short-term forecasting, with an Mean Absolute Error (MAE) of 32.97 ppm across an observed CO₂ range of 403–2305 ppm, representing improvements of approximately 24% and 43% over Linear Regression and K-Nearest Neighbors (KNN), respectively. Temporal diagnostics showed strong phase alignment with observed CO₂ rises during occupancy transitions and statistically reliable prediction intervals. Five-fold walk-forward cross-validation confirmed the temporal stability of these results, with top models achieving consistent R² values of 0.93–0.95 across Folds 2–5. These results demonstrate that, within a single-room university laboratory setting, historical sensor data from low-cost IoT devices can support accurate short-term CO₂ forecasting, providing a predictive layer that could support future proactive ventilation scheduling aimed at reducing CO₂ lag at the start of occupancy while avoiding unnecessary ventilation runtime. Generalization to other building types and occupancy profiles requires further validation.