Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Feature merging-based MCRF (Multiple CRF Ensemble Model) abnormal behavior real-time recognition method

A recognition method and behavior technology, applied in the computer field, can solve the problem of not considering the real-time performance of behavior recognition

Inactive Publication Date: 2018-08-28
CHONGQING UNIV OF POSTS & TELECOMM
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In these user behavior recognition projects, researchers did not consider the real-time nature of behavior recognition

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
  • Feature merging-based MCRF (Multiple CRF Ensemble Model) abnormal behavior real-time recognition method
  • Feature merging-based MCRF (Multiple CRF Ensemble Model) abnormal behavior real-time recognition method
  • Feature merging-based MCRF (Multiple CRF Ensemble Model) abnormal behavior real-time recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] The preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0018] 1 MCRF model

[0019] In order to ensure the ability of the classifier to link contextual information, the present invention adopts the multi-CRF combined model (Multiple CRF Ensemble Model, MCRF) for abnormal behavior identification. First, a feature set is formed for each feature after feature extraction, and multiple CRF models are formed by using the CRF model to model each feature set, and then the MCRF model is obtained by fusing multiple CRF models, and finally the abnormal behavior is identified using the MCRF model.

[0020] Suppose X=(x 1 ,x 2 ,...,x N ) represents the observation sequence, Y=(y 1 ,y 2 ,...,y N ) is the label corresponding to the observation sequence, y i ∈(1,2,…,L), L is the category of behavior. In order to use the CRF model to model each feature, the present invention extracts the feature set of...

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 feature merging-based MCRF (Multiple CRF Ensemble Model) abnormal behavior real-time recognition method and belongs to the computer field. In view of a problem that abnormalbehavior recognition in a smart home environment is low in real-time performance and low in recognition accuracy, the idea of feature merging is introduced in the MCRF, and therefore, observation feature dimensions can be effectively reduced, and the abnormal behavior recognition efficiency of the MCRF model is improved. With the method of the invention adopted, abnormalities can be identified inreal time and accurately; detected abnormality results are fed back to sons and daughters or medical staff through a mobile terminal in real time; and hurt to old people living alone caused by some unexpected accidents such as falling and syncope can be decreased to a great extent.

Description

technical field [0001] The invention belongs to the field of computers and relates to a real-time identification method for MCRF abnormal behavior based on feature merging. Background technique [0002] Advances in ubiquitous computing have led to the development of wireless sensors for collecting activity information. Combining the behavioral data collected by wireless sensors with the most advanced machine learning algorithms has further promoted the research on the user's daily behavior recognition algorithm in the smart home environment. Currently, the research on user behavior recognition algorithms in the smart home environment mainly includes CASAS, MavHome, PlaceLab, CARE and Aware Home. In these user behavior recognition projects, researchers did not consider the real-time performance of behavior recognition. but. In the process of abnormal behavior recognition in the actual smart home environment, the selection of features plays a crucial role in the real-time p...

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): G06K9/62
CPCG06F18/213G06F18/22G06F18/2415
Inventor 付蔚巩莉郑方雄何雨
Owner CHONGQING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com