This study explored the integration of blockchain and artificial intelligence technologies to enhance the security framework of electronic voting (e-voting) systems. Amid increasing vulnerabilities and cyber threats to electoral integrity, these technologies provided robust solutions by ensuring the immutability of voting records and enabling real-time anomaly detection. Blockchain technology secured votes in a decentralized, tamper-proof ledger, preventing unauthorized modifications, and enhancing transparency. Concurrently, artificial intelligence leveraged predictive analytics to dynamically monitor and respond to potential security threats, thereby ensuring the reliability and integrity of the voting process. This paper presented a dual-technology approach where blockchain’s transparency complemented artificial intelligence’s (AI) threat detection capabilities, providing a comprehensive security solution for e-voting systems. Through theoretical models and empirical data, we demonstrated significant improvements in transaction throughput, threat detection accuracy, and system scalability. The findings suggested that the strategic application of these technologies could substantially mitigate current e-voting vulnerabilities, offering a pathway to more secure, transparent, and efficient electoral processes globally.
30 August 2024 in Eastern-European Journal of Enterprise Technologies
The study focuses on the enhancement of e-voting blockchain network security through the integration of artificial intelligence. The critical problem addressed is the existing limitations in real-time threat detection and anomaly detection within blockchain transactions. These limitations can compromise the integrity and security of blockchain networks, making them vulnerable to attacks and fraudulent activities. The core results of the research include the development and implementation of sophisticated AI algorithms designed to enhance the monitoring of blockchain transactions and the auditing of smart contracts. These AI-driven advancements introduce unique features, such as the capability to detect and respond to security threats and anomalies in real-time. This significantly strengthens and optimizes the security frameworks of blockchain systems in e-voting. These results are explained by the strategic application of machine learning and natural language processing methodologies. By employing these advanced AI techniques, the study has achieved more accurate and efficient threat detection, thereby addressing the security challenges previously mentioned. The practical applications of these findings are extensive and diverse. Enhanced security mechanisms can be utilized in financial transactions, supply chain management, and decentralized applications, providing a robust framework for improved blockchain-based e-voting security. In conclusion, integrating AI into blockchain security mechanisms addresses current limitations in threat detection and offers a scalable and effective solution for future security challenges
30 December 2025 in Eastern-European Journal of Enterprise Technologies
The object of this study is the process and analysis of intelligent recognition and classification of spatiotemporal patterns in large arrays of streaming data. The problem to be solved is the absence of a deep learning framework that can guarantee adaptability to rapidly changing concepts, efficient computation for continuous data streams, and the transparency of the prediction process when working with heterogeneous and dynamically changing sources of big data used to support decision making. The developed programing framework applies convolutional neural network- long short – term memory networks with an attention-gating mechanism that enables detection of spatiotemporal dependencies and exhibits model interpretation of decisions. Extensive evaluation of the implemented system using multivariate flow-based data demonstrated the performance capabilities of the system with a classification accuracy of 0.98, F1 score of 0.97, area under the receiver operating characteristic curve of 0.99 and Harmonic Score of 0.90. The interpretation of the results is summarized by the interaction of multilevel feature extraction followed by an optimization process through Kullback-Leibler divergence that ensures reliable online drift detection and automatic models re-training. Additional contributions of the systematic use of the framework included interpretable decisions using Shapley Additive explanations and gradient-weighted class activation mapping visualizations. It has a strong evidence of sustained reliable model performance in non-stationarity data conditions and streaming data. The outcome of this study embodies significant practical implications toward the creation of real-time decision-support systems in domains. Finally, the structured framework can also be utilized for future investigations into the development of highly scalable, explainable, and trust-worthy artificial intelligence architectures.
The paper presents the development of a simplified laboratory selective laser melting (SLM) unit aimed at cheapening the technology by replacing the complex powder feeding system with an open surface with software-controlled dosing and leveling mechanisms. The proposed design allows the use of typical 3D printing software with minimal modifications, facilitating integration and control. A technical implementation of the powder dispensing module is described, including stepper motors, an Arduino microcontroller, and a C# user interface. A layer formation algorithm is developed to ensure that mechanical damage to the part is prevented due to the special motion of the platform. The results of pilot experiments on the creation of a volumetric metal object using a 100 W fiber laser are presented.
30 March 2025 in Bulletin of the National Engineering Academy of the Republic of Kazakhstan
SUS. Seifullin Kazakh Agrotechnical Research University
S. Seifullin Kazakh Agrotechnical Research University
+2
In the COVID-19 pandemic, the education system has faced unprecedented challenges requiring adaptation and implementation of new teaching methods and data analysis. This article discusses the use of ensemble machine learning models to predict student learning activity in distance education. The data on student engagement collected through the questionnaire is analyzed, and forecasting models are built based on these data. The study revealed that the combination of random forest (RF), k-nearest neighbor (KNN) algorithms and the gradient bootstrap method (XGBoost) demonstrates high accuracy and reliability of forecasts. The results of the study show that ensemble models can be effectively used to analyze educational data and make informed decisions in crisis situations. The research uses data from a survey conducted by the National Academy of Education named after I. Altynsarin in 2020 with the participation of 39,450 students from schools in the Republic of Kazakhstan.
Machine learning on small designed experiments is prone to optimistic evaluation when several observations share one physical unit and are split row-wise between training and test sets. We study this problem on a small hierarchical factorial dataset—81 section-level observations from 27 specimens of hard-turned 51CrV4 steel—with two physically different targets: surface roughness (Ra) and post-process hardness (HV30). We propose (i) a leakage-safe evaluation protocol based on specimen-grouped nested cross-validation (nine outer, four inner folds) with fold-local preprocessing, and (ii) Factorial-Aware Asymmetric Target Fusion (FA-ATF), a multi-output learner that encodes the specimen–section hierarchy through a factorial line-profile backbone, uses target-specific backbones, and admits additional experts and residual correction only when inner-fold gains are stable. Under the same protocol, FA-ATF was compared with 17 models spanning regularized regression, mixed-effects, kernel, ensemble, boosting, Gaussian process, and neural approaches. FA-ATF yielded the best observed performance (mean target-wise normalized root-mean-square error (NRMSE) 0.3773; macro-R2 0.8542) and ranked first in 83% of specimen-cluster bootstrap resamples, and ablation attributed almost all of the gain to the factorial line-profile backbone, which is the core contribution, rather than to the additional components. Multiplicity-corrected paired tests did not establish statistically significant superiority over the strongest comparators, and several differences were too small to matter in practice, illustrating how grouped validation tempers performance claims on small data. Code, fold specifications, and out-of-fold predictions are openly available.