Economics, Econometrics and Finance, Computer Science, Information Systems and Management, Language and Linguistics
5
Scopus Publications
Scopus Publications
Development of a Machine Learning Model for Forecasting the Labor Market of the Kyrgyz Republic Saltanat Biibosunova, Huang Da, Fan Xingzhuo, Zhenh Xiaohang, Ma Yi Ming, Liu Fang International Conference on Artificial Intelligence Computer Data Sciences and Applications Acdsa 2026, 2026 The research creates machine learning system which predicts Kyrgyz Republic employment based on monthly economic data from January 2013 through December 2024. The research method starts with data preparation steps which include handling missing data and detecting outliers and normalizing the data and verifying its stationarity. The research team tested five different models including Linear Regression and Polynomial Regression and Support Vector Regression (SVR) and Random Forest and Gradient Boosting and a fully connected Neural Network. The research used Time-series walk-forward validation together with k-fold cross-validation to achieve stable results while using persistence and seasonal naïve benchmarks as reference points. The Gradient Boosting model produced the highest performance results through its RMSE and MAE and MAPE metrics which exceeded all competing models. The analysis reveals that employment responds most strongly to GDP and wage rates and industrial output but trade statistics have minimal impact. The research findings offer valuable policy information while showing how machine learning methods work effectively in countries with restricted access to data.
PCB Board Defect Detection Algorithm Based on Improved YOLOv8 Meijie Zhao, Haoyuan Xu, Saltanat Biibosunova, Shuo Zhang 2025 10th International Symposium on Advances in Electrical Electronics and Computer Engineering Isaeece 2025, 2025 To address the issues of insufficient fine-grained defect feature extraction and limited detection accuracy in traditional YOLOv8 algorithm models for PCB industrial board defect detection, this paper proposes a PCB board defect detection method based on an improved YOLOv8 network. This method introduces partial convolutional modules and multi-scale channel attention mechanisms into the head network of the original YOLOv8 algorithm framework to enhance the model’s feature extraction capabilities and multi-scale information fusion capabilities for defect regions. The PConv module effectively improves the model’s perception of local features in defect regions, while the MLCA mechanism enhances the model’s ability to focus on features across different scale channels, thereby improving detection accuracy and robustness. Experiments show that the improved algorithm model achieves an average accuracy of 87.3% and a recall rate of 82.1%, which are 4.1% and 2.9% higher than the original YOLOv8 model, respectively. This study provides an efficient and high-precision solution for PCB board defect detection, which is of great value for practical industrial detection.
Loyalty assessment system for the small business customers Saltanat Biibosunova, Li Dan, Yu Xinqi, Zholchubek Kutunaev, Li Jiaohui, Han Xiuzhi International Conference on Artificial Intelligence Computer Data Sciences and Applications Acdsa 2025, 2025 This paper describes the development of a loyalty points system for small businesses. The system is developed using monolithic architecture and the Django framework to minimize development time and for easy deployment. PostgreSQL is chosen as the strong and stable database management system. The ease of use of the Django Admin is enhanced by Django-admin-interface. A comprehensive analysis of the existing loyalty program solutions is performed; the specificities of small business requirements are identified and described in detail; the system architecture, business logic, user interfaces, and security measures of the system are described in detail. An economic rationale for development is also provided.
MACHINE LEARNING FOR CROP YIELD FORECASTING Bolotbek Biibosunov, Baratbek Sabitov, Saltanat Biibosunova, Zhamin Sheishenov, Sharshenbek Zhusupkeldiev, Zhyldyz Mamadalieva Cybernetics and Physics, 2023 Amid the persistent rise in global population, there has been a heightened focus on food security by academia, governmental initiatives, and international endeavors. Food security serves as a critical pillar in the national security framework, contributing to a nation’s sovereignty and self-sufficiency in food supply. To fulfill global requirements for essential food items, there is an imperative need to enhance agricultural efficiency across countries. Concurrently, agricultural practices must align with contemporary quality standards and meet consumer needs, drawing upon an integrated approach to crop cultivation technologies and yield classifications. Methodologies and tools for yield augmentation, grounded in scientific advancements in predictive modeling, are of paramount importance. Investigating the plethora of variables that contribute to optimal crop development, which in turn influences yield, poses significant challenges. Comprehensive inquiries that incorporate cutting-edge scientific and technological methodologies are essential for creating precise yield forecasts. The evolving landscape of yield modeling and prediction has emerged as a technologically sophisticated domain. Advanced methods such as machine learning and deep learning offer robust platforms for addressing crop yield forecasting, particularly when coupled with extensive datasets on environmental variables. A growing body of literature suggests the promising role of computational technologies and machine learning paradigms, inclusive of various forms of remote sensing data, in fine-tuning yield models. Yield prediction models are often characterized by intricate nonlinear equations influenced by a range of factors: seed quality and diversity, soil attributes, climatic variables, fertilizer usage, and other agronomic practices. The impacts of these variables on crop yield are varied, with some exerting greater influence than others. Additionally, crop yield is susceptible to adverse environmental and climatic conditions. While there exists a rich corpus of research on yield forecasting, addressing this issue remains an exigent priority in the agricultural sector.
Development of Digital Platform for Social Media Creating in the Kyrgyz Republic Bolotbek Biibosunov, Saltanat Biibosunova, Marat Kozhonov ACM International Conference Proceeding Series, 2019 Here in the paper we outline and tell about the Project developed by us, named ELTOR.KG -- multipurpose hardware and software platform, autonomous information network, virtual cloud technology. Our ElTOR.KG system allows implementing all the above-mentioned components to build a modern information society. ELTOR.KG information network consists of two mutually integrated informational web portals, social media and business network. The public network is of a social nature and belongs to the category of Government-to-Public-to-Citizens (G2P2C) - Government-Public-Citizens. This network has been pretested and is ready for launch. The business network is commercial in nature, designed for small and medium-sized businesses, manufacturing, agriculture, trade, services, etc. and belongs to the category of Business-to-business-to-Customer (B2B2C) - Business-Business-Consumer. This network is in the testing phase. ELTOR.KG Project as an information network is designed and developed on its own software platform.
