Lower Limb Motion Recognition Method Based on Improved Wavelet Packet Transform and Unscented Kalman Neural Network

Abstract

Exoskeleton robot is a typical application to assist the motion of lower limbs. To make the lower extremity exoskeleton more flexible, it is necessary to identify various motion intentions of the lower limbs of the human body. Although more sEMG sensors can be used to identify more lower limb motion intention, with the increase in the number of sensors, more and more data need to be processed. In the process of human motion, the collected sEMG signal is easy to be interfered with noise. To improve the practicality of the lower extremity exoskeleton robot, this paper proposed a wavelet packet transform- (WPT-) based sliding window difference average filtering feature extract algorithm and the unscented Kalman neural network (UKFNN) recognition algorithm. We established an sEMG energy feature model, using a sliding window difference average filtering method to suppress noise interference and extracted stable feature values and using UKF filtering to optimize the neural network weights to improve the adaptability and accuracy of the recognition model. In this paper, we collected the sEMG signals of three muscles to identify six lower limb motion intentions. The average accuracy of 94.83% is proposed in this paper. Experiments show that the algorithm improves the accuracy and anti-interference of motion intention recognition of lower limb sEMG signals. The algorithm is superior to the backpropagation neural network (BPNN) recognition algorithm in the lower limb motion intention recognition and proves the effectiveness, novelty, and reliability of the method in this paper.

Motion Recognition Based on Sum of the Squared Errors Distribution

“…As shown in the Table Ⅸ, WTS has higher segmentation rate and more stable segmentation effect. We compare the recognition rate of BPTS with that of other algorithms, such as Average Threshold Crossing (ATC) [77], CNN [78], Deep Forest algorithm (DF) [79], Deep Convolutional Network (DCN) [80], Dynamic Time Warping (DTW) [81], PCA [82] and SVM [83], WPT and unscented Kalman neural network (UKFNN) [84], Hybrid Bidirectional Unidirectional Long Short-Term Memory (HBU-LSTM) [85], and PCA and SVM [13]. Some parameters or structures of other algorithms are configured as shown in Table Ⅹ.…”

A Novel Method for Hand Movement Recognition Based on Wavelet Packet Transform and Principal Component Analysis with Surface Electromyogram

“…Compared with the wavelet packet basis functions of fk8, coif2, db4, and sym3, the wavelet packet basis functions of dmey have advantages in the classifcation of hand movement intentions. Tis can be explained by the research of Shi et al [56]; that is, the waveform of the dmey wavelet is similar to the sEMG signal, and it has strong compactness and fast attenuation performance. For this reason, the dmey wavelet is capable of analyzing the small change information in the sEMG signal, which is benefcial in improving the classifcation performance of hand movements.…”

“…The WPT is a sophisticated decomposition algorithm that can subdivide the high-frequency and low-frequency components of a signal [ 39 , 56 ]. The definition of WPT is as follows.…”

AI‐Enabled Soft Sensing Array for Simultaneous Detection of Muscle Deformation and Mechanomyography for Metaverse Somatosensory Interaction

“…[ 22 ] Therefore, muscle activity measurement is a popular approach for capturing and recognizing human lower‐limb motions without interfering with joint movement. Presently, the standard muscle activity measurement techniques are electromyography (EMG) [ 23 , 24 ] and surface EMG (sEMG) with using noninvasive electrodes, [ 13 , 25 , 26 , 27 ] both of which measure the electrical signals generated by muscle contraction. These two techniques have demonstrated exceptional recognition accuracy for several common lower‐limb motions.…”