A Phase Variable Approach for IMU-Based Locomotion Activity Recognition

2018 ◽  
Vol 65 (6) ◽  
pp. 1330-1338 ◽  
Author(s):  
Harrison L. Bartlett ◽  
Michael Goldfarb
Keyword(s):  
Activity Recognition ◽  
Phase Variable ◽  
Variable Approach ◽  
Locomotion Activity

Locomotion Activity Recognition Using Stacked Denoising Autoencoders

2018 ◽  
Vol 5 (3) ◽  
pp. 2085-2093 ◽  
Author(s):  
Fuqiang Gu ◽  
Kourosh Khoshelham ◽  
Shahrokh Valaee ◽  
Jianga Shang ◽  
Rui Zhang
Keyword(s):  
Activity Recognition ◽  
Locomotion Activity

scholarly journals Lower Limb Locomotion Activity Recognition of Healthy Individuals Using Semi-Markov Model and Single Wearable Inertial Sensor

Sensors ◽  
2019 ◽  
Vol 19 (19) ◽  
pp. 4242 ◽  
Author(s):  
Haoyu Li ◽  
Stéphane Derrode ◽  
Wojciech Pieczynski
Keyword(s):  
Markov Model ◽  
Activity Recognition ◽  
Lower Limb ◽  
Model Updating ◽  
Inertial Sensor ◽  
Lower Limbs ◽  
Healthy Individuals ◽  
Batch Mode ◽  
On Line ◽  
Locomotion Activity

Lower limb locomotion activity is of great interest in the field of human activity recognition. In this work, a triplet semi-Markov model-based method is proposed to recognize the locomotion activities of healthy individuals when lower limbs move periodically. In the proposed algorithm, the gait phases (or leg phases) are introduced into the hidden states, and Gaussian mixture density is introduced to represent the complex conditioned observation density. The introduced sojourn state forms the semi-Markov structure, which naturally replicates the real transition of activity and gait during motion. Then, batch mode and on-line Expectation-Maximization (EM) algorithms are proposed, respectively, for model training and adaptive on-line recognition. The algorithm is tested on two datasets collected from wearable inertial sensors. The batch mode recognition accuracy reaches up to 95.16%, whereas the adaptive on-line recognition gradually obtains high accuracy after the time required for model updating. Experimental results show an improvement in performance compared to the other competitive algorithms.

A novel fusion strategy for locomotion activity recognition based on multimodal signals

2021 ◽  
Vol 67 ◽  
pp. 102524
Author(s):  
Fo Hu ◽  
Hong Wang ◽  
Naishi Feng ◽  
Bin Zhou ◽  
Chunfeng Wei ◽  
...  
Keyword(s):  
Activity Recognition ◽  
Fusion Strategy ◽  
Multimodal Signals ◽  
Locomotion Activity

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

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 109840-109855 ◽  
Author(s):  
Siavash Rezazadeh ◽  
David Quintero ◽  
Nikhil Divekar ◽  
Emma Reznick ◽  
Leslie Gray ◽  
...  
Keyword(s):  
Phase Variable ◽  
Ankle Prosthesis ◽  
Variable Approach
Sign in / Sign up

Export Citation Format

Share Document