Fall detection method and device based on multi-sensor data fusion

A data fusion and multi-sensor technology, applied in the direction of instruments, alarms, etc., can solve the problems of great influence on the recognition rate and high complexity of the recognition model, and achieve the effect of improving recognition ability, improving reliability and reducing false alarms

Inactive Publication Date: 2017-05-31
SOUTH CHINA UNIV OF TECH +1
View PDF6 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The algorithm based on threshold recognition is more intuitive in algorithm design and easy to implement. It is a commonly used method in fall detection at present. Its shortcoming is that the setting of threshold has a great influence on the recognition rate. The setting of threshold needs to be based on intuitive judgment or Based on a large amount of data, and due to individual differences, different thresholds need to be set, and the complexity of the recognition model is high

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
  • Fall detection method and device based on multi-sensor data fusion
  • Fall detection method and device based on multi-sensor data fusion
  • Fall detection method and device based on multi-sensor data fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] Such as figure 1 with figure 2 As shown, a method of fall detection based on multi-sensor data fusion provided in this embodiment includes the following steps:

[0036] S1. Collect a sufficient number of human motion state data samples.

[0037] In order to build a support vector machine-based human fall recognition model, the support vector machine model is trained, and multiple groups of sample data of human motion states are collected, including fall action data and ADL (human daily behavior activities, Activity of daily livings) data.

[0038] The fall actions include fall forward, fall backward, fall left, fall right, fall on the back, fall on the stomach and other fall types. ADL data includes normal walking, up and down stairs, running, and posture changes such as standing, sitting, and squatting.

[0039] S2. Extract the feature vector of the plantar pressure of the human fall from the sample data, and establish a human fall recognition model based on the s...

Embodiment 2

[0059] Such as image 3 As shown, a fall detection device based on multi-sensor data fusion disclosed in this embodiment includes a pressure sensor, a triaxial acceleration sensor, a wireless sending module, a wireless receiving module, a microprocessor, and a help module. The pressure sensor, The triaxial acceleration sensors are respectively connected to the wireless sending module, the wireless sending module is connected to the wireless receiving module by wireless, the wireless receiving module is connected to the microprocessor, and the microprocessing module according to the pressure The sensor and the triaxial acceleration data are analyzed and judged to determine whether the human body has fallen; the microprocessor is connected to the distress module, and the distress module sends a distress signal according to the judgment result.

[0060] In a specific embodiment, the pressure sensor and the triaxial acceleration sensor are arranged on the sole of the human body. ...

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 a fall detection method and device based on multi-sensor data fusion; the fall detection method employs a pattern recognition method and divides human body behaviors into a fall pattern and an ADL (activities of daily living) pattern, feature vectors acting as human body fall criteria are screened out by means of machine learning method based on support vector machine, and human body fall is detected jointly according to the feature vectors and human body movement state data. The fall detection device comprises a pressure sensor, an acceleration sensor, a wireless transmitting module, a wireless receiving module, a microprocessor, a call-for-help module and the like. According to the fall detection method, pressure data and acceleration data of a fall process are monitored and processed in real time to recognize human body fall correctly, and positional information is sent to family members or nursing staff in order to gain timely rescue and treatment. The feature vectors are extracted based on multi-sensor data, and the ability to recognize a fall is improved effectively.

Description

technical field [0001] The invention relates to the technical field of automatic detection, in particular to a fall detection method and device based on multi-sensor data fusion. Background technique [0002] With the progress of society, population aging is an unstoppable trend in the development of human society, and it has already become a development problem that cannot be ignored in our country. Statistics show that by the end of 2014, the number of elderly people over the age of 60 in my country had reached 210 million, accounting for 15.5% of the total population, and the number of people over 65 was 130 million, accounting for 10.1% of the total population. [0003] As the functions of the various organs of the elderly body begin to age, the body function declines, the response is not sensitive, and accidental falls often occur, which has become one of the important reasons that threaten the life and health of the elderly. According to statistics, more than one-thir...

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): G08B21/04
CPCG08B21/043G08B21/0446
Inventor 史景伦张福伟洪冬梅
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