Research on Lower Limb Motion Recognition Based on Fusion of sEMG and Accelerometer Signals
Since surface electromyograghic (sEMG) signals are non-invasive and capable of reflecting humans’ motion intention, they have been widely used for the motion recognition of upper limbs. However, limited research has been conducted for lower limbs, because the sEMGs of lower limbs are easily affected...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2017-08-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/9/8/147 |
| _version_ | 1817989671556218880 |
|---|---|
| author | Qingsong Ai Yanan Zhang Weili Qi Quan Liu and Kun Chen |
| author_facet | Qingsong Ai Yanan Zhang Weili Qi Quan Liu and Kun Chen |
| author_sort | Qingsong Ai |
| collection | DOAJ |
| description | Since surface electromyograghic (sEMG) signals are non-invasive and capable of reflecting humans’ motion intention, they have been widely used for the motion recognition of upper limbs. However, limited research has been conducted for lower limbs, because the sEMGs of lower limbs are easily affected by body gravity and muscle jitter. In this paper, sEMG signals and accelerometer signals are acquired and fused to recognize the motion patterns of lower limbs. A curve fitting method based on median filtering is proposed to remove accelerometer noise. As for movement onset detection, an sEMG power spectral correlation coefficient method is used to detect the start and end points of active signals. Then, the time-domain features and wavelet coefficients of sEMG signals are extracted, and a dynamic time warping (DTW) distance is used for feature extraction of acceleration signals. At last, five lower limbs’ motions are classified and recognized by using Gaussian kernel-based linear discriminant analysis (LDA) and support vector machine (SVM) respectively. The results prove that the fused feature-based classification outperforms the classification with only sEMG signals or accelerometer signals, and the fused feature can achieve 95% or higher recognition accuracy, demonstrating the validity of the proposed method. |
| first_indexed | 2024-04-14T00:49:32Z |
| format | Article |
| id | doaj.art-284e53b7db5b4af68c1cc9f297da2ad7 |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-04-14T00:49:32Z |
| publishDate | 2017-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-284e53b7db5b4af68c1cc9f297da2ad72022-12-22T02:21:51ZengMDPI AGSymmetry2073-89942017-08-019814710.3390/sym9080147sym9080147Research on Lower Limb Motion Recognition Based on Fusion of sEMG and Accelerometer SignalsQingsong Ai0Yanan Zhang1Weili Qi2Quan Liu3and Kun Chen4School of Information Engineering, Wuhan University of Technology, Wuhan 430070, ChinaSchool of Information Engineering, Wuhan University of Technology, Wuhan 430070, ChinaSchool of Information Engineering, Wuhan University of Technology, Wuhan 430070, ChinaSchool of Information Engineering, Wuhan University of Technology, Wuhan 430070, ChinaSchool of Information Engineering, Wuhan University of Technology, Wuhan 430070, ChinaSince surface electromyograghic (sEMG) signals are non-invasive and capable of reflecting humans’ motion intention, they have been widely used for the motion recognition of upper limbs. However, limited research has been conducted for lower limbs, because the sEMGs of lower limbs are easily affected by body gravity and muscle jitter. In this paper, sEMG signals and accelerometer signals are acquired and fused to recognize the motion patterns of lower limbs. A curve fitting method based on median filtering is proposed to remove accelerometer noise. As for movement onset detection, an sEMG power spectral correlation coefficient method is used to detect the start and end points of active signals. Then, the time-domain features and wavelet coefficients of sEMG signals are extracted, and a dynamic time warping (DTW) distance is used for feature extraction of acceleration signals. At last, five lower limbs’ motions are classified and recognized by using Gaussian kernel-based linear discriminant analysis (LDA) and support vector machine (SVM) respectively. The results prove that the fused feature-based classification outperforms the classification with only sEMG signals or accelerometer signals, and the fused feature can achieve 95% or higher recognition accuracy, demonstrating the validity of the proposed method.https://www.mdpi.com/2073-8994/9/8/147surface electromyograghic (sEMG)accelerometer signalsfeature fusionmotion recognition |
| spellingShingle | Qingsong Ai Yanan Zhang Weili Qi Quan Liu and Kun Chen Research on Lower Limb Motion Recognition Based on Fusion of sEMG and Accelerometer Signals Symmetry surface electromyograghic (sEMG) accelerometer signals feature fusion motion recognition |
| title | Research on Lower Limb Motion Recognition Based on Fusion of sEMG and Accelerometer Signals |
| title_full | Research on Lower Limb Motion Recognition Based on Fusion of sEMG and Accelerometer Signals |
| title_fullStr | Research on Lower Limb Motion Recognition Based on Fusion of sEMG and Accelerometer Signals |
| title_full_unstemmed | Research on Lower Limb Motion Recognition Based on Fusion of sEMG and Accelerometer Signals |
| title_short | Research on Lower Limb Motion Recognition Based on Fusion of sEMG and Accelerometer Signals |
| title_sort | research on lower limb motion recognition based on fusion of semg and accelerometer signals |
| topic | surface electromyograghic (sEMG) accelerometer signals feature fusion motion recognition |
| url | https://www.mdpi.com/2073-8994/9/8/147 |
| work_keys_str_mv | AT qingsongai researchonlowerlimbmotionrecognitionbasedonfusionofsemgandaccelerometersignals AT yananzhang researchonlowerlimbmotionrecognitionbasedonfusionofsemgandaccelerometersignals AT weiliqi researchonlowerlimbmotionrecognitionbasedonfusionofsemgandaccelerometersignals AT quanliu researchonlowerlimbmotionrecognitionbasedonfusionofsemgandaccelerometersignals AT andkunchen researchonlowerlimbmotionrecognitionbasedonfusionofsemgandaccelerometersignals |