Evaluation of sEMG-Based Feature Extraction and Effective Classification Method for Gait Phase Detection

Fang Peng, Wei Peng, Cheng Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Gait phase detection is an essential procedure for amputated person with an artificial leg to walk naturally. However, a high-performance gait phase detection system is challenging due to (1) the complexity of surface electromyography (sEMG) and redundancy among the numerous features; (2) a robust recognition algorithm which can satisfy the real-time and high accuracy requirement of the system. This paper presents a gait phase detection method based on feature selection and ensemble learning. Four kinds of features extraction methods of sEMG, including time, frequency, time/frequency domain and entropy, are quantitatively analyzed by statistical analysis and calculation complexity to select the best features set. Furthermore, a multiclass classifier using Light Gradient Boosting Machine (LightGBM) is first introduced in gait recognition for discriminating six different gait phases with an average accuracy (94.1%) in a reasonable calculation time (85 ms), and the average accuracy is 5%, which is better than the traditional multiple classifiers decision fusion model. The proposed robust algorithm can effectively reduce the effect of speed on the result, which make it a perfect choice for gait phase detection.

Original languageEnglish
Title of host publicationCognitive Systems and Signal Processing - 4th International Conference, ICCSIP 2018, Revised Selected Papers
EditorsDewen Hu, Fuchun Sun, Huaping Liu
PublisherSpringer-Verlag
Pages138-149
Number of pages12
ISBN (Print)9789811379857
DOIs
Publication statusPublished - 2019 Jan 1
Event4th International Conference on Cognitive Systems and Information Processing, ICCSIP 2018 - Beijing, China
Duration: 2018 Nov 292018 Dec 1

Publication series

NameCommunications in Computer and Information Science
Volume1006
ISSN (Print)1865-0929

Conference

Conference4th International Conference on Cognitive Systems and Information Processing, ICCSIP 2018
CountryChina
CityBeijing
Period18/11/2918/12/1

Fingerprint

Electromyography
Gait
Feature Extraction
Feature extraction
Classifiers
Evaluation
Robust Algorithm
Redundancy
Statistical methods
Entropy
Fusion reactions
Classifier Fusion
Gait Recognition
Decision Fusion
Multiple Classifiers
Ensemble Learning
Recognition Algorithm
Multi-class
Boosting
Walk

Keywords

  • Classifier
  • Features extraction
  • Gait phase detection
  • LightGBM
  • sEMG

ASJC Scopus subject areas

  • Computer Science(all)
  • Mathematics(all)

Cite this

Peng, F., Peng, W., & Zhang, C. (2019). Evaluation of sEMG-Based Feature Extraction and Effective Classification Method for Gait Phase Detection. In D. Hu, F. Sun, & H. Liu (Eds.), Cognitive Systems and Signal Processing - 4th International Conference, ICCSIP 2018, Revised Selected Papers (pp. 138-149). (Communications in Computer and Information Science; Vol. 1006). Springer-Verlag. https://doi.org/10.1007/978-981-13-7986-4_13

Evaluation of sEMG-Based Feature Extraction and Effective Classification Method for Gait Phase Detection. / Peng, Fang; Peng, Wei; Zhang, Cheng.

