EVALUATION OF ATHLETE PHYSICAL FITNESS BASED ON DEEP LEARNING

被引:0
作者
Lv, Youyang [1 ]
机构
[1] Guizhou Normal Univ, Sch Phys Educ, Guiyang 550025, Guizhou, Peoples R China
来源
SCALABLE COMPUTING-PRACTICE AND EXPERIENCE | 2024年 / 25卷 / 06期
关键词
Deep learning; Athlete physical fitness; Evaluation; Flipped Classroom;
D O I
10.12694/scpe.v25i6.3222
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
In order to promote deep learning in physical education for students, guided by the concept of deep learning, the author integrates the concept of deep learning into flipped classrooms. The author proposes a flipped classroom design and classroom implementation process for promoting deep learning, and conducts a semester long experimental research based on basketball courses, continuously optimizing the design during this period.Through the analysis of various parameters appearing in the operation, the test results are satisfactory. The study found that students in three classes were physically trained by using the classroom teaching method of "deep learning". The classroom teaching mode based on deep learning achieved the best teaching results in the first stage. One habit that inspires real emotion in children is their pace: running in different directions. Classroom teaching based on deep learning can make students understand the importance of cross-movement. Thus, after experiment, there was no significant difference between the flipped classes and the traditional class teaching method in the cross run compared to before experiment. The effectiveness of flipped classroom design for promoting deep learning has been verified, achieving a promoting effect on students' deep learning. The flipped classroom designed by this research institute can effectively promote learners to achieve deep learning, specifically manifested as: The physical fitness level of students has improved, the level of cognitive structure has improved, and students are more able to learn independently. The goal of deep learning for students has been achieved.
引用
收藏
页码:5286 / 5294
页数:9
相关论文
共 10 条
  • [1] Fauzi I., 2023, Sport Pedagogy Journal, V879, P790
  • [2] Fully automated deep-learning section-based muscle segmentation from CT images for sarcopenia assessment
    Islam, S.
    Kanavati, F.
    Arain, Z.
    Da Costa, O. Fadeeva
    Crum, W.
    Aboagye, E. O.
    Rockall, A. G.
    [J]. CLINICAL RADIOLOGY, 2022, 77 (05) : E363 - E371
  • [3] Jiao C., 2022, Computational and Mathematical Methods in Medicine, V2022, P78
  • [4] Qi K., 2022, Emergency Management Science and Technology, V1, P1
  • [5] Qian Q., 2022, ITM Web of Conferences, V89, P24
  • [6] Wang H, 2023, J MECH MED BIOL, V23, DOI [10.16429/j.1009-7848.2023.08.001, 10.1142/S0219519423400018]
  • [7] Wang J., 2022, Mathematical Problems in Engineering: Theory, Methods and Applications, V35, P46
  • [8] Optimal Frequency Regulation Based on Characterizing the Air Conditioning Cluster by Online Deep Learning
    Xu, Yeyan
    Yao, Liangzhong
    Liao, Siyang
    Li, Yaping
    Xu, Jian
    Cheng, Fan
    [J]. CSEE JOURNAL OF POWER AND ENERGY SYSTEMS, 2022, 8 (05): : 1373 - 1387
  • [9] Research on Simulation Analysis of Physical Training Based on Deep Learning Algorithm
    Zhao Hui
    Chen Jing
    Wang Taining
    [J]. SCIENTIFIC PROGRAMMING, 2022, 2022