Real-Time Detection of Gait Events by Recurrent Neural Networks

被引:9
|
作者
Wang, Fu-Cheng [1 ]
Li, You-Chi [1 ]
Kuo, Tien-Yun [1 ]
Chen, Szu-Fu [2 ,3 ]
Lin, Chin-Hsien [4 ]
机构
[1] Natl Taiwan Univ, Dept Mech Engn, Taipei 10617, Taiwan
[2] Cheng Hsin Gen Hosp, Dept Phys Med & Rehabil, Taipei 112, Taiwan
[3] Natl Def Med Ctr, Dept Physiol & Biophys, Taipei 114, Taiwan
[4] Natl Taiwan Univ Hosp, Dept Neurol, Taipei 100, Taiwan
关键词
Legged locomotion; Real-time systems; Recurrent neural networks; Data models; Diseases; Heuristic algorithms; Stroke (medical condition); Gait; neural network; deep learning; heel strike; stroke; Parkinson's disease; CLASSIFICATION; OSTEOARTHRITIS; NAVIGATION; DISORDERS; STROKE; HIP;
D O I
10.1109/ACCESS.2021.3116047
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper proposes a gait detection model that can recognize important gait events in real time. Human gaits are periodic, with each gait cycle containing the important gait events of mid-swing, heel-strike (HS), and toe-off. The correct identification of different gait patterns caused by stroke or progressive neurodegenerative Parkinson's disease could ensure that the patients receive appropriate treatment and rehabilitation strategies. However, online detection of gait events can be challenging because each person has their own walking patterns and speeds. This paper applies recurrent neural networks (RNNs) to develop a model that can instantly detect important gait events in any subject. We collected clinical gait data and used them to develop an RNN model for real-time detection of HS. The model correctly recognized HS events with an average success rate of 98.84% and an average delay of 0.024 s in the laboratory environment. We then applied the model to three different groups of subjects: healthy elderly subjects, stroke patients, and patients with Parkinson's disease. The developed RNN model also correctly recognized HS events in all three groups with an average accuracy of more than 99.65%, even though the subjects had very different walking patterns. In the future, the developed gait detection model can be integrated with real-time rehabilitation systems to provide patients with repetitive guidance using clinician-determined cures for enhanced clinical gait training.
引用
收藏
页码:134849 / 134857
页数:9
相关论文
共 50 条
  • [1] Abnormal Gait Recognition in Real-Time using Recurrent Neural Networks
    Jinnovart, Thanaporn
    C, Xiongcai
    Thonglek, Kundjanasith
    [J]. 2020 59TH IEEE CONFERENCE ON DECISION AND CONTROL (CDC), 2020, : 972 - 977
  • [2] Intelligent Real-Time Earthquake Detection by Recurrent Neural Networks
    Chin, Tai-Lin
    Chen, Kuan-Yu
    Chen, Da-Yi
    Lin, De-En
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2020, 58 (08): : 5440 - 5449
  • [3] Embedding Recurrent Neural Networks in Wearable Systems for Real-Time Fall Detection
    Torti, Emanuele
    Fontanella, Alessandro
    Musci, Mirto
    Blago, Nicola
    Pau, Danilo
    Leporati, Francesco
    Piastra, Marco
    [J]. MICROPROCESSORS AND MICROSYSTEMS, 2019, 71
  • [4] Automatic real-time gait event detection in children using deep neural networks
    Kidzinski, Lukasz
    Delp, Scott
    Schwartz, Michael
    [J]. PLOS ONE, 2019, 14 (01):
  • [5] Road surface real-time detection based on Raspberry Pi and recurrent neural networks
    Wang, Junyi
    Meng, Qinggang
    Shang, Peng
    Saada, Mohamad
    [J]. TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL, 2021, 43 (11) : 2540 - 2550
  • [6] Recurrent Neural Networks for real-time distributed collaborative prognostics
    Palau, Adria Salvador
    Bakliwal, Kshitij
    Dhada, Maharshi Harshadbhai
    Pearce, Tim
    Parlikad, Ajith Kumar
    [J]. 2018 IEEE INTERNATIONAL CONFERENCE ON PROGNOSTICS AND HEALTH MANAGEMENT (ICPHM), 2018,
  • [7] Recurrent Neural Networks for Stochastic Control in Real-Time Bidding
    Grislain, Nicolas
    Perrin, Nicolas
    Thabault, Antoine
    [J]. KDD'19: PROCEEDINGS OF THE 25TH ACM SIGKDD INTERNATIONAL CONFERENCCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2019, : 2801 - 2809
  • [8] A REAL-TIME LEARNING ALGORITHM FOR RECURRENT ANALOG NEURAL NETWORKS
    SATO, M
    [J]. BIOLOGICAL CYBERNETICS, 1990, 62 (03) : 237 - 241
  • [9] Real-time computation at the edge of chaos in recurrent neural networks
    Bertschinger, N
    Natschläger, T
    [J]. NEURAL COMPUTATION, 2004, 16 (07) : 1413 - 1436
  • [10] Real-Time Motor Control using Recurrent Neural Networks
    Huh, Dongsung
    Todorov, Emanuel
    [J]. ADPRL: 2009 IEEE SYMPOSIUM ON ADAPTIVE DYNAMIC PROGRAMMING AND REINFORCEMENT LEARNING, 2009, : 42 - 49