Abstract
The application of wireless sensor networks (WSNs) for monitoring vital signs of a human body, i.e., Wireless body sensor networks (WBSNs), has attained significant attention. The realization of WBSNs has cemented its place among a wide range of communication networks for monitoring various postures of a human being. One of the fundamental ways to increase athletes’ competitive level in modern sports is to accurately analyze aerobics workout postures using technical tools. The current generative models of three-dimensional (3D) human motion performs poorly and faces difficulties in analyzing the new movements of an athlete. Therefore, accurate prediction and analysis of aerobics training pose need to be made in real-time. This study uses deep learning (DL) and WBSN approaches to build artificial intelligence (AI)-based system for predicting and analyzing athletes’ posture. The solution uses an Arduino embedded development board as the basis, equipped with multiple inertial measurement units (IMUs) and vision sensors. Further, using stepper motors in combination, a system for collecting accurate human motion data such as velocity and acceleration is established. The proposed configuration yields accurate data on human motion. This study builds a DL model based on the symmetric, time-scale, and structural coding to identify human motion models precisely. These models’ performance was assessed in terms of classification error using the H3.5 M and CMU datasets. The experimental results verify the functional performance of the system, and the comparison with the existing latest encoder-recurrent-decoder (ERD) classification algorithms shows that the system has a low classification error and high real-time performance, which has good prospects for secondary development.
Similar content being viewed by others
References
Hasan, K., Biswas, K., Ahmed, K., Nafi, N. S., & Islam, M. S. (2019). “A comprehensive review of wireless body area network,“. Journal of Network and Computer Applications, 143, 178–198
Guo, X., Zhang, N., Guo, J., Zhang, H., Hao, Y., & Hang, J. (2019). Automated polyp segmentation for colonoscopy images: A method based on convolutional neural networks and ensemble learning,. Medical Physics, 46, 5666–5676
Kosisi (2017). he Xiping Exchange rate time series prediction based on trestle self encoder model Computer applications and software, 34 (3): 218-221247
Hongyan, Y., Yu, Z., Weihua, Z., Ming, S., & Yexin, Z. (2019). Design of IMU Dynamic Coefficient Calibration Based on Reduced Space Search Algorithm,. Journal of System Simulation, 31, 2485
XU, C., HE, J., ZHANG, X., YAO, C., S.-h. DUAN, and, & QI, Y. (2019). Human Motion Tracking Performance Evaluation Method Based on IMU/TOA Fusion,. ACTA ELECTONICA SINICA, 47, 1748
Li, M., Deng, J., Zha, F., Qiu, S., & Wang, X. (2018).“Motion Intention Estimation for Active Power-Assist Lower Limb Exoskeleton Robot (APAL),“
Guan, D., Cheng, J., Zhao, L., & Fei, Z. (2016). “Inertial-frame-based coarse initial alignment for marine strapdown inertial navigation system using wavelet de-noising,“ in 2016 35th Chinese Control Conference (CCC), pp. 5596–5600
Silanon, K. (2017). “Thai finger-spelling recognition using a cascaded classifier based on histogram of orientation gradient features,“ Computational Intelligence and Neuroscience, vol. 2017
Pereira Neiva, H., Brandão Faíl, L., Izquierdo, M., Marques, M. C., & Marinho, D. A. (2018). The effect of 12 weeks of water-aerobics on health status and physical fitness: An ecological approach,. PloS one, 13, e0198319
Chen, Q., & Alsemmeari, R. A. (2021). “Research on aerobics training posture motion capture based on mathematical similarity matching statistical analysis,“Applied Mathematics and Nonlinear Sciences,
Zenina, I., Kuzmenko, N., & Gavrilova, N. (2020). ; The Influence of Aerobics on The Emotional and Physical State of Students,
Chen, C. (2021). “Research on aerobics training and evaluation method based on artificial intelligence-aided modeling,“ Scientific Programming, vol. 2021
Zhou, Y. (2021). “Role of Human Body Posture Recognition Method Based on Wireless Network Kinect in Line Dance Aerobics and Gymnastics Training,“ Wireless Communications and Mobile Computing, vol. 2021
Abasgholipour, A., Shahbazi, M., Boroujeni, S. T., & Ameri, E. A. (2021). The effects of in-water and on-land aerobic training on postural sway and balance in patients with type 2 diabetes,. International Journal of Diabetes in Developing Countries, 41, 657–663
Liu, Q. (2022). “Aerobics posture recognition based on neural network and sensors,“. Neural Computing and Applications, 34, 3337–3348
Maksym Yachnyk (2021). ; Olena Zendyk; Iurii Iachniuk; Iryna Iachniuk; Carrying Out Specialties of Aqua Aerobics Lessons and Its Varieties,
Chu Jinghui, L., & Wei (2017). LV Wei Application of multigraph embedded representation in human motion pattern recognition. Computer science and exploration, 11(6), 941–949
Nothnagel, M., Fan, G., Guo, F., He, Y., Hou, Y., Hu, S., Huang, J., Jiang, X., Kim, W., & Kim, K. (2017). Revisiting the male genetic landscape of China: a multi-center study of almost 38,000 Y-STR haplotypes,. Human Genetics, 136, 485–497
Chen, S., & Yang, J. (2021). “Human Pose Estimation Based on Domain of Interest and Part Affinity Field,“ in 2021 3rd International Conference on Robotics and Computer Vision (ICRCV), pp. 78–81
Lee, G. M. (2021). “Human Face Detection Techniques: A Comprehensive Review and Future Research Directions,“
Wang, & Tao, G. (2019). Multi-layer perceptron generation countermeasure network based on semi supervised learning. Small microcomputer system, 40(11), 2297–2303
Liu, & Jiatong, Ge Fen Implementation of data decoding system of S / PDIF receiver based on FPGA,Electronic devices, 2018,41 (3):738–742
Liu Haibo, F., & Shi (2019). Yu Ge A collaborative filtering automatic encoder model based on side information enhancement. Journal of Northeast University (NATURAL SCIENCE EDITION), 40(11), 1527–1532
Li, & Xing (2018). Xiao Qin Kun Human motion behavior recognition method based on automatic encoder and probabilistic neural network. Software guide, 17(1), 11–1318
Ji Xiaofei, Q., & Linlin (2019). Wang Yangyang Interactive behavior recognition of two people based on RGB and joint point data fusion model. Computer applications, 39(11), 3349–3354
Tian Yi, H., Xinbo, Y., Zhengkang, et al. (2020). Design and improvement of transmission line on-line monitoring communication network,Journal of Xi’an University of engineering, (4):72–79
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Cao, T. Analysis of aerobic training posture using machine vision for body area networks. Wireless Netw 29, 1611–1620 (2023). https://doi.org/10.1007/s11276-022-03123-5
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11276-022-03123-5