Title :
A synchronous and multi-domain feature extraction method of EEG and sEMG in power-assist rehabilitation robot
Author :
Yan Song ; Yihao Du ; Xiaoguang Wu ; Xiaoling Chen ; Ping Xie
Author_Institution :
Key Lab. of Meas. Technol. & Instrum. of Hebei Province, Yanshan Univ., Qinhuangdao, China
fDate :
May 31 2014-June 7 2014
Abstract :
To propose a synchronous and multi-domain feature extraction method of electroencephalogram (EEG) and surface electromyogram (sEMG) signals is of great significance to power-assist rehabilitation robot control with humancomputer interface (HCI). In this paper, nonnegative Tucker decomposition which is one model of nonnegative tensor factorization (NTF) is used to fuse two kinds of bioelectricity signals (EEG and sEMG) and extract multi-domain features of EEG and sEMG signals for classification which contain time, frequency, and space domains. In the first step the EEG and sEMG data are transformed into multidimensional information using continuous wavelet transform and the 4-D EEG-sEMG tensor is established. Then the tensor is decomposed into four components (spatial components, spectral components, temporal components and category components) and the core tensor is the feature extracted. The feature after being eliminated and compressed are fed into KNN, LDA and SVM classifiers for pattern recognition, and a comparison is done in single EEG analysis, single sEMG analysis and both EEG and sEMG analysis. An experiment about 10 healthy participants´ upper limb movements was carried out to verify the validity of this algorithm. The result implied that NTF is a meaningful and valuable synchronous and multi-domain feature extraction method which may be promising in power-assist rehabilitation robot control.
Keywords :
control engineering computing; electroencephalography; electromyography; feature extraction; frequency-domain analysis; human computer interaction; matrix decomposition; medical robotics; medical signal processing; patient rehabilitation; pattern classification; signal classification; support vector machines; tensors; time-domain analysis; 4D EEG-sEMG tensor; EEG signal; HCI; KNN classifier; LDA classifier; NTF; SVM classifier; bioelectricity signal; category components; continuous wavelet transform; core tensor; electroencephalogram; frequency domain; human computer interface; multidimensional information; multidomain feature extraction method; nonnegative Tucker decomposition; nonnegative tensor factorization; pattern recognition; power-assist rehabilitation robot control; sEMG signal; single EEG analysis; single sEMG analysis; space domain; spatial components; spectral components; surface electromyogram signal; synchronous feature extraction method; temporal components; time domain; upper limb movements; Elbow; Electroencephalography; Feature extraction; Muscles; Robots; Tensile stress; Time-frequency analysis;
Conference_Titel :
Robotics and Automation (ICRA), 2014 IEEE International Conference on
Conference_Location :
Hong Kong
DOI :
10.1109/ICRA.2014.6907583