Design of motion pattern recognition system based on MPU6050 and pressure sensor

Haoyuan Li; Xufeng Hu; Jingxu Huang; Yang Wang

doi:10.1117/12.2662807

16 December 2022 Design of motion pattern recognition system based on MPU6050 and pressure sensor

Haoyuan Li, Xufeng Hu, Jingxu Huang, Yang Wang

Proceedings Volume 12500, Fifth International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022); 125001M (2022) https://doi.org/10.1117/12.2662807
Event: 5th International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022), 2022, Chongqing, China

Abstract

Aimed at the defects of low accuracy of motion pattern recognition and large volume of measuring equipment, a motion pattern recognition system based on MPU6050 and pressure sensor is designed, and the overall structure of the system is given. The system takes nRF2401 wireless transmission module as the node to transmit the pressure and acceleration data collected by the data acquisition system to the data processing system. After preprocessing the data, the system extracts the eigenvalues, passes them into the double classification model based on SVM, corrects the model parameters, and achieve the task of motion pattern recognition. Experiments show that the system has small volume, high accuracy, and the accuracy is as high as 92%, which is obviously superior to the model using pressure data and classification model based on SVM.

Citation Download Citation

Haoyuan Li, Xufeng Hu, Jingxu Huang, and Yang Wang "Design of motion pattern recognition system based on MPU6050 and pressure sensor", Proc. SPIE 12500, Fifth International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022), 125001M (16 December 2022); https://doi.org/10.1117/12.2662807

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available