Motion state recognition method and system based on three-axis accelerometer

A technology of motion state and axis acceleration, applied in the field of electronics, can solve problems such as functional limitation and single function, and achieve the effect of improving accuracy

Inactive Publication Date: 2018-05-08
HUIZHOU DESAY IND RES INST CO LTD +1
View PDF21 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] In recent years, wearable technology devices have become increasingly common, and various products have sprung up. At the same time, artificial intelligence technology has also been integrated into wearable devices to achieve more proactive services and smarter data analysis. , to bring better exercise advice and a healthier lifestyle to users. At present, smart shoes have appeared on the market, and their functions are basically limited to human body indicators, such as the measurement of temperature, humidity, weight, etc., as well as heating and dehumidification services and simple alarms, etc. , as a wearable smart device, its single function cannot meet the increasing needs of people

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
  • Motion state recognition method and system based on three-axis accelerometer
  • Motion state recognition method and system based on three-axis accelerometer

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 2

[0033] Embodiment 2: This embodiment is similar to Embodiment 1, and the difference is that step S50 described in this embodiment also includes the following voting process: select the one with the highest number of votes according to the adjacent motion state recognition results, and output the motion obtained after voting. State recognition results to improve the accuracy of motion state recognition. For example, the recognition results of several adjacent motion states are walking, walking, running, walking, and walking. Correction to get more accurate result output.

Embodiment 3

[0034] Embodiment three: as figure 2 As shown, a motion state recognition system based on a three-axis acceleration sensor includes: a data acquisition module for collecting acceleration data in a person's motion state; an algorithm module for marking the motion type and signaling the collected acceleration data Process and select the axis used for data analysis, and perform feature extraction on the axis of data analysis; the classifier training module is used to train the learning model with the extracted features and corresponding motion type labels; the state recognition module is used to extract the extracted features The feature performs state recognition, and outputs the motion state recognition result and step count result, and the data acquisition module is a three-axis acceleration sensor.

[0035] Among them, the algorithm module includes a data preprocessing unit and a feature extraction unit. The data preprocessing unit performs motion type marking and signal pro...

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 provides a motion state recognition method and system based on a three-axis accelerometer, which comprise a self learning stage and a practical application stage. The self learning stagecomprises the following steps: S10, acceleration data in the motion state of a person are acquired through the three-axis accelerometer; S20, the acquired acceleration data are subjected to motion type marking and signal processing; S30, an axis for data analysis is selected according to an x, y and z coordinate system of the three-axis accelerometer, and the axis for data analysis is subjected to feature extraction; and S40, the extracted features and the corresponding motion type mark are applied to a classifier to train a learning model. The practical application stage comprises the following step: S50, the three-axis accelerometer acquires the user data, steps S20 and S30 are repeated, the extracted features are inputted to the learning model, and a motion state recognition result anda step count result are obtained. The motion type of the user can be recognized, the step count can be calculated, and the accuracy is high.

Description

technical field [0001] The invention relates to the field of electronic technology, in particular to a motion state recognition method and system based on a three-axis acceleration sensor. Background technique [0002] In recent years, wearable technology devices have become increasingly common, and various products have sprung up. At the same time, artificial intelligence technology has also been integrated into wearable devices to achieve more proactive services and smarter data analysis. , to bring better exercise advice and a healthier lifestyle to users. At present, smart shoes have appeared on the market, and their functions are basically limited to human body indicators, such as the measurement of temperature, humidity, weight, etc., as well as heating and dehumidification services and simple alarms, etc. , as a wearable smart device, its single function cannot meet the increasing needs of people. Contents of the invention [0003] In view of the above technical pr...

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): G01P15/18G01C22/00
CPCG01C22/006G01P15/18
Inventor 王明悦邬志强黄伟烈钟晨
Owner HUIZHOU DESAY IND RES INST CO LTD
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