The Application of Multimedia Network Teaching Based on Big Data in Physical Education Teaching in Colleges and Universities

Abstract

The integration of educational information technology presents novel opportunities for revolutionizing traditional pedagogical approaches in college physical education (PE). This study leverages big data analytics through the application of the OpenPose algorithm to meticulously map human postural features, thereby refining instructional design within the college PE framework. In parallel, to align pedagogical resources more precisely with the unique demands of college education, a decision tree algorithm is employed to derive comprehensive user profiles from a cohort of college students, which aids in the targeted recommendation of educational materials. Moreover, this research incorporates online teaching methodologies to develop and implement a big data-driven multimedia network teaching platform tailored specifically for college sports education. Empirical evidence underscores substantial benefits following the platform’s deployment. Post-implementation metrics revealed a marked increase in both the duration and frequency of students’ independent physical activities; the proportion of students engaging in 91-120 minutes of exercise escalated by 15%, and those exercising between three to five times per week saw an increase of 16%. Additionally, the platform significantly enhanced the PE performance of students. Users of the platform attained an average score of 89.29 in their assessments, surpassing the control group’s average of 83.23, who did not utilize the platform. Consequently, this multimedia network teaching platform emerges as a formidable enhancement to college physical education, delivering significant pedagogical advancements and fostering increased physical activity among students.

Keywords

• big data
• physical education
• openpose
• decision tree algorithm
• multimedia instruction
• 68p30