Scholarlink

Students’ performance prediction in modern education remains a critical task. Due to the evaluation of the education system into individualized learning, E-learning platforms have emerged as the major environment of learning with a high count of people. The existing researches on the students’ performance prediction faced several challenges such as time complexity, interpretability, computational cost, and so on. To overcome the challenges addressed by the conventional methods, Sea Hawk optimized Single head attention enabled Bi-directional Long Short Term Memory (SH2ABM) is proposed in the research. The Sea Hawk optimization (SHO) is utilized to achieve the accurate prediction incorporation of the Bi-directional Long Short Term Memory (BiLSTM). Further, the integration of Single head attention aids in attaining the contextual information that provides better accuracy. The performance of the model is evaluated with the Mean Absolute Error (MAE), Mean Square Error (MSE), and Root Mean Square Error (RMSE) achieved at 1.15, 7.04, and 2.65 respectively.

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

Students’ Performance Prediction in an E-Learning Platform With Sea Hawk Optimized Single Head Attention Enabled Bi-Directional Long Short Term Memory

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Geeta Tripathi,
  • Sushama A. Deshmukh

摘要

Students’ performance prediction in modern education remains a critical task. Due to the evaluation of the education system into individualized learning, E-learning platforms have emerged as the major environment of learning with a high count of people. The existing researches on the students’ performance prediction faced several challenges such as time complexity, interpretability, computational cost, and so on. To overcome the challenges addressed by the conventional methods, Sea Hawk optimized Single head attention enabled Bi-directional Long Short Term Memory (SH2ABM) is proposed in the research. The Sea Hawk optimization (SHO) is utilized to achieve the accurate prediction incorporation of the Bi-directional Long Short Term Memory (BiLSTM). Further, the integration of Single head attention aids in attaining the contextual information that provides better accuracy. The performance of the model is evaluated with the Mean Absolute Error (MAE), Mean Square Error (MSE), and Root Mean Square Error (RMSE) achieved at 1.15, 7.04, and 2.65 respectively.