Cognitive Systems and Signal Processing - 4th International Conference, ICCSIP 2018, Revised Selected Papers. ed. / Dewen Hu; Fuchun Sun; Huaping Liu. Springer-Verlag, 2019. p. 138-149 (Communications in Computer and Information Science; Vol. 1006).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Peng, F, Peng, W & Zhang, C 2019, Evaluation of sEMG-Based Feature Extraction and Effective Classification Method for Gait Phase Detection. in D Hu, F Sun & H Liu (eds), Cognitive Systems and Signal Processing - 4th International Conference, ICCSIP 2018, Revised Selected Papers. Communications in Computer and Information Science, vol. 1006, Springer-Verlag, pp. 138-149, 4th International Conference on Cognitive Systems and Information Processing, ICCSIP 2018, Beijing, China, 18/11/29. https://doi.org/10.1007/978-981-13-7986-4_13
Peng F, Peng W, Zhang C. Evaluation of sEMG-Based Feature Extraction and Effective Classification Method for Gait Phase Detection. In Hu D, Sun F, Liu H, editors, Cognitive Systems and Signal Processing - 4th International Conference, ICCSIP 2018, Revised Selected Papers. Springer-Verlag. 2019. p. 138-149. (Communications in Computer and Information Science). https://doi.org/10.1007/978-981-13-7986-4_13
Peng, Fang ; Peng, Wei ; Zhang, Cheng. / Evaluation of sEMG-Based Feature Extraction and Effective Classification Method for Gait Phase Detection. Cognitive Systems and Signal Processing - 4th International Conference, ICCSIP 2018, Revised Selected Papers. editor / Dewen Hu ; Fuchun Sun ; Huaping Liu. Springer-Verlag, 2019. pp. 138-149 (Communications in Computer and Information Science).
@inproceedings{f9e52c4291c74925b54b69d73bdf23de,
title = "Evaluation of sEMG-Based Feature Extraction and Effective Classification Method for Gait Phase Detection",
abstract = "Gait phase detection is an essential procedure for amputated person with an artificial leg to walk naturally. However, a high-performance gait phase detection system is challenging due to (1) the complexity of surface electromyography (sEMG) and redundancy among the numerous features; (2) a robust recognition algorithm which can satisfy the real-time and high accuracy requirement of the system. This paper presents a gait phase detection method based on feature selection and ensemble learning. Four kinds of features extraction methods of sEMG, including time, frequency, time/frequency domain and entropy, are quantitatively analyzed by statistical analysis and calculation complexity to select the best features set. Furthermore, a multiclass classifier using Light Gradient Boosting Machine (LightGBM) is first introduced in gait recognition for discriminating six different gait phases with an average accuracy (94.1{\%}) in a reasonable calculation time (85{\^A} ms), and the average accuracy is 5{\%}, which is better than the traditional multiple classifiers decision fusion model. The proposed robust algorithm can effectively reduce the effect of speed on the result, which make it a perfect choice for gait phase detection.",
keywords = "Classifier, Features extraction, Gait phase detection, LightGBM, sEMG",
author = "Fang Peng and Wei Peng and Cheng Zhang",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/978-981-13-7986-4_13",
language = "English",
isbn = "9789811379857",
series = "Communications in Computer and Information Science",
publisher = "Springer-Verlag",
pages = "138--149",
editor = "Dewen Hu and Fuchun Sun and Huaping Liu",
booktitle = "Cognitive Systems and Signal Processing - 4th International Conference, ICCSIP 2018, Revised Selected Papers",

}

TY - GEN

T1 - Evaluation of sEMG-Based Feature Extraction and Effective Classification Method for Gait Phase Detection

AU - Peng, Fang

AU - Peng, Wei

AU - Zhang, Cheng

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Gait phase detection is an essential procedure for amputated person with an artificial leg to walk naturally. However, a high-performance gait phase detection system is challenging due to (1) the complexity of surface electromyography (sEMG) and redundancy among the numerous features; (2) a robust recognition algorithm which can satisfy the real-time and high accuracy requirement of the system. This paper presents a gait phase detection method based on feature selection and ensemble learning. Four kinds of features extraction methods of sEMG, including time, frequency, time/frequency domain and entropy, are quantitatively analyzed by statistical analysis and calculation complexity to select the best features set. Furthermore, a multiclass classifier using Light Gradient Boosting Machine (LightGBM) is first introduced in gait recognition for discriminating six different gait phases with an average accuracy (94.1%) in a reasonable calculation time (85 ms), and the average accuracy is 5%, which is better than the traditional multiple classifiers decision fusion model. The proposed robust algorithm can effectively reduce the effect of speed on the result, which make it a perfect choice for gait phase detection.

AB - Gait phase detection is an essential procedure for amputated person with an artificial leg to walk naturally. However, a high-performance gait phase detection system is challenging due to (1) the complexity of surface electromyography (sEMG) and redundancy among the numerous features; (2) a robust recognition algorithm which can satisfy the real-time and high accuracy requirement of the system. This paper presents a gait phase detection method based on feature selection and ensemble learning. Four kinds of features extraction methods of sEMG, including time, frequency, time/frequency domain and entropy, are quantitatively analyzed by statistical analysis and calculation complexity to select the best features set. Furthermore, a multiclass classifier using Light Gradient Boosting Machine (LightGBM) is first introduced in gait recognition for discriminating six different gait phases with an average accuracy (94.1%) in a reasonable calculation time (85 ms), and the average accuracy is 5%, which is better than the traditional multiple classifiers decision fusion model. The proposed robust algorithm can effectively reduce the effect of speed on the result, which make it a perfect choice for gait phase detection.

KW - Classifier

KW - Features extraction

KW - Gait phase detection

KW - LightGBM

KW - sEMG

UR - http://www.scopus.com/inward/record.url?scp=85065716656&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065716656&partnerID=8YFLogxK

U2 - 10.1007/978-981-13-7986-4_13

DO - 10.1007/978-981-13-7986-4_13

M3 - Conference contribution

SN - 9789811379857

T3 - Communications in Computer and Information Science

SP - 138

EP - 149

BT - Cognitive Systems and Signal Processing - 4th International Conference, ICCSIP 2018, Revised Selected Papers

A2 - Hu, Dewen

A2 - Sun, Fuchun

A2 - Liu, Huaping

PB - Springer-Verlag

ER -