Recognition of Walking Activity and Prediction of Gait Periods with a CNN and First-Order MC Strategy

Uriel Martinez-Hernandez; Adrian Rubio-Solis; Abbas A. Dehghani-Sanij

doi:10.1109/BIOROB.2018.8487220

Recognition of Walking Activity and Prediction of Gait Periods with a CNN and First-Order MC Strategy

Uriel Martinez-Hernandez, Adrian Rubio-Solis, Abbas A. Dehghani-Sanij

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

22 Citations (SciVal)

161 Downloads (Pure)

Abstract

In this paper, a strategy for recognition of human walking activities and prediction of gait periods using wearable sensors is presented. First, a Convolutional Neural Network (CNN) is developed for the recognition of three walking activities (level-ground walking, ramp ascent and descent) and recognition of gait periods. Second, a first-order Markov Chain (MC) is employed for the prediction of gait periods, based on the observation of decisions made by the CNN for each walking activity. The validation of the proposed methods is performed using data from three inertial measurement units (IMU) attached to the lower limbs of participants. The results show that the CNN, together with the first-order MC, achieves mean accuracies of 100% and 98.32% for recognition of walking activities and gait periods, respectively. Prediction of gait periods are achieved with mean accuracies of 99.78%, 97.56% and 97.35% during level-ground walking, ramp ascent and descent, respectively. Overall, the benefits of our work for accurate recognition and prediction of walking activity and gait periods, make it a suitable high-level method for the development of intelligent assistive robots.

Original language	English
Title of host publication	BIOROB 2018 - 7th IEEE International Conference on Biomedical Robotics and Biomechatronics
Publisher	IEEE
Pages	897-902
Number of pages	6
Volume	2018-August
ISBN (Electronic)	9781538681831
DOIs	https://doi.org/10.1109/BIOROB.2018.8487220
Publication status	Published - 11 Oct 2018
Event	7th IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics, BIOROB 2018 - Enschede, Netherlands Duration: 26 Aug 2018 → 29 Aug 2018

Publication series

Name	International Conference on Biomedical Robotics and Biomechatronics (BIOROB)
Publisher	IEEE
Volume	7
ISSN (Print)	2155-1774
ISSN (Electronic)	2155-1782

Conference

Conference	7th IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics, BIOROB 2018
Country/Territory	Netherlands
City	Enschede
Period	26/08/18 → 29/08/18

Funding

This work was supported by the EPSRC for the project ‘Wearable soft robotics for independent living’ (EP/M026388/1).

ASJC Scopus subject areas

Artificial Intelligence
Biomedical Engineering
Mechanical Engineering

Access to Document

10.1109/BIOROB.2018.8487220

BioRob_2018_Uriel
(C) 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
Accepted author manuscript, 1.89 MB

Cite this

Martinez-Hernandez, U., Rubio-Solis, A., & Dehghani-Sanij, A. A. (2018). Recognition of Walking Activity and Prediction of Gait Periods with a CNN and First-Order MC Strategy. In BIOROB 2018 - 7th IEEE International Conference on Biomedical Robotics and Biomechatronics (Vol. 2018-August, pp. 897-902). Article 8487220 (International Conference on Biomedical Robotics and Biomechatronics (BIOROB); Vol. 7). IEEE. https://doi.org/10.1109/BIOROB.2018.8487220

Recognition of Walking Activity and Prediction of Gait Periods with a CNN and First-Order MC Strategy. / Martinez-Hernandez, Uriel; Rubio-Solis, Adrian; Dehghani-Sanij, Abbas A.
BIOROB 2018 - 7th IEEE International Conference on Biomedical Robotics and Biomechatronics. Vol. 2018-August IEEE, 2018. p. 897-902 8487220 (International Conference on Biomedical Robotics and Biomechatronics (BIOROB); Vol. 7).

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

Martinez-Hernandez, U, Rubio-Solis, A & Dehghani-Sanij, AA 2018, Recognition of Walking Activity and Prediction of Gait Periods with a CNN and First-Order MC Strategy. in BIOROB 2018 - 7th IEEE International Conference on Biomedical Robotics and Biomechatronics. vol. 2018-August, 8487220, International Conference on Biomedical Robotics and Biomechatronics (BIOROB), vol. 7, IEEE, pp. 897-902, 7th IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics, BIOROB 2018, Enschede, Netherlands, 26/08/18. https://doi.org/10.1109/BIOROB.2018.8487220

Martinez-Hernandez U, Rubio-Solis A, Dehghani-Sanij AA. Recognition of Walking Activity and Prediction of Gait Periods with a CNN and First-Order MC Strategy. In BIOROB 2018 - 7th IEEE International Conference on Biomedical Robotics and Biomechatronics. Vol. 2018-August. IEEE. 2018. p. 897-902. 8487220. (International Conference on Biomedical Robotics and Biomechatronics (BIOROB)). doi: 10.1109/BIOROB.2018.8487220

Martinez-Hernandez, Uriel ; Rubio-Solis, Adrian ; Dehghani-Sanij, Abbas A. / Recognition of Walking Activity and Prediction of Gait Periods with a CNN and First-Order MC Strategy. BIOROB 2018 - 7th IEEE International Conference on Biomedical Robotics and Biomechatronics. Vol. 2018-August IEEE, 2018. pp. 897-902 (International Conference on Biomedical Robotics and Biomechatronics (BIOROB)).

