Human body behavior recognition method based on heterogeneous layered PSO and SVM

A recognition method and technology of the human body, applied in character and pattern recognition, artificial life, instruments, etc., can solve problems such as poor optimization ability and low accuracy, and achieve the effect of reducing constraints, accelerating convergence speed, and avoiding premature convergence.

Active Publication Date: 2019-09-27
BEIJING INSTITUTE OF TECHNOLOGYGY +1
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The purpose of the present invention is to propose a human behavior recognition method based on heterogeneous layered PSO and SVM for the existing technical defects of low accuracy and poor optimization ability for identifying human motion behavior based on PSO and SVM

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
  • Human body behavior recognition method based on heterogeneous layered PSO and SVM
  • Human body behavior recognition method based on heterogeneous layered PSO and SVM
  • Human body behavior recognition method based on heterogeneous layered PSO and SVM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0108] This embodiment illustrates the process of applying the present invention "a human behavior recognition method based on heterogeneous layered particle swarm optimization and support vector machine" to the scene of human motion behavior classification.

[0109] figure 1 It is an algorithm flow chart of this method and a flow chart of this embodiment. As can be seen from the figure, the method includes the following steps:

[0110] Specific to this embodiment, the input data is the human body behavior motion data set collected by the three-axis inertial sensor, and the three-axis inertial sensor sequentially collects the different movements of the human body such as going up and down stairs at a constant speed, walking at a constant speed, jogging at a uniform speed, walking at a random speed, and squatting and standing up. The three-axis acceleration and angular velocity data signals under behavioral motion, and the input sequence data set of sensor motion data are 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
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a human body behavior recognition method based on heterogeneous layered PSO and SVM, and belongs to the technical field of human body behavior recognition and pattern recognition. Firstly, a particle fitness function is established according to input data, and then particle initialization is carried out on parameters needing to be optimized in a classifier based on a mixed random chaotic mapping method; the particles is layered by adopting a dynamic threshold rule, the acting force of the heterogeneous particles is fused into the particle position and speed updating process of each layer, and a layering speed updating principle is set; and finally, carrying out iterative optimization on each dimension parameter in the classifier to obtain a classification model based on heterogeneous layered optimization. And human motion behavior data input by the sensor is classified based on the model. Compared with the prior art, the optimization algorithm solves the problem that parameters are prone to falling into local optimum when a support vector machine classification model is established, the established heterogeneous hierarchical classification model parameter optimization convergence block is high in fluctuation interference resistance, and the recognition precision of human body behaviors is improved.

Description

technical field [0001] The invention relates to a human behavior recognition method based on heterogeneous layered PSO and SVM, and belongs to the technical field of human behavior recognition and pattern recognition. Background technique [0002] Human behavior recognition technology can fully reflect the movement conditions and physiological functions of the human body. Through digital information means, the signal collection and analysis of various behaviors and actions manifested by various movement symptoms of the human body can not only reduce the doctor's subjective judgment on the diagnosis of movement system diseases. At the same time, based on the pathological mechanism of motion control, we can further understand the movement rules of the human body and the decision-making and control mechanisms of various motion behaviors. fields have important guiding significance. [0003] In the process of human behavior recognition, the feature extraction of motion signals i...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/00
CPCG06N3/006G06V40/20G06F18/2411G06F18/24
Inventor 郭树理张祎彤何昆仑韩丽娜刘宏斌范利王春喜
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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