The correction system of student actions in the physical education classroom based on improved machine learning

• Published in: 2023 International Conference on Emerging Research in Computational Science (ICERCS) pp. 1 - 6
• Main Authors: Abdulsada, Zainab. R., Ahmed, Ibrahem, Alubady, Raaid, Salman Mazin, Hayder Mahmood, Al-Tahee, Mustafa, Abdulaziz, Saad
• Format: Conference Proceeding
• Language: English
• Published: IEEE 07-12-2023
• Subjects: Analytical models; Education; Hidden Markov Model; Hidden Markov models; Machine learning; Mathematical models; Numerical models; Physical Education; Predictive models; student actions
• DOI: 10.1109/ICERCS57948.2023.10434099

The educational system has a general evaluation of the effects of physical education on universities that give students instruction without the involvement of educators. Physical education (PE) teachers face several obstacles in the classroom, including the difficulty of conveying complex concepts like proper form, correct pupil mobility, and adequate exercise assignments. Increasing the effectiveness of university education programmes and student activity is necessary. Therefore, utilizing improved machine learning, the Hidden Markov model-assisted correction system (HMMCS) has been suggested in this research to improve student behaviour in the physical education classroom. The student's CS examines how the college physical education classroom has improved. University physical education instruction is evaluated using HMM, and university physical education learning is estimated using a mathematical calculation. The experiment's outcome demonstrates that encouraging physical education teacher performance assessment in colleges is advantageous. The simulation outcomes depicts that proposed HMM-CS model improves the predictive rate of 98.8%, overall efficiency of 96.8%, probability ratio of 97.3%, score analysis rate of 98.5%, and an error occurance of 20.3% in contrast to the state-of-the-art alternatives.