Abstract
The convolutional neural network (CNN) is analyzed in sports motion identification to study human motion recognition based on deep learning and smart wearable devices in sports. First, the convolution feature extraction algorithms are introduced, which include the one-dimensional (1D) convolution feature extraction algorithm, the two-dimensional (2D) convolution feature extraction algorithm, and the combination of the 1D convolution and recurrent neural network (RNN) algorithm. Then, the human motion behavior recognition is studied based on an RNN that includes simple RNN, long short-term memory network (LSTM), bilateral recurrent neural network (BLSTM), and gated recurrent unit (GRU). Finally, the 1D CNN + LSTM algorithm is chosen as the optimal algorithm through experimental analysis and comparison. Meanwhile, two kinds of sensors supported by smart wearable devices are chosen through the above methods, and a network model is constructed for human sports behavior recognition to process data collected through smart wearable devices. Smart wearable devices can operate under any circumstances. Due to low energy consumption and cost, they have been widely used in various sports events. The sensitivity and accuracy of the sensors in the smart wearable devices can be improved through the proposed 1D + LSTM algorithm, promoting their application in various sport events.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Ascioglu G, Senol Y (2020) Design of a wearable wireless multi-sensor monitoring system and application for activity recognition using deep learning. IEEE Access 8:169183–169195
Ban TW, Lee W (2019) A deep learning based transmission algorithm for mobile device-to-device networks. Electronics 8(11):1361
Duan L, Yang K, Ruan L (2020) Research on automatic recognition of casting defects based on deep learning. IEEE Access 99:1–1
Dubey AK, Jain V (2020) Automatic facial recognition using VGG16 based transfer learning model. J Inf Opt Sci 41(7):1589–1596
Gao J, Gu P, Ren Q et al (2019) Abnormal gait recognition algorithm based on LSTM-CNN fusion network. IEEE Access 7:1–1
Gao Z, Xue KX, Wan SH (2020) Multiple discrimination and pairwise CNN for view-based 3D object retrieval. Neural Netw 125:290–302
Hsieh YZ, Lin SS, Xu FX (2020) Development of a wearable guide device based on convolutional neural network for blind or visually impaired persons. Multimed Tools Appl 79(4):743–752
Hsu YL, Chang HC, Chiu YJ (2019) Wearable sport activity classification based on deep convolutional neural network. IEEE Access 7:170199–170212
Huang W, Zhang H (2020) Research on application of deep learning based on mobile learning in smart grid. J Phys Conf Ser 1544(1):012094
Jankovi M, Savi A, Novii M et al (2018) Deep learning approaches for human activity recognition using wearable technology. Medicinski podmladak 69(3):14–24
Katariya MVB, Makawana YN, Goswami MPA (2012) A review on implementation of automatic movement controlled using gesture recognition. Int J Recent Technol Eng 1(5):124–135
Kim H, Kim J, Kim YS et al (2020) Energy-efficient wearable EPTS device using on-device DCNN processing for football activity classification. Sensors 20(21):6004
Liu D, Yang C, Li S et al (2019) FitCNN: a cloud-assisted and low-cost framework for updating CNNs on IoT devices. Futur Gener Comput Syst 91(2):277–289
Lv X, Ding L, Zhang G (2021) Research on fingerprint feature recognition of access control based on deep learning. Int J Biom 13(1):80
Nguyen MN, Nguyen TH (2020) Deep learning approaches to human gait pattern classification based on MEMS sensors. IEIE Trans Smart Process Comput 9(4):284
Shen S, Gu K, Chen XR et al (2020) Gesture recognition through sEMG with wearable device based on deep learning. Mobile Netw Appl 1:1–12
Shi J, Chen D, Wang M (2020) Pre-impact fall detection with CNN-based class activation mapping method. Sensors 20(17):4750
Shin SY, Cha JH (2018) Human activity recognition system using multimodal sensor and deep learning based on LSTM. Trans Korean Soc Mech Eng A 42(2):111–121
Termritthikun C, Jamtsho Y, Muneesawang P (2019) On-device facial verification using NUF-Net model of deep learning. Eng Appl Artif Intell 85:579–589
Wang L, Peng M, Zhou Q (2020) Pre-impact fall detection based on multi-source CNN ensemble. IEEE Sens J 20(10):5442–5451
Wasimuddin M, Elleithy K, Abuzneid A et al (2021) Multiclass ECG signal analysis using global average-based 2-D convolutional neural network modeling. Electronics 10(2):170
Xu H, Yan R (2020) Research on sports action recognition system based on cluster regression and improved ISA deep network. J Intell Fuzzy Syst 39(4):5871–5881
Xu Z, Zhao J, Yu Y et al (2020) Improved 1D-CNNs for behavior recognition using wearable sensor network. Comput Commun 151:165–171
Yun J , Woo J . A Comparative Analysis of Deep Learning and Machine Learning on Detecting Movement Directions Using PIR Sensors. IEEE Internet of Things Journal, 2019, PP(99):1–1.
Zeng F, Hu S, Xiao K (2019) Research on partial fingerprint recognition algorithm based on deep learning. Neural Comput Appl 31(2):1–10
Zhang W, Su C, He C (2020) Rehabilitation exercise recognition and evaluation based on smart sensors with deep learning framework. IEEE Access, (99):1–1
Zhao L, Su C, Dai Z et al (2020) Indoor device-free passive localization with DCNN for location-based services. J Supercomput 76(11):8432–8449
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
About this article
Cite this article
Zhang, X. Application of human motion recognition utilizing deep learning and smart wearable device in sports. Int J Syst Assur Eng Manag 12, 835–843 (2021). https://doi.org/10.1007/s13198-021-01118-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13198-021-01118-7