Multi-feature gait recognition with DNN based on sEMG signals.

This study proposed a gait recognition method based on the deep neural network of surface electromyography (sEMG) signals to improve the stability and accuracy of gait recognition using sEMG signals of the lower limbs. First, we determined the parameters of time domain features, including the mean of absolute value, root mean square, waveform length, the number of zero-crossing points of the sEMG signals after noise elimination, and the frequency domain features, including mean power frequency and median frequency. Second, the time domain feature and frequency domain feature were combined into a multi-feature combination. Then, the classifier was trained and used for gait recognition. Finally, in terms of the recognition rate, the classifier was compared with the support vector machine (SVM) and extreme learning machine (ELM). The results showed the method of deep neural network (DNN) had a better recognition rate than that of SVM and ELM. The experimental results of the participants indicated that the average recognition rate obtained with the method of DNN exceeded 95%. On the other hand, from the statistical results of standard deviation, the difference between subjects ranged from 0.46 to 0.94%, which also proved the robustness and stability of the proposed method.

[1]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Zhe Wang,et al.  sEMG Based Human Motion Intention Recognition , 2019, J. Robotics.

[3]  Adel Al-Jumaily,et al.  A fusion of time-domain descriptors for improved myoelectric hand control , 2016, 2016 IEEE Symposium Series on Computational Intelligence (SSCI).

[4]  Ying Li,et al.  A Determination Method for Gait Event Based on Acceleration Sensors , 2019, Sensors.

[5]  Byung-Gyu Kim,et al.  Deep Joint Spatiotemporal Network (DJSTN) for Efficient Facial Expression Recognition , 2020, Sensors.

[6]  Huosheng Hu,et al.  PCA and deep learning based myoelectric grasping control of a prosthetic hand , 2018, BioMedical Engineering OnLine.

[7]  Wang Jiaji,et al.  Non-Uniform Characteristics and Its Recognition Effects for Walking Gait Based on sEMG , 2016 .

[8]  Shuang Xu,et al.  Hand motions recognition based on sEMG nonlinear feature and time domain feature fusion , 2019 .

[9]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[10]  Zhizeng Luo,et al.  Evaluation of Feature Extraction and Recognition for Activity Monitoring and Fall Detection Based on Wearable sEMG Sensors , 2017, Sensors.

[11]  J. Richman,et al.  Physiological time-series analysis using approximate entropy and sample entropy. , 2000, American journal of physiology. Heart and circulatory physiology.

[12]  F Felici,et al.  Amplitude and spectral characteristics of biceps Brachii sEMG depend upon speed of isometric force generation. , 2003, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[13]  Byung-Gyu Kim,et al.  Efficient Facial Expression Recognition Algorithm Based on Hierarchical Deep Neural Network Structure , 2019, IEEE Access.

[14]  M. Perc.  The dynamics of human gait , 2005 .

[15]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[16]  Clément Gosselin,et al.  Deep Learning for Electromyographic Hand Gesture Signal Classification Using Transfer Learning , 2018, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[17]  Martin Vetterli,et al.  Adaptive wavelet thresholding for image denoising and compression , 2000, IEEE Trans. Image Process..

[18]  Guodong Guo,et al.  A survey on deep learning based face recognition , 2019, Comput. Vis. Image Underst..

[19]  Yogendra Narayan.  Hb vsEMG signal classification with time domain and Frequency domain features using LDA and ANN classifier , 2020 .

[20]  Bruce C. Wheeler,et al.  EMG feature evaluation for movement control of upper extremity prostheses , 1995 .

[21]  Guang-Bin Huang,et al.  Extreme learning machine: a new learning scheme of feedforward neural networks , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[22]  Qingshan She,et al.  Gait Recognition Based on EMG Information with Multiple Features , 2018, Intelligent Information Processing.

[23]  Maria Lindén,et al.  A Deep Machine Learning Method for Classifying Cyclic Time Series of Biological Signals Using Time-Growing Neural Network , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[24]  J.C. Pereira,et al.  Evaluation of adaptive/nonadaptive filtering and wavelet transform techniques for noise reduction in EMG mobile acquisition equipment , 2003, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[25]  Farong Gao,et al.  Human Gait Recognition Based on Multiple Feature Combination and Parameter Optimization Algorithms , 2021, Comput. Intell. Neurosci..

[26]  Ahmad Reza Naghsh-Nilchi,et al.  Efficient Image Denoising Method Based on a New Adaptive Wavelet Packet Thresholding Function , 2012, IEEE Transactions on Image Processing.

[27]  Olivier Gibaru,et al.  A Review on Electromyography Decoding and Pattern Recognition for Human-Machine Interaction , 2019, IEEE Access.

[28]  Patrick van der Smagt,et al.  Surface EMG in advanced hand prosthetics , 2008, Biological Cybernetics.

[29]  Suman Samui,et al.  An experimental study on upper limb position invariant EMG signal classification based on deep neural network , 2020, Biomed. Signal Process. Control..

[30]  Pornchai Phukpattaranont,et al.  Feature reduction and selection for EMG signal classification , 2012, Expert Syst. Appl..

[31]  Mohammad Hassan Moradi,et al.  Evaluation of the forearm EMG signal features for the control of a prosthetic hand. , 2003, Physiological measurement.

[32]  Angkoon Phinyomark,et al.  EMG feature evaluation for improving myoelectric pattern recognition robustness , 2013, Expert Syst. Appl..

[33]  Huihui Chen,et al.  Angle Estimation for Knee Joint Movement Based on PCA-RELM Algorithm , 2020, Symmetry.

[34]  Arun Ross,et al.  Biometric recognition by gait: A survey of modalities and features , 2018, Comput. Vis. Image Underst..

[35]  Amit M. Joshi,et al.  Portable EMG Data Acquisition Module for Upper Limb Prosthesis Application , 2018, IEEE Sensors Journal.

[36]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[37]  Sandro Fioretti,et al.  A Deep Learning Approach to EMG-Based Classification of Gait Phases during Level Ground Walking , 2019, Electronics.

[38]  Ling Zhang,et al.  Gesture recognition method based on a single-channel sEMG envelope signal , 2018, EURASIP J. Wirel. Commun. Netw..

[39]  Jianfeng Wu,et al.  Extreme learning machine classification method for lower limb movement recognition , 2017, Cluster Computing.

[40]  Debi Prosad Dogra,et al.  deepGesture: Deep learning-based gesture recognition scheme using motion sensors , 2018, Displays.

[41]  Ravinder Agarwal,et al.  Performance evaluation of various classifiers for predicting knee angle from electromyography signals , 2019, Expert Syst. J. Knowl. Eng..

[42]  Deok-Hwan Kim,et al.  sEMG Signal-Based Lower Limb Human Motion Detection Using a Top and Slope Feature Extraction Algorithm , 2017, IEEE Signal Processing Letters.

[43]  Faruk Ortes,et al.  Comparative evaluation of EMG signal features for myoelectric controlled human arm prosthetics , 2017 .