Open AccessRunning gait pattern recognition based on cross-correlation analysis of single acceleration sensor
Author(s) -
Lingfei Mo,
Lu Zeng
Publication year - 2019
Publication title -
mathematical biosciences and engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.451
H-Index - 45
eISSN - 1551-0018
pISSN - 1547-1063
DOI - 10.3934/mbe.2019311
Subject(s) - gait , forefoot , gait analysis , acceleration , computer science , generalization , simulation , correlation , physical medicine and rehabilitation , artificial intelligence , mathematics , medicine , mathematical analysis , physics , geometry , surgery , classical mechanics , complication
As people pay more attention to physical fitness and health keeping, running becomes the first choice for daily sport. However, due to the lack of scientific management and guidance, unreasonable running sometimes has a negative impact on health. The foot strike pattern has a great impact on the knee joint of the runner during running. Therefore, it is important for runners to monitor and record their running gait, so as to customize more appropriate training programs. Through cross-correlation analysis on two axial signals of the acceleration sensor, two common running landing gait patterns, the forefoot strike pattern and the rearfoot strike pattern, can be identified and distinguished. Based on the theoretical analysis, two running gait pattern recognition experiments were designed and conducted. Experiment results reveal that the method proposed can effectively characterize the two running gait patterns and shows a good universality and generalization ability among different subjects.