Publication Details

Robust and Adaptive Terrain Classification and Gait Event Detection System

SHAIKH Qamar Usman, SHAHZAIB Muhammad, SHAKIL Sadia, BHATTI A. Farrukh and MALIK Aamir Saeed. Robust and Adaptive Terrain Classification and Gait Event Detection System. Heliyon, vol. 9, no. 11, 2023, pp. 1-12. ISSN 2405-8440. Available from: https://www.sciencedirect.com/science/article/pii/S2405844023089284
Czech title
Robustní a adaptivní klasifikace terénu a systém detekce chůze
Type
journal article
Language
english
Authors
Shaikh Qamar Usman ()
Shahzaib Muhammad ()
Shakil Sadia, Ph.D. (DCSY FIT BUT)
Bhatti A. Farrukh ()
Malik Aamir Saeed, Ph.D. (DCSY FIT BUT)
URL
Keywords

Gait event detection (GED), terrain classification, adaptive.

Abstract

Real-time gait event detection (GED) system can be utilized for gait analysis and tracking fitness activities. GED for various types of terrains (e.g., stair-walk, uneven surfaces, etc.) is still an open research problem. This study presents an inertial sensor-based approach for real-time GED system that works for diverse terrains in an uncontrolled environment. The GED system classifies three types of terrains, i.e., flat-walk, stair-ascend and stair-descend, with an average classification accuracy of 99%. It also accurately detects various gait events, including, toe-strike, heel-rise, toe-off, and heel-strike. It is computationally efficient, implemented on a low-cost microcontroller, works in real-time and can be used in portable rehabilitation devices for use in dynamic environments.

Published
2023
Pages
1-12
Journal
Heliyon, vol. 9, no. 11, ISSN 2405-8440
Publisher
Elsevier Science
DOI
BibTeX
@ARTICLE{FITPUB12872,
   author = "Usman Qamar Shaikh and Muhammad Shahzaib and Sadia Shakil and Farrukh A. Bhatti and Saeed Aamir Malik",
   title = "Robust and Adaptive Terrain Classification and Gait Event Detection System",
   pages = "1--12",
   journal = "Heliyon",
   volume = 9,
   number = 11,
   year = 2023,
   ISSN = "2405-8440",
   doi = "10.1016/j.heliyon.2023.e21720",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/12872"
}
Back to top