Literature DB >> 28910754

A Phase Variable Approach for IMU-Based Locomotion Activity Recognition.

Harrison L Bartlett, Michael Goldfarb.   

Abstract

OBJECTIVE: This paper describes a gait classification method that utilizes measured motion of the thigh segment provided by an inertial measurement unit.
METHODS: The classification method employs a phase-variable description of gait, and identifies a given activity based on the expected curvature characteristics of that activity over a gait cycle. The classification method was tested in experiments conducted with seven healthy subjects performing three different locomotor activities: level ground walking, stair descent, and stair ascent. Classification accuracy of the phase variable classification method was assessed for classifying each activity, and transitions between activities, and compared to a linear discriminant analysis (LDA) classifier as a benchmark.
RESULTS: For the subjects tested, the phase variable classification method outperformed LDA when using nonsubject-specific training data, while the LDA outperformed the phase variable approach when using subject-specific training.
CONCLUSIONS: The proposed method may provide improved classification accuracy for gait classification applications trained with nonsubject-specific data. SIGNIFICANCE: This paper offers a new method of gait classification based on a phase variable description. The method is shown to provide improved classification accuracy relative to an LDA pattern recognition framework when trained with nonsubject-specific data.

Mesh:

Year:  2017        PMID: 28910754     DOI: 10.1109/TBME.2017.2750139

Source DB:  PubMed          Journal:  IEEE Trans Biomed Eng        ISSN: 0018-9294            Impact factor:   4.538


  6 in total

1.  Modeling the Kinematics of Human Locomotion Over Continuously Varying Speeds and Inclines.

Authors:  Kyle R Embry; Dario J Villarreal; Rebecca L Macaluso; Robert D Gregg
Journal:  IEEE Trans Neural Syst Rehabil Eng       Date:  2018-11-05       Impact factor: 3.802

2.  Modeling the Transitional Kinematics Between Variable-Incline Walking and Stair Climbing.

Authors:  Shihao Cheng; Edgar Bolívar-Nieto; Cara Gonzalez Welker; Robert D Gregg
Journal:  IEEE Trans Med Robot Bionics       Date:  2022-06-22

3.  Design of Decision Tree Structure with Improved BPNN Nodes for High-Accuracy Locomotion Mode Recognition Using a Single IMU.

Authors:  Yang Han; Chunbao Liu; Lingyun Yan; Lei Ren
Journal:  Sensors (Basel)       Date:  2021-01-13       Impact factor: 3.576

4.  Moving the Lab into the Mountains: A Pilot Study of Human Activity Recognition in Unstructured Environments.

Authors:  Brian Russell; Andrew McDaid; William Toscano; Patria Hume
Journal:  Sensors (Basel)       Date:  2021-01-19       Impact factor: 3.576

5.  A Phase Variable Approach for Improved Rhythmic and Non-Rhythmic Control of a Powered Knee-Ankle Prosthesis.

Authors:  Siavash Rezazadeh; David Quintero; Nikhil Divekar; Emma Reznick; Leslie Gray; Robert D Gregg
Journal:  IEEE Access       Date:  2019-08-06       Impact factor: 3.367

6.  On-board Training Strategy for IMU-Based Real-Time Locomotion Recognition of Transtibial Amputees With Robotic Prostheses.

Authors:  Dongfang Xu; Qining Wang
Journal:  Front Neurorobot       Date:  2020-10-22       Impact factor: 2.650

  6 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.