An Abnormal Gait Detection Method Based on Deterministic Learning Theory

A technique to determine learning theory, gait detection, applied in the field of pattern recognition, can solve the lack of research and other problems

Active Publication Date: 2017-11-07
SOUTH CHINA UNIV OF TECH
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, how to model the dynamics of the nonlinear gait system and distinguish between the two groups of people based on the differences in gait system dynamics to detect abnormal gaits caused by motor neurodegenerative diseases is lacking. Research is also a difficult problem

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • An Abnormal Gait Detection Method Based on Deterministic Learning Theory
  • An Abnormal Gait Detection Method Based on Deterministic Learning Theory
  • An Abnormal Gait Detection Method Based on Deterministic Learning Theory

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0065] Such as figure 1 As shown, an abnormal gait detection method based on deterministic learning theory includes the following steps:

[0066] Step 1. The feature extraction process is as follows:

[0067] The gait database that the present invention adopts is an online gait analysis database PhysioNet ( PhysioNet ( http: / / www.physionet.org / physiobank / database / gaitndd ), the gait signal is obtained through the force-sensitive membrane switch placed on the sole of the tester, the sampling frequency of the signal acquisition system is 300Hz, and the sampling resolution is 12bit. At present, the database provides the following gait parameters: single step duration of left and right feet (one foot touches the ground from the beginning to the next time it touches the ground again); standing time of left and right feet (time length of touching the ground within a single step); Swing duration (the length of time the inner foot swings in the air in a single step); double-foot su...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an abnormal gait detection method based on deterministic learning theory. The steps of the method include: feature extraction; based on the extracted gait features, neural network modeling and identification of the gait system dynamics of healthy normal people and patients with different types of motor neurodegenerative diseases; establishment of a constant value neural network; The dynamic estimator is constructed by the value neural network, based on the difference in gait system dynamics between the gait patterns of healthy normal people and patients with different types of motor neurodegenerative diseases, and the difference caused by motor neurodegenerative diseases is distinguished according to the principle of minimum error. Abnormal gait and normal gait of general healthy people, realize accurate detection of abnormal gait, and evaluate the detection effect. It is convenient, simple, non-invasive, and in a smart home environment, daily gait monitoring of family members can be realized by installing a pressure-sensitive floor system or wearing special shoes with sensor insoles.

Description

technical field [0001] The invention relates to a pattern recognition technology, in particular to an abnormal gait detection method based on deterministic learning theory. Background technique [0002] Human walking motion is a precise and complex process, and its motion pattern is determined by the dynamic interaction between the central nervous system and feedback mechanisms. Some diseases of aging, as well as some neurological diseases, can cause problems with this process. When a person walks, there is a signal transduction pathway between the motor nerve that produces movement awareness in the central nervous system and the muscles that produce action in the lower limbs. If there is a movement signal transmission obstacle in this pathway, the direct symptom is the abnormal gait of the person. Many common diseases in the elderly, such as Parkinson's disease (Parkinson Disease; PD), amyotrophic lateral sclerosis (Amyotrophic Lateral Sclerosis; ALS), Huntington's disease...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/66G06K9/46
Inventor 曾玮胡俊敏王聪
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap