The classification of movement intention through machine learning models: the identification of significant time-domain EMG features
Electromyography (EMG) signal is one of the extensively utilised biological signals for predicting human motor intention, which is an essential element in human-robot collaboration platforms. Studies on motion intention prediction from EMG signals have often been concentrated on either classificatio...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2021-02-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-379.pdf |
| _version_ | 1819171190254600192 |
|---|---|
| author | Ismail Mohd Khairuddin Shahrul Naim Sidek Anwar P.P. Abdul Majeed Mohd Azraai Mohd Razman Asmarani Ahmad Puzi Hazlina Md Yusof |
| author_facet | Ismail Mohd Khairuddin Shahrul Naim Sidek Anwar P.P. Abdul Majeed Mohd Azraai Mohd Razman Asmarani Ahmad Puzi Hazlina Md Yusof |
| author_sort | Ismail Mohd Khairuddin |
| collection | DOAJ |
| description | Electromyography (EMG) signal is one of the extensively utilised biological signals for predicting human motor intention, which is an essential element in human-robot collaboration platforms. Studies on motion intention prediction from EMG signals have often been concentrated on either classification and regression models of muscle activity. In this study, we leverage the information from the EMG signals, to detect the subject’s intentions in generating motion commands for a robot-assisted upper limb rehabilitation platform. The EMG signals are recorded from ten healthy subjects’ biceps muscle, and the movements of the upper limb evaluated are voluntary elbow flexion and extension along the sagittal plane. The signals are filtered through a fifth-order Butterworth filter. A number of features were extracted from the filtered signals namely waveform length (WL), mean absolute value (MAV), root mean square (RMS), standard deviation (SD), minimum (MIN) and maximum (MAX). Several different classifiers viz. Linear Discriminant Analysis (LDA), Logistic Regression (LR), Decision Tree (DT), Support Vector Machine (SVM) and k-Nearest Neighbour (k-NN) were investigated on its efficacy to accurately classify the pre-intention and intention classes based on the significant features identified (MIN and MAX) via Extremely Randomised Tree feature selection technique. It was observed from the present investigation that the DT classifier yielded an excellent classification with a classification accuracy of 100%, 99% and 99% on training, testing and validation dataset, respectively based on the identified features. The findings of the present investigation are non-trivial towards facilitating the rehabilitation phase of patients based on their actual capability and hence, would eventually yield a more active participation from them. |
| first_indexed | 2024-12-22T19:47:21Z |
| format | Article |
| id | doaj.art-affa24dd2aa14b0c8ecb8bbd75019e2b |
| institution | Directory Open Access Journal |
| issn | 2376-5992 |
| language | English |
| last_indexed | 2024-12-22T19:47:21Z |
| publishDate | 2021-02-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj.art-affa24dd2aa14b0c8ecb8bbd75019e2b2022-12-21T18:14:39ZengPeerJ Inc.PeerJ Computer Science2376-59922021-02-017e37910.7717/peerj-cs.379The classification of movement intention through machine learning models: the identification of significant time-domain EMG featuresIsmail Mohd Khairuddin0Shahrul Naim Sidek1Anwar P.P. Abdul Majeed2Mohd Azraai Mohd Razman3Asmarani Ahmad Puzi4Hazlina Md Yusof5Faculty of Manufacturing & Mechatronics Engineering Technology, Innovative Manufacturing, Mechatronics and Sports Laboratory, Universiti Malaysia Pahang, Pekan, Pahang, MalaysiaDepartment of Mechatronics, Kulliyyah of Engineering, Biomechatronics Research Laboratory, International Islamic University, Gombak, Selangor, MalaysiaFaculty of Manufacturing & Mechatronics Engineering Technology, Innovative Manufacturing, Mechatronics and Sports Laboratory, Universiti Malaysia Pahang, Pekan, Pahang, MalaysiaFaculty of Manufacturing & Mechatronics Engineering Technology, Innovative Manufacturing, Mechatronics and Sports Laboratory, Universiti Malaysia Pahang, Pekan, Pahang, MalaysiaDepartment of Mechatronics, Kulliyyah of Engineering, Biomechatronics Research Laboratory, International Islamic University, Gombak, Selangor, MalaysiaDepartment of Mechatronics, Kulliyyah of Engineering, Biomechatronics Research Laboratory, International Islamic University, Gombak, Selangor, MalaysiaElectromyography (EMG) signal is one of the extensively utilised biological signals for predicting human motor intention, which is an essential element in human-robot collaboration platforms. Studies on motion intention prediction from EMG signals have often been concentrated on either classification and regression models of muscle activity. In this study, we leverage the information from the EMG signals, to detect the subject’s intentions in generating motion commands for a robot-assisted upper limb rehabilitation platform. The EMG signals are recorded from ten healthy subjects’ biceps muscle, and the movements of the upper limb evaluated are voluntary elbow flexion and extension along the sagittal plane. The signals are filtered through a fifth-order Butterworth filter. A number of features were extracted from the filtered signals namely waveform length (WL), mean absolute value (MAV), root mean square (RMS), standard deviation (SD), minimum (MIN) and maximum (MAX). Several different classifiers viz. Linear Discriminant Analysis (LDA), Logistic Regression (LR), Decision Tree (DT), Support Vector Machine (SVM) and k-Nearest Neighbour (k-NN) were investigated on its efficacy to accurately classify the pre-intention and intention classes based on the significant features identified (MIN and MAX) via Extremely Randomised Tree feature selection technique. It was observed from the present investigation that the DT classifier yielded an excellent classification with a classification accuracy of 100%, 99% and 99% on training, testing and validation dataset, respectively based on the identified features. The findings of the present investigation are non-trivial towards facilitating the rehabilitation phase of patients based on their actual capability and hence, would eventually yield a more active participation from them.https://peerj.com/articles/cs-379.pdfEMGMachine learningFeature extractionMovement intentionClassification |
| spellingShingle | Ismail Mohd Khairuddin Shahrul Naim Sidek Anwar P.P. Abdul Majeed Mohd Azraai Mohd Razman Asmarani Ahmad Puzi Hazlina Md Yusof The classification of movement intention through machine learning models: the identification of significant time-domain EMG features PeerJ Computer Science EMG Machine learning Feature extraction Movement intention Classification |
| title | The classification of movement intention through machine learning models: the identification of significant time-domain EMG features |
| title_full | The classification of movement intention through machine learning models: the identification of significant time-domain EMG features |
| title_fullStr | The classification of movement intention through machine learning models: the identification of significant time-domain EMG features |
| title_full_unstemmed | The classification of movement intention through machine learning models: the identification of significant time-domain EMG features |
| title_short | The classification of movement intention through machine learning models: the identification of significant time-domain EMG features |
| title_sort | classification of movement intention through machine learning models the identification of significant time domain emg features |
| topic | EMG Machine learning Feature extraction Movement intention Classification |
| url | https://peerj.com/articles/cs-379.pdf |
| work_keys_str_mv | AT ismailmohdkhairuddin theclassificationofmovementintentionthroughmachinelearningmodelstheidentificationofsignificanttimedomainemgfeatures AT shahrulnaimsidek theclassificationofmovementintentionthroughmachinelearningmodelstheidentificationofsignificanttimedomainemgfeatures AT anwarppabdulmajeed theclassificationofmovementintentionthroughmachinelearningmodelstheidentificationofsignificanttimedomainemgfeatures AT mohdazraaimohdrazman theclassificationofmovementintentionthroughmachinelearningmodelstheidentificationofsignificanttimedomainemgfeatures AT asmaraniahmadpuzi theclassificationofmovementintentionthroughmachinelearningmodelstheidentificationofsignificanttimedomainemgfeatures AT hazlinamdyusof theclassificationofmovementintentionthroughmachinelearningmodelstheidentificationofsignificanttimedomainemgfeatures AT ismailmohdkhairuddin classificationofmovementintentionthroughmachinelearningmodelstheidentificationofsignificanttimedomainemgfeatures AT shahrulnaimsidek classificationofmovementintentionthroughmachinelearningmodelstheidentificationofsignificanttimedomainemgfeatures AT anwarppabdulmajeed classificationofmovementintentionthroughmachinelearningmodelstheidentificationofsignificanttimedomainemgfeatures AT mohdazraaimohdrazman classificationofmovementintentionthroughmachinelearningmodelstheidentificationofsignificanttimedomainemgfeatures AT asmaraniahmadpuzi classificationofmovementintentionthroughmachinelearningmodelstheidentificationofsignificanttimedomainemgfeatures AT hazlinamdyusof classificationofmovementintentionthroughmachinelearningmodelstheidentificationofsignificanttimedomainemgfeatures |