Raspberry Pi elder people tumbling detection system based on deep learning

A deep learning and detection system technology, applied in the input/output process of data processing, instruments, electrical and digital data processing, etc., can solve the problems of high price, difficult to promote, and complex design.

Inactive Publication Date: 2018-10-12
GUANGXI NORMAL UNIV OF SCI & TECH
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, although some fall detection based on MEMS technology in China can better realize fall detection, most o

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
  • Raspberry Pi elder people tumbling detection system based on deep learning
  • Raspberry Pi elder people tumbling detection system based on deep learning
  • Raspberry Pi elder people tumbling detection system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The present invention will be described in detail below in combination with specific embodiments.

[0021] The algorithm of the present invention is based on Google's Internet of Things operating system Android Things. First collect data, based on the acceleration signal collector of the three-axis acceleration sensor. Each collector contains two three-axis acceleration sensors placed in parallel, so that the collector can collect two three-axis acceleration data at the same time when doing each movement. Prevent data loss with one sensor.

[0022] The CUT-NAA database used contains 10 types of motion data from 44 different collectors. During the collection process, the collectors are respectively placed on the collector's belt, trousers pocket, and jacket pocket. The 10 types of actions and their descriptions are listed in Table 1 below:

[0023] Table 1

[0024]

[0025] The data generated by the acceleration sensor is data with time as the independent variabl...

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 Raspberry Pi elder people tumbling detection system based on deep learning. Each collector comprises two parallel three-axis acceleration sensors, and the collectors are placed on a waistband, pockets of trousers and pockets of a coat of a person needing collection respectively. When changes of acceleration and angular velocity exceed a certain range, alarm information issent out; redundant information is contained in the data, the data is reduced from 150 dimensions to 100 dimensions, then the data of behavior states is trained through a DBN deep neural network, anda network model generated through training is used for detecting the real-time behavior states. The system has the advantages that the tumbling detection principle is based on the DBN deep neural network, and false tumbling can be effectively prevented, for example, when equipment freely falls on the ground, mistaken judgment of false tumbling is avoided. The cost of Raspberry Pie hardware equipment is low, and popularization can be better achieved.

Description

technical field [0001] The invention belongs to the technical field of electronic devices, and relates to a raspberry pie elderly fall detection system based on deep learning. Background technique [0002] The growing population of the elderly has become the focus of attention. Due to the inconvenient physical activities of the elderly, falls have become the fourth cause of casualties in my country, and accidental falls are the main health threat to people over 65 years old. Relevant scholars in my country have conducted research on the fall problem of the elderly, but the products produced by the research institute are mainly crutches and walkers. Although these products can reduce the probability of the elderly falling, they cannot effectively rescue the elderly when they fall in the first place. Therefore, this study is based on the combination of traditional products and the application of the Internet of Things era, and explores its results on the elderly who will not...

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): G08B21/04G06K9/00G06K9/62G06F3/0346
CPCG06F3/0346G08B21/043G08B21/0446G06F2218/06G06F2218/12G06F18/2135
Inventor 丁红饶万贤黄炎钊
Owner GUANGXI NORMAL UNIV OF SCI & 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