Research on sports training model based on intelligent data aggregation processing in internet of things

被引:24
作者
Dan, Juan [1 ]
Zheng, Yanjun [2 ]
Hu, Jianping [3 ]
机构
[1] Henan Univ, Sch Phys Educ, Kaifeng 475001, Peoples R China
[2] Henan Polytech Univ, Sch Math & Informat Sci, Jiaozuo 454000, Henan, Peoples R China
[3] Henan Polytech Univ, Sch Phys Educ, Jiaozuo 454000, Henan, Peoples R China
来源
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS | 2022年 / 25卷 / 01期
关键词
Intelligent data aggregation; Modern computer technology; Physical training; Simulation; Internet of things;
D O I
10.1007/s10586-021-03469-z
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In order to improve the visual level of physical training and promote the optimization of sports training, the computer multimedia technology and Internet of things (IoT) are used to simulate the sports training model. Traditionally, the design complexity and control performance of the high-dimensional spatial sports training model are high, and the control performance is poor. A design method of computer multimedia simulation sports training model is proposed based on attitude change space fast exploration control, and computer multimedia simulation method is adopted to construct human body sports training and body movement mathematical model. In the physical training and kinematics model of human body, the position and pose feature information of human body is extracted quickly. Multimedia image analysis and intelligent control are used to simulate the process of human sports training and analyze the constraint parameters of motion planning in attitude change space to realize the optimal control of physical training and body motion planning. The simulation results show that the design of sports training model based on computer multimedia simulation is more controllable, the prediction error of motion attitude parameter is lower, and the multimedia control ability of sports training model is stronger, the effect of physical training is improved. In addition, the simulation results verify the effectiveness of in IoT.
引用
收藏
页码:727 / 734
页数:8
相关论文
共 25 条
[1]  
[毕安琪 Bi Anqi], 2016, [计算机研究与发展, Journal of Computer Research and Development], V53, P1029
[2]  
de Frein R., 2008, International Mathematical Forum, V3, P1853
[3]  
Deng Zhongliang, 2016, Journal of Computer Applications, V36, P295, DOI 10.11772/j.issn.1001-9081.2016.02.0295
[4]   Achieving Efficient Cloud Search Services: Multi-Keyword Ranked Search over Encrypted Cloud Data Supporting Parallel Computing [J].
Fu, Zhangjie ;
Sun, Xingming ;
Liu, Qi ;
Zhou, Lu ;
Shu, Jiangang .
IEICE TRANSACTIONS ON COMMUNICATIONS, 2015, E98B (01) :190-200
[5]   Internet of Things (IoT): A vision, architectural elements, and future directions [J].
Gubbi, Jayavardhana ;
Buyya, Rajkumar ;
Marusic, Slaven ;
Palaniswami, Marimuthu .
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2013, 29 (07) :1645-1660
[6]  
[胡俐蕊 Hu Lirui], 2013, [计算机科学, Computer Science], V40, P269
[7]   Collaborative Fuzzy Clustering From Multiple Weighted Views [J].
Jiang, Yizhang ;
Chung, Fu-Lai ;
Wang, Shitong ;
Deng, Zhaohong ;
Wang, Jun ;
Qian, Pengjiang .
IEEE TRANSACTIONS ON CYBERNETICS, 2015, 45 (04) :688-701
[8]   Collaborative filtering algorithm based on structured projective nonnegative matrix factorization [J].
Ju, Bin ;
Qian, Yun-Tao ;
Ye, Min-Chao .
Zhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science), 2015, 49 (07) :1319-1325
[9]   Efficient backprop [J].
LeCun, Y ;
Bottou, L ;
Orr, GB ;
Müller, KR .
NEURAL NETWORKS: TRICKS OF THE TRADE, 1998, 1524 :9-50
[10]  
[李冰锋 Li Bingfeng], 2017, [信息与控制, Information and Control], V46, P53