scholarly journals A Doppler-Tolerant Ultrasonic Multiple Access Localization System for Human Gait Analysis

Sensors ◽  
2018 ◽  
Vol 18 (8) ◽  
pp. 2447 ◽  
Author(s):  
Karalikkadan Ashhar ◽  
Mohammad Khyam ◽  
Cheong Soh ◽  
Keng Kong
Keyword(s):  
Gait Analysis ◽  
Multiple Access ◽  
Human Movement ◽  
Lower Limbs ◽  
Human Gait ◽  
Tracking Accuracy ◽  
Ultrasonic Sensors ◽  
Access Methods ◽  
Localization System ◽  
Human Gait Analysis

Ranging based on ultrasonic sensors can be used for tracking wearable mobile nodes accurately for a long duration and can be a cost-effective method for human movement analysis in rehabilitation clinics. In this paper, we present a Doppler-tolerant ultrasonic multiple access localization system to analyze gait parameters in human subjects. We employ multiple access methods using linear chirp wave-forms and narrow-band piezoelectric transducers. A Doppler shift compensation Technique is also incorporated without compromising on the tracking accuracy. The system developed was used for tracking the trajectory of both lower limbs of five healthy adults during a treadmill walk. An optical motion capture system was used as the reference to compare the performance. The average Root Mean Square Error values between the 3D coordinates estimated from the proposed system and the reference system while tracking both lower limbs during treadmill walk experiment by 5 subjects were found to be 16.75, 14.68 and 20.20 mm respectively along X, Y and Z-directions. Errors in the estimation of spatial and temporal parameters from the proposed system were also quantified. These promising results show that narrowband ultrasonic sensors can be utilized to accurately track more than one mobile node for human gait analysis.

DEVELOPMENT OF A SYSTEM FOR HUMAN GAIT ANALYSIS USING KINECT V2

2019 ◽  
Author(s):  
Ítalo Rodrigues ◽  
Jadiane Dionisio ◽  
Rogério Sales Gonçalves
Keyword(s):  
Gait Analysis ◽  
Human Gait ◽  
Kinect V2 ◽  
Human Gait Analysis

scholarly journals Human Gait Analysis in Neurodegenerative Diseases: a Review

2021 ◽  
pp. 1-1
Author(s):  
Grazia Cicirelli ◽  
Donato Impedovo ◽  
Vincenzo Dentamaro ◽  
Roberto Marani ◽  
Giuseppe Pirlo ◽  
...  
Keyword(s):  
Neurodegenerative Diseases ◽  
Gait Analysis ◽  
Human Gait ◽  
Human Gait Analysis

Human Gait Analysis Method Based on Sample Entropy Fusion AlphaPose Algorithm

2021 ◽  
Author(s):  
Xinyu Lv ◽  
Shengying Wang ◽  
Tao Chen ◽  
Jing Zhao ◽  
Desheng Chen ◽  
...  
Keyword(s):  
Gait Analysis ◽  
Sample Entropy ◽  
Human Gait ◽  
Analysis Method ◽  
Human Gait Analysis

scholarly journals Human Gait-labeling Uncertainty and a Hybrid Model for Gait Segmentation

2021 ◽  
Author(s):  
Jiaen Wu ◽  
Henrik Maurenbrecher ◽  
Alessandro Schaer ◽  
Barna Becsek ◽  
Chris Awai Easthope ◽  
...  
Keyword(s):  
Gait Analysis ◽  
Motion Capture ◽  
Ground Truth ◽  
Absolute Error ◽  
Human Gait ◽  
Heel Strike ◽  
Analysis Model ◽  
Flat Foot ◽  
Dynamic Time ◽  
Human Gait Analysis

<div><div><div><p>Motion capture systems are widely accepted as ground-truth for gait analysis and are used for the validation of other gait analysis systems.To date, their reliability and limitations in manual labeling of gait events have not been studied.</p><p><b>Objectives</b>: Evaluate human manual labeling uncertainty and introduce a new hybrid gait analysis model for long-term monitoring.</p><p><b>Methods</b>: Evaluate and estimate inter-labeler inconsistencies by computing the limits-of-agreement; develop a model based on dynamic time warping and convolutional neural network to identify a valid stride and eliminate non-stride data in walking inertial data collected by a wearable device; Gait events are detected within a valid stride region afterwards; This method makes the subsequent data computation more efficient and robust.</p><p><b>Results</b>: The limits of inter-labeler agreement for key</p><p>gait events of heel off, toe off, heel strike, and flat foot are 72 ms, 16 ms, 22 ms, and 80 ms, respectively; The hybrid model's classification accuracy for a stride and a non-stride are 95.16% and 84.48%, respectively; The mean absolute error for detected heel off, toe off, heel strike, and flat foot are 24 ms, 5 ms, 9 ms, and 13 ms, respectively.</p><p><b>Conclusions</b>: The results show the inherent label uncertainty and the limits of human gait labeling of motion capture data; The proposed hybrid-model's performance is comparable to that of human labelers and it is a valid model to reliably detect strides in human gait data.</p><p><b>Significance</b>: This work establishes the foundation for fully automated human gait analysis systems with performances comparable to human-labelers.</p></div></div></div>

Sign in / Sign up

Export Citation Format

Share Document