Multi-Feature Gait Pattern Recognition Based on Fisher Discriminant and GKF-RELM Algorithm

被引：0
作者：
Li Y.-D. [1 ,2 ]
Gao F.-R. [1 ]
Yao T. [1 ]
Cai L.-J. [1 ]
机构：
[1] School of Automation, Hangzhou Dianzi University, Hangzhou
[2] Beijing Jingdong Dry Stone Technology Co. Ltd, Beijing
来源：
Tien Tzu Hsueh Pao/Acta Electronica Sinica | 2021年 / 49卷 / 10期
关键词：
Deep neural network (DNN); Fisher discriminant analysis; Gait recognition; GKF-RELM algorithm; Multi-feature fusion;
D O I：
10.12263/DZXB.20200033
中图分类号：
学科分类号：
摘要：
To improve the recognition accuracy and computational efficiency of gait recognition for lower extremity surface electromyography (sEMG), the Gaussian kernel function-regularized extreme learning machine (GKF-RELM) algorithm is presented. The features of time domain, frequency domain and non-linear dynamics via sEMG signals are extracted and the corresponding gait recognition rates are calculated, respectively. Fisher discriminant function is utilized to analyze the separability of the proposed features, and the fusion features of multi-class features are obtained as the input data to train the classifiers, and the trained classifier is used for gait recognition. The recognition rate and calculation time are compared with support vector machine (SVM) and deep neural network (DNN). The results show that the combination of multi-class features based on Fisher discriminant separability index can obtain the optimal recognition effects, and improve the classification accuracy, as well as optimize the calculation efficiency. In addition, the recognition rate of GKF-RELM method is preferable to that of traditional ELM method. © 2021, Chinese Institute of Electronics. All right reserved.
引用
收藏
页码：1993 / 2001
页数：8
相关论文
共 34 条
  • [1] Mei C, Gao F R, Li Y., A determination method for gait event based on acceleration sensors, Sensors, 19, 24, (2019)
  • [2] Shi P, Zhang Q Z, Zhang H P, Et al., Static balance capability assessment of multivariate multiscale entropy based on multivariate empirical mode decomposition, Acta Electronica Sinica, 48, 4, pp. 670-674, (2020)
  • [3] Ryu J, Lee B H, Kim D H., sEMG signal-based lower limb human motion detection using a top and slope feature extraction algorithm, IEEE Signal Processing Letters, 24, 7, pp. 929-932, (2017)
  • [4] Connor P, Ross A., Biometric recognition by gait: A survey of modalities and features, Computer Vision and Image Understanding, 167, pp. 1-27, (2018)
  • [5] Zhang X F, Sun S Q, Li C, Et al., Impact of load variation on the accuracy of gait recognition from surface EMG signals, Applied Sciences, 8, 9, pp. 1462-1476, (2018)
  • [6] Phinyomark A, Phukpattaranont P, Limsakul C., Feature reduction and selection for EMG signal classification, Expert Systems With Applications, 39, 8, pp. 7420-7431, (2012)
  • [7] Mu Y G, Peng C L, Zheng X L, Et al., Time-frequency analysis of surface myoelectric signals during dynamic contractions, Acta Biophysica Sinica, 20, 4, pp. 323-328, (2004)
  • [8] Too J, Abdullah A R, Zawawi T N, Et al., Classification of EMG signal based on time domain and frequency domain features, International Journal of Human and Technology Interaction, 1, 1, pp. 25-29, (2017)
  • [9] Xie P, Wei X L, Du Y H, Et al., Feature extraction method of sEMG based on auto permutation entropy, Pattern Recognition and Artificial Intelligence, 27, 6, pp. 496-501, (2014)
  • [10] Cheng J, Chen X, Peng H., An onset detection method for action surface electromyography based on sample entropy, Acta Electronica Sinica, 44, 2, pp. 479-484, (2016)
1234