Fusion from Multimodal Gait Spatiotemporal Data for Human Gait Speed Classifications

Abdullah S. Alharthi, Krikor B. Ozanyan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Human gait pattens remain largely undefined when relying on a single sensing modality. We report a pilot implementation of sensor fusion to classify gait spatiotemporal signals, from a publicly available dataset of 50 participants, harvested from four different type of sensors. For fusion we propose a hybrid Convolutional Neural Network and Long Short-Term Memory (hybrid CNN+LSTM) and Multi-stream CNN. The classification results are compared to single modality data using Single-stream CNN, a state-of-the-art Vision Transformer, and statistical classifiers algorithms. The fusion models outperformed the single modality methods and classified gait speed of previously unseen 10 random subjects with 97% F1-score prediction accuracy of the four gait speed classes.

Original languageEnglish (US)
Title of host publication2021 IEEE Sensors, SENSORS 2021 - Conference Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728195018
DOIs
StatePublished - 2021
Event20th IEEE Sensors, SENSORS 2021 - Virtual, Online, Australia
Duration: Oct 31 2021Nov 4 2021

Publication series

NameProceedings of IEEE Sensors
Volume2021-October
ISSN (Print)1930-0395
ISSN (Electronic)2168-9229

Conference

Conference20th IEEE Sensors, SENSORS 2021
Country/TerritoryAustralia
CityVirtual, Online
Period10/31/2111/4/21

Keywords

  • Deep Convolutional Neural Networks (CNN)
  • Gait Speed
  • Long Short-Term Memory (LSTM)
  • Multimodal Data
  • Transformers

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Fusion from Multimodal Gait Spatiotemporal Data for Human Gait Speed Classifications'. Together they form a unique fingerprint.

Cite this