Next Article in Journal
Evaluating State-of-the-Art LEED-NCv4 in the U.S.
Next Article in Special Issue
Identification of Epileptic EEG Signals Using Convolutional Neural Networks
Previous Article in Journal
High Performance Self-Compacting Concrete with Electric Arc Furnace Slag Aggregate and Cupola Slag Powder
Previous Article in Special Issue
Bag-of-Visual-Words for Cattle Identification from Muzzle Print Images
Article

Gait Recognition via Deep Learning of the Center-of-Pressure Trajectory

1
Haute-Ecole Arc Santé, HES-SO University of Applied Sciences and Arts Western Switzerland, 2000 Neuchâtel, Switzerland
2
Department of Thoracic and Endocrine Surgery, University Hospitals of Geneva, 1205 Geneva, Switzerland
Appl. Sci. 2020, 10(3), 774; https://doi.org/10.3390/app10030774
Received: 3 December 2019 / Revised: 8 January 2020 / Accepted: 20 January 2020 / Published: 22 January 2020
(This article belongs to the Special Issue Deep Learning-Based Biometric Recognition)
The fact that every human has a distinctive walking style has prompted a proposal to use gait recognition as an identification criterion. Using end-to-end learning, I investigated whether the center-of-pressure (COP) trajectory is sufficiently unique to identify a person with high certainty. Thirty-six adults walked for 30 min on a treadmill equipped with a force platform that continuously recorded the positions of the COP. The raw two-dimensional signals were sliced into segments of two gait cycles. A set of 20,250 segments from 30 subjects was used to configure and train convolutional neural networks (CNNs). The best CNN classified a separate set containing 2250 segments with an overall accuracy of 99.9%. A second set of 4500 segments from the six remaining subjects was then used for transfer learning. Several small subsamples of this set were selected randomly and used to fine tune the pretrained CNNs. Training with two segments per subject was sufficient to achieve 100% accuracy. The results suggest that every person produces a unique trajectory of underfoot pressures while walking and that CNNs can learn the distinctive features of these trajectories. By applying a pretrained CNN (transfer learning), a couple of strides seem enough to learn and identify new gaits. However, these promising results should be confirmed in a larger sample under realistic conditions. View Full-Text
Keywords: biometric recognition; footstep recognition; user verification; force platform; neural networks; machine learning biometric recognition; footstep recognition; user verification; force platform; neural networks; machine learning
Show Figures

Figure 1

MDPI and ACS Style

Terrier, P. Gait Recognition via Deep Learning of the Center-of-Pressure Trajectory. Appl. Sci. 2020, 10, 774. https://doi.org/10.3390/app10030774

AMA Style

Terrier P. Gait Recognition via Deep Learning of the Center-of-Pressure Trajectory. Applied Sciences. 2020; 10(3):774. https://doi.org/10.3390/app10030774

Chicago/Turabian Style

Terrier, Philippe. 2020. "Gait Recognition via Deep Learning of the Center-of-Pressure Trajectory" Appl. Sci. 10, no. 3: 774. https://doi.org/10.3390/app10030774

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop