Scholarlink

This paper presents the development and practical implementation of a multi-level intelligent system based on artificial intelligence technologies to improve educational quality. The proposed framework integrates two core components: hybrid clustering techniques and evolutionary neural networks. In the first stage, student-related academic data - including grades, test scores, attendance records, and other performance indicators - are grouped automatically using a combination of K-Means and hierarchical clustering algorithms. In the second stage, a Decision Tree model is employed to predict academic outcomes. Based on the identified clusters, personalized learning strategies and recommendations are generated through neural networks optimized by evolutionary algorithms. The model has been tested on real-world educational data, and its effectiveness in forecasting performance and supporting adaptive learning was evaluated. This approach offers a scalable solution for accelerating digital transformation in education and enhancing student-centered instruction within the context of Uzbekistan’s educational reform.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Multi-level AI System for Enhancing Educational Quality Using Hybrid Clustering and Evolutionary Neural Networks

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Aziza Kayumova,
  • Nigina Bakhtiyorova,
  • Iroda Karshibaeva,
  • Nigina Mukhammadieva,
  • Maksud Beshimov

摘要

This paper presents the development and practical implementation of a multi-level intelligent system based on artificial intelligence technologies to improve educational quality. The proposed framework integrates two core components: hybrid clustering techniques and evolutionary neural networks. In the first stage, student-related academic data - including grades, test scores, attendance records, and other performance indicators - are grouped automatically using a combination of K-Means and hierarchical clustering algorithms. In the second stage, a Decision Tree model is employed to predict academic outcomes. Based on the identified clusters, personalized learning strategies and recommendations are generated through neural networks optimized by evolutionary algorithms. The model has been tested on real-world educational data, and its effectiveness in forecasting performance and supporting adaptive learning was evaluated. This approach offers a scalable solution for accelerating digital transformation in education and enhancing student-centered instruction within the context of Uzbekistan’s educational reform.