A novel method of non-stationary sEMG signal analysis and decomposition using a latent process model

To solve the problems of conventional signal analysis methods about non-stationary and frequency characteristics of surface electromyogrphy (sEMG) is of great significance to rehabilitation robot control with EMG-based human-computer interfaces (HCI). In this paper, the latent process models of sEMG signals were developed based on the combination of time-varying auto-regression (TVAR) model and dynamic linear model (DLM), which decomposed the signals into several components, and each component represents different time-frequency behavior of sEMG signals. On the basis of the latent process model, time-varying parameters, modulus and wavelength features were extracted. The fusing features of sEMG signals in two elbow movement conditions (elbow flexion and elbow extension) were adopted for clustering analysis and classification of data was visualized by using self-organizing map (SOM). An experiment with 9 healthy participants was carried out to verify the validity of this algorithm. The result implied that latent process model is a meaningful and valuable non-stationary sEMG signal analysis method which may be promising in rehabilitation robot control.

[1]  Gabriella Olmo,et al.  Analysis of EMG signals by means of the matched wavelet transform , 1997 .

[2]  Toshio Tsuji,et al.  EMG-based human-robot interface for rehabilitation aid , 1998, Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146).

[3]  P.A. Karjalainen,et al.  Estimation of event-related synchronization changes by a new TVAR method , 1997, IEEE Transactions on Biomedical Engineering.

[4]  Michael A. West,et al.  Evaluation and Comparison of EEG Traces: Latent Structure in Nonstationary Time Series , 1999 .

[5]  W. Marsden.  I and J , 2012 .

[6]  Marco Pirini,et al.  The ABC of EMG , 2014 .

[7]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[8]  Anthony L Bertapelle.  Spectral Analysis of Time Series. , 1979 .

[9]  M. West,et al.  Dynamic Generalized Linear Models and Bayesian Forecasting: Rejoinder , 1985 .

[10]  F. Mohd-Yasin,et al.  Techniques of EMG signal analysis: detection, processing, classification and applications , 2006, Biological Procedures Online.

[11]  R. Scott,et al.  The short-time Fourier transform and muscle fatigue assessment in dynamic contractions. , 2001, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[12]  D. T. Lee,et al.  A study of neuromuscular-like control in rehabilitation robot , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[13]  Othman Omran Khalifa,et al.  EMG signal classification for human computer interaction: a review , 2009 .

[14]  Maarten J. IJzerman,et al.  Systematic review of the effect of robot-aided therapy on recovery of the hemiparetic arm after stroke. , 2006, Journal of rehabilitation research and development.

[15]  P. Brown.  Cortical drives to human muscle: the Piper and related rhythms , 2000, Progress in Neurobiology.

[16]  Timothy G. Gregoire,et al.  Modelling Longitudinal and Spatially Correlated Data , 1997 .

[17]  Georges De Moor,et al.  Correlations between short-time Fourier- and continuous wavelet transforms in the analysis of localized back and hip muscle fatigue during isometric contractions. , 2008, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[18]  D. Gravel,et al.  Normality and stationarity of EMG signals of elbow flexor muscles during ramp and step isometric contractions. , 1997, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[19]  Esa Alhoniemi,et al.  Self-organizing map in Matlab: the SOM Toolbox , 1999 .

[20]  Raquel Prado,et al.  Latent Structure In Non-Stationary Time Series , 1998 .

[21]  M. Cassidy,et al.  Hidden Markov based autoregressive analysis of stationary and non-stationary electrophysiological signals for functional coupling studies , 2002, Journal of Neuroscience Methods.

[22]  Raquel Prado,et al.  Multichannel electroencephalographic analyses via dynamic regression models with time‐varying lag–lead structure , 2001 .

[23]  G. Inbar,et al.  Autoregressive Modeling of Surface EMG and Its Spectrum with Application to Fatigue , 1987, IEEE Transactions on Biomedical Engineering.

[24]  D. Halliday,et al.  The frequency content of common synaptic inputs to motoneurones studied during voluntary isometric contraction in man. , 1993, The Journal of physiology.

[25]  Xiaoli Li,et al.  Condition monitoring using a latent process model with an application to sheet metal stamping processes , 2005 .

[26]  Michael A. West,et al.  Exploratory Modelling of Multiple Non-Stationary Time Series: Latent Process Structure and Decompositions , 1997 .

[27]  H. Krebs,et al.  Effects of Robot-Assisted Therapy on Upper Limb Recovery After Stroke: A Systematic Review , 2008, Neurorehabilitation and neural repair.

[28]  Joseph P Weir,et al.  Comparison of Fourier and wavelet transform procedures for examining the mechanomyographic and electromyographic frequency domain responses during fatiguing isokinetic muscle actions of the biceps brachii. , 2005, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[29]  M. West,et al.  Dynamic Generalized Linear Models and Bayesian Forecasting , 1985 .

[30]  M. West,et al.  Time series decomposition , 1997 .

[31]  Mehmet Rahmi Canal,et al.  Comparison of Wavelet and Short Time Fourier Transform Methods in the Analysis of EMG Signals , 2010, Journal of Medical Systems.

[32]  Huosheng Hu,et al.  Myoelectric control systems - A survey , 2007, Biomed. Signal Process. Control..

[33]  Zunaid Kazi,et al.  Multimodal HCI for Robot Control: Towards an Intelligent Robotic Assistant for People with Disabilities , 1996 .

[34]  D Stashuk,et al.  EMG signal decomposition: how can it be accomplished and used? , 2001, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[35]  M. West,et al.  New methods of time series analysis of non-stationary EEG data: eigenstructure decompositions of time varying autoregressions , 1999, Clinical Neurophysiology.

[36]  Dmitriy Melkonian,et al.  High-resolution fragmentary decomposition—a model-based method of non-stationary electrophysiological signal analysis , 2003, Journal of Neuroscience Methods.