An Improved LSTM Based Early Warning Model for Physical Education Network Teaching Achievements
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
The development of data mining technology has pushed data-driven decision-making to gradually become thecore content of educational data mining. To identify students who are at risk of failing physical education onlinecourses at an early stage, this article uses bidirectional long-short term memory (BiLSTM) neural networks toconstruct a deep BiLSTM (DBiLSTM) prediction model. The experimental verification of its effectivenessshowed that in the full attribute data experiment, the DBiLSTM specificity at Stage 1 was the highest, at 30.8%,and the accuracy rate at Stage 3 was as high as 73.6%. In the best attribute data experiment, compared to thefull attribute, the accuracy of all models at Stage 2 increased, except for the SVM model, which had a 61.8%accuracy rate. At Stage 3, the early warning accuracy of DBiLSTM was higher than other algorithms, with arate of 75.7%. In the experiment after introducing the balanced data method, the accuracy of the DBiLSTMSMOTEmodel combined with the Synthetic Minority Oversampling Technique was 72.6%. At this time, theAUC value of DBiLSTM-SMPOTE reached 72.6% in the middle of the semester, significantly superior to otheralgorithm models. Overall, DBiLSTM is effective in the early warning of students’ performance in online sportscourses, while DBiLSTM-SMOTE is highly practical in early warning of performance in online sports teaching.
Abstract
The development of data mining technology has pushed data-driven decision-making to gradually become thecore content of educational data mining. To identify students who are at risk of failing physical education onlinecourses at an early stage, this article uses bidirectional long-short term memory (BiLSTM) neural networks toconstruct a deep BiLSTM (DBiLSTM) prediction model. The experimental verification of its effectivenessshowed that in the full attribute data experiment, the DBiLSTM specificity at Stage 1 was the highest, at 30.8%,and the accuracy rate at Stage 3 was as high as 73.6%. In the best attribute data experiment, compared to thefull attribute, the accuracy of all models at Stage 2 increased, except for the SVM model, which had a 61.8%accuracy rate. At Stage 3, the early warning accuracy of DBiLSTM was higher than other algorithms, with arate of 75.7%. In the experiment after introducing the balanced data method, the accuracy of the DBiLSTMSMOTEmodel combined with the Synthetic Minority Oversampling Technique was 72.6%. At this time, theAUC value of DBiLSTM-SMPOTE reached 72.6% in the middle of the semester, significantly superior to otheralgorithm models. Overall, DBiLSTM is effective in the early warning of students’ performance in online sportscourses, while DBiLSTM-SMOTE is highly practical in early warning of performance in online sports teaching.
참고문헌 (11)
- M. N. Yakubu, "Applying machine learning approach to predict students’ performance in higher educational institutions", Kybernetes, 51(2), pp.916~934 (2022)[DOI]
- S. Plak, "Early warning systems for more effective student counselling in higher education : evidence from a Dutch field experiment", Higher Education Quarterly, 76(1), pp.131~152 (2022)[DOI]
- S. Batool, "Educational data mining to predict students’ academic performance : a survey study", Education and Information Technologies, 28(1), pp.905~971 (2023)[DOI]
- M. Zhang, "Data mining applications in university information management system development", Journal of Intelligent Systems, 31(1), pp.207~220 (2022)[DOI]
- K. Mahboob, "Quality enhancement at higher education institutions by early identifying students at risk using data mining", Mehran University Research Journal of Engineering and Technology, 42(1), pp.120~136 (2023)[DOI]
- H. Ma, "Construction and implementation of a college talent cultivation system under deep learning and data mining algorithms", The Journal of Supercomputing, 78(4), pp.5681~5696 (2022)[DOI]
- L. Khanna, "Analysis of dependence of grade point average over psychological factors incorporating advanced data mining", International Journal of Intelligent Enterprise, 10(1), pp.31~47 (2023)[DOI]
- E. Buyukatak, "An investigation of data mining classification methods in classifying students according to 2018 PISA reading scores", International Journal of Assessment Tools in Education, 9(4), pp.867~882 (2022)[DOI]
- B. Quadir, "Analyzing the educational goals, problems and techniques used in educational big data research from 2010 to 2018", Interactive Learning Environments, 30(8), pp.1539~1555 (2022)[DOI]
- I. K. D. Nuryana, "Modeling data mining algorithm for predicting timely student graduation at State University Surabaya", Journal Research of Social, Science, Economics, and Management, 1(7), pp.795~808 (2022)[DOI]
- R. Kimmons, "Trends and topics in educational technology, 2022 edition", TechTrends, 66(2), pp.134~140 (2022)[DOI]