@inproceedings{cf0e388a1e084df28df713a654f97c54,

title = "Recognition of Walking Activity and Prediction of Gait Periods with a CNN and First-Order MC Strategy",

abstract = "In this paper, a strategy for recognition of human walking activities and prediction of gait periods using wearable sensors is presented. First, a Convolutional Neural Network (CNN) is developed for the recognition of three walking activities (level-ground walking, ramp ascent and descent) and recognition of gait periods. Second, a first-order Markov Chain (MC) is employed for the prediction of gait periods, based on the observation of decisions made by the CNN for each walking activity. The validation of the proposed methods is performed using data from three inertial measurement units (IMU) attached to the lower limbs of participants. The results show that the CNN, together with the first-order MC, achieves mean accuracies of 100% and 98.32% for recognition of walking activities and gait periods, respectively. Prediction of gait periods are achieved with mean accuracies of 99.78%, 97.56% and 97.35% during level-ground walking, ramp ascent and descent, respectively. Overall, the benefits of our work for accurate recognition and prediction of walking activity and gait periods, make it a suitable high-level method for the development of intelligent assistive robots.",

author = "Uriel Martinez-Hernandez and Adrian Rubio-Solis and Dehghani-Sanij, {Abbas A.}",

year = "2018",

month = oct,

day = "11",

doi = "10.1109/BIOROB.2018.8487220",

language = "English",

volume = "2018-August",

series = "International Conference on Biomedical Robotics and Biomechatronics (BIOROB)",

publisher = "IEEE",

pages = "897--902",

booktitle = "BIOROB 2018 - 7th IEEE International Conference on Biomedical Robotics and Biomechatronics",

address = "USA United States",

note = "7th IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics, BIOROB 2018 ; Conference date: 26-08-2018 Through 29-08-2018",

}

TY - GEN

T1 - Recognition of Walking Activity and Prediction of Gait Periods with a CNN and First-Order MC Strategy

AU - Martinez-Hernandez, Uriel

AU - Rubio-Solis, Adrian

AU - Dehghani-Sanij, Abbas A.

PY - 2018/10/11

Y1 - 2018/10/11

N2 - In this paper, a strategy for recognition of human walking activities and prediction of gait periods using wearable sensors is presented. First, a Convolutional Neural Network (CNN) is developed for the recognition of three walking activities (level-ground walking, ramp ascent and descent) and recognition of gait periods. Second, a first-order Markov Chain (MC) is employed for the prediction of gait periods, based on the observation of decisions made by the CNN for each walking activity. The validation of the proposed methods is performed using data from three inertial measurement units (IMU) attached to the lower limbs of participants. The results show that the CNN, together with the first-order MC, achieves mean accuracies of 100% and 98.32% for recognition of walking activities and gait periods, respectively. Prediction of gait periods are achieved with mean accuracies of 99.78%, 97.56% and 97.35% during level-ground walking, ramp ascent and descent, respectively. Overall, the benefits of our work for accurate recognition and prediction of walking activity and gait periods, make it a suitable high-level method for the development of intelligent assistive robots.

AB - In this paper, a strategy for recognition of human walking activities and prediction of gait periods using wearable sensors is presented. First, a Convolutional Neural Network (CNN) is developed for the recognition of three walking activities (level-ground walking, ramp ascent and descent) and recognition of gait periods. Second, a first-order Markov Chain (MC) is employed for the prediction of gait periods, based on the observation of decisions made by the CNN for each walking activity. The validation of the proposed methods is performed using data from three inertial measurement units (IMU) attached to the lower limbs of participants. The results show that the CNN, together with the first-order MC, achieves mean accuracies of 100% and 98.32% for recognition of walking activities and gait periods, respectively. Prediction of gait periods are achieved with mean accuracies of 99.78%, 97.56% and 97.35% during level-ground walking, ramp ascent and descent, respectively. Overall, the benefits of our work for accurate recognition and prediction of walking activity and gait periods, make it a suitable high-level method for the development of intelligent assistive robots.

UR - http://www.scopus.com/inward/record.url?scp=85056585701&partnerID=8YFLogxK

U2 - 10.1109/BIOROB.2018.8487220

DO - 10.1109/BIOROB.2018.8487220

M3 - Chapter in a published conference proceeding

AN - SCOPUS:85056585701

VL - 2018-August

T3 - International Conference on Biomedical Robotics and Biomechatronics (BIOROB)

SP - 897

EP - 902

BT - BIOROB 2018 - 7th IEEE International Conference on Biomedical Robotics and Biomechatronics

PB - IEEE

T2 - 7th IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics, BIOROB 2018

Y2 - 26 August 2018 through 29 August 2018

ER -

Recognition of Walking Activity and Prediction of Gait Periods with a CNN and First-Order MC Strategy

Abstract

Publication series

Conference

Funding

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this