Gait Phase Detection Based on LSTM-CRF for Stair Ambulation

Haochen Wei; Raymond Kai Yu Tong; Michael Yu Wang; Chao Chen

doi:10.1109/LRA.2023.3303787

Gait Phase Detection Based on LSTM-CRF for Stair Ambulation

Haochen Wei, Raymond Kai Yu Tong, Michael Yu Wang, Chao Chen^*

^*Corresponding author for this work

Research output: Contribution to journal › Journal Article › peer-review

15 Citations (Scopus)

Abstract

It is essential to accurately identify gait phases when active exoskeleton devices assist with the lower limbs. This work focuses on IMU-based phase detection for stair ambulation. In order to enhance the detection sensitivity of phase transition, this work utilises the LSTM-CRF hybrid model. Four IMU sensors attached to the thighs and shanks on both legs were utilised to collect data during trials on ten healthy subjects for stair ascent and descent. The network's performance is evaluated by F1-score, recall (true positive rate), and precision, which are 96.3% on average with a standard deviation (std) of 1.9%, 96.6% on average with an std of 1.6%, and 95.9% on average with an std of 2.7%, respectively.

Original language	English
Pages (from-to)	6029-6035
Number of pages	7
Journal	IEEE Robotics and Automation Letters
Volume	8
Issue number	9
DOIs	https://doi.org/10.1109/LRA.2023.3303787
Publication status	Published - 1 Sept 2023
Externally published	Yes

Bibliographical note

Publisher Copyright:
© 2016 IEEE.

Keywords

Deep learning methods
IMU
gait phase detection
prosthetics and exoskeletons
stair ambulation

Access to Document

10.1109/LRA.2023.3303787

Cite this

@article{41e5f392e4ce47bf9b961cbf76c3082f,

title = "Gait Phase Detection Based on LSTM-CRF for Stair Ambulation",

abstract = "It is essential to accurately identify gait phases when active exoskeleton devices assist with the lower limbs. This work focuses on IMU-based phase detection for stair ambulation. In order to enhance the detection sensitivity of phase transition, this work utilises the LSTM-CRF hybrid model. Four IMU sensors attached to the thighs and shanks on both legs were utilised to collect data during trials on ten healthy subjects for stair ascent and descent. The network's performance is evaluated by F1-score, recall (true positive rate), and precision, which are 96.3\% on average with a standard deviation (std) of 1.9\%, 96.6\% on average with an std of 1.6\%, and 95.9\% on average with an std of 2.7\%, respectively.",

keywords = "Deep learning methods, IMU, gait phase detection, prosthetics and exoskeletons, stair ambulation",

author = "Haochen Wei and Tong, \{Raymond Kai Yu\} and Wang, \{Michael Yu\} and Chao Chen",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.",

year = "2023",

month = sep,

day = "1",

doi = "10.1109/LRA.2023.3303787",

language = "English",

volume = "8",

pages = "6029--6035",

journal = "IEEE Robotics and Automation Letters",

issn = "2377-3766",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "9",

}

TY - JOUR

T1 - Gait Phase Detection Based on LSTM-CRF for Stair Ambulation

AU - Wei, Haochen

AU - Tong, Raymond Kai Yu

AU - Wang, Michael Yu

AU - Chen, Chao

PY - 2023/9/1

Y1 - 2023/9/1

N2 - It is essential to accurately identify gait phases when active exoskeleton devices assist with the lower limbs. This work focuses on IMU-based phase detection for stair ambulation. In order to enhance the detection sensitivity of phase transition, this work utilises the LSTM-CRF hybrid model. Four IMU sensors attached to the thighs and shanks on both legs were utilised to collect data during trials on ten healthy subjects for stair ascent and descent. The network's performance is evaluated by F1-score, recall (true positive rate), and precision, which are 96.3% on average with a standard deviation (std) of 1.9%, 96.6% on average with an std of 1.6%, and 95.9% on average with an std of 2.7%, respectively.

AB - It is essential to accurately identify gait phases when active exoskeleton devices assist with the lower limbs. This work focuses on IMU-based phase detection for stair ambulation. In order to enhance the detection sensitivity of phase transition, this work utilises the LSTM-CRF hybrid model. Four IMU sensors attached to the thighs and shanks on both legs were utilised to collect data during trials on ten healthy subjects for stair ascent and descent. The network's performance is evaluated by F1-score, recall (true positive rate), and precision, which are 96.3% on average with a standard deviation (std) of 1.9%, 96.6% on average with an std of 1.6%, and 95.9% on average with an std of 2.7%, respectively.

KW - Deep learning methods

KW - IMU

KW - gait phase detection

KW - prosthetics and exoskeletons

KW - stair ambulation

UR - https://www.webofscience.com/wos/woscc/full-record/WOS:001049939600003

UR - https://www.scopus.com/pages/publications/85167778471

U2 - 10.1109/LRA.2023.3303787

DO - 10.1109/LRA.2023.3303787

M3 - Journal Article

SN - 2377-3766

VL - 8

SP - 6029

EP - 6035

JO - IEEE Robotics and Automation Letters

JF - IEEE Robotics and Automation Letters

IS - 9

ER -

Gait Phase Detection Based on LSTM-CRF for Stair Ambulation

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this