Vibration-based terrain classification recognition using a six-axis accelerometer. (December 2021)

• Record Type: Journal Article
• Authors: Liu, Ruijun; Zhang, Bohua; Yu, Zhuo; Han, Zhiyuan; Wu, Jingbang; Wang, Ting
• Is Part Of: Computers & electrical engineering. Volume 96:Part B(2021)
• Publication Date: 2021-12
• Subjects: Vibration -- Terrain classification -- Gabor atomic decomposition -- Time-frequency analysis; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2021.107556
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: Aging is a key problem in our daily life which demands more technology such as the terrain classification recognition for the detailed path planning. In this article, a six-axis accelerometer was placed on the base of a walking stick to capture walking gait vibration information. The signal features in the collected information were used to reflect the terrain. We used a matching tracking method to decompose the signal data into linear combinations of Gabor atoms and a joint time-frequency analysis method to perform analysis on the topographic features in a three-dimensional space. Three types of terrains were classified from space-time data. Results show that the proposed algorithm could achieve an average accuracy rate of 88.6%, which is 4% higher than conventional methods.