Robust and adaptive terrain classification and gait event detection system

Usman Qamar Shaikh; Muhammad Shahzaib; Sadia Shakil; Farrukh A Bhatti; Malik Aamir Saeed

doi:10.1016/j.heliyon.2023.e21720

Robust and adaptive terrain classification and gait event detection system

Heliyon. 2023 Oct 31;9(11):e21720. doi: 10.1016/j.heliyon.2023.e21720. eCollection 2023 Nov.

Authors

Usman Qamar Shaikh^{1

2}, Muhammad Shahzaib², Sadia Shakil^{2

3}, Farrukh A Bhatti⁴, Malik Aamir Saeed⁵

Affiliations

¹ Institute of Biomedical Technologies, Auckland University of Technology, Auckland, New Zealand.
² Biosignal Processing and Computational NeuroScience (BiCoNeS) Lab, Institute of Space Technology, Pakistan.
³ Department of Biomedical Engineering, The Chinese University of Hong Kong, Hong Kong.
⁴ NewVative Technologies (Pvt) Ltd, Islamabad, Pakistan.
⁵ Faculty of Information Technology, Brno University of Technology, Brno, Czech Republic.

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.

Keywords: Adaptive; Gait event detection (GED); Terrain classification.