Fall detection method based on human acceleration multi-feature fusion and KNN

A multi-feature fusion and detection method technology, applied in the field of fall detection based on human acceleration signals, can solve the problems of low fall detection accuracy and poor fault tolerance, and achieve the effects of reducing medical care costs, high specificity, and improving safety.

Inactive Publication Date: 2019-01-11
HANGZHOU DIANZI UNIV
View PDF7 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The threshold-based fall detection method is easy to implement and has high computational ef

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 based on human acceleration multi-feature fusion and KNN
  • Fall detection method based on human acceleration multi-feature fusion and KNN
  • Fall detection method based on human acceleration multi-feature fusion and KNN

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings: this embodiment is implemented on the premise of the technical solution of the present invention, and provides detailed implementation methods and specific operating procedures.

[0023] Such as figure 1 As shown, this embodiment includes the following steps:

[0024] Step 1: Use two triaxial acceleration sensor units, the corresponding measuring range is ±6g, and the size of the sensor is 49mm×38mm×19mm. Set the sampling frequency to 50Hz according to the actual movement frequency of the human body, and capture and record the original movement data of the x, y, and z axes. The data acquisition device transmits the data to the host computer software through Bluetooth, and the host computer software records and saves the original motion data.

[0025] Embodiment The subjects are three healthy males (24±3 years old, 65±5kg, 170±5cm) and three healthy...

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 based on human body acceleration multi-feature fusion and KNN. The fall detection method collects human motion information through two acceleration sensors, extracts characteristic parameters of human acceleration, and reduces the feature set from 162 dimensions to 12 dimensions through the data compression method of principal component analysis. Through improved KNN machine learning algorithm, that is, through clustering method to search sample points in the fall and non-fall two categories, training sample clusters are formed, and according tothe fuzzy entropy calculation weighted Euclidean distance to find the nearest neighbor K points, the action to be classified into the K nearest neighbors belong to the majority of the category. The fall detection method aims at the action with the highest frequency of daily life as an experiment, and provides a fall detection algorithm based on human acceleration multi-feature fusion and KNN, which has the sensitivity of 100%, can detect the fall quickly and effectively, and has high specificity, and does not mistakenly judge the daily action as the fall.

Description

technical field [0001] The invention belongs to the field of human body gesture recognition and fall detection, and relates to a fall detection method based on human body acceleration signals, and an example is used to identify and detect falls and non-fall human actions. Background technique [0002] According to my country's sixth national census, the total population is 1.37 billion, of which 119 million are elderly people over the age of 65, accounting for 8.87% of the total population, becoming the country with the largest number of elderly people in the world. As the aging population continues to intensify, dynamic monitoring of the activity status of the elderly has become a prominent area of ​​multidisciplinary research. According to the U.S. Centers for Disease Control and Prevention, nearly 30 percent of people 65 and older experience frequent, accidental falls. The World Health Organization defines a fall as a sudden, involuntary, unintentional change of position...

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
IPC IPC(8): A61B5/11
CPCA61B5/1117A61B5/1128
Inventor 席旭刚华仙汤敏彦罗志增张启忠佘青山蒋鹏
Owner HANGZHOU DIANZI UNIV
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