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 in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)
50 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 languageEnglish
Title of host publicationBIOROB 2018 - 7th IEEE International Conference on Biomedical Robotics and Biomechatronics
PublisherIEEE
Pages897-902
Number of pages6
Volume2018-August
ISBN (Electronic)9781538681831
DOIs
Publication statusPublished - 9 Oct 2018
Event7th IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics, BIOROB 2018 - Enschede, Netherlands
Duration: 26 Aug 201829 Aug 2018

Conference

Conference7th IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics, BIOROB 2018
CountryNetherlands
CityEnschede
Period26/08/1829/08/18

ASJC Scopus subject areas

  • Artificial Intelligence
  • Biomedical Engineering
  • Mechanical Engineering

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). [8487220] 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.

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

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, 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 https://doi.org/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
@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 = "10",
day = "9",
doi = "10.1109/BIOROB.2018.8487220",
language = "English",
volume = "2018-August",
pages = "897--902",
booktitle = "BIOROB 2018 - 7th IEEE International Conference on Biomedical Robotics and Biomechatronics",
publisher = "IEEE",
address = "USA United States",

}

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 - 2018/10/9

Y1 - 2018/10/9

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 - Conference contribution

VL - 2018-August

SP - 897

EP - 902

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

PB - IEEE

ER -