Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Journal of Artificial Intelligence Practice
  4. Vol 6, Issue 2, 2023

Neural network and system for attitude and behavior detection based on pressure data

Download as PDF

DOI: 10.23977/jaip.2023.060209 | Downloads: 16 | Views: 417

Author(s)

Jianzhong Qiu 1,2, Caiwei Liu 1,2, Jun Wu 1,2, Bingyan Zhao 1

Affiliation(s)

1 School of Mechanical and Automotive Engineering, Qilu University of Technology (Shandong Academy of Sciences), 3501, University Road, Jinan, Shandong, 250353, China
2 Sichuan Machinery Research and Design Institute (Group) Co., Ltd, 48, Moxiang Road, Chengdu, Sichuan, 610094, China

Corresponding Author

Jun Wu

ABSTRACT

In the process of monitoring the behavior of the elderly, wearable devices and visual devices are easily limited by the site and environment, resulting in poor monitoring results. This paper proposes a posture behavior detection method and system based on pressure data. The convolutional neural network algorithm is used to identify the pressure data to detect the posture, calculate the posture holding time and posture change frequency, judge the posture change action process according to the trajectory of the pressure center point, and finally record and analyze the user's behavior. The correct rate of pose classification of the model used in this paper has reached 98.69%, and the correct rate of pose retention time has reached 98.06%. Finally completed the research and development of the relevant monitoring system, which can be used in the field of medical treatment and daily care.

KEYWORDS

Pressure Sensor, Deep Learning, Gesture Recognition, Behavior Monitoring

CITE THIS PAPER

Jianzhong Qiu, Caiwei Liu, Jun Wu, Bingyan Zhao, Neural network and system for attitude and behavior detection based on pressure data. Journal of Artificial Intelligence Practice (2023) Vol. 6: 54-65. DOI: http://dx.doi.org/10.23977/jaip.2023.060209.

REFERENCES

[1] Wang Lei. Analysis of pension risks and avoidance of elderly living alone [J]. Journal of Chongqing University of Technology (Social Sciences), 2020, 34(12):64-70.
[2] Sun Jieying, Zhang Xuetong, Wang Zhuying. The relationship between the accumulation pattern of meditation and the risk of common chronic diseases among the urban elderly [J]. Journal of Capital Institute of Physical Education, 2022, 34(01):63-70+108.
[3] Li Qian, Li Yanling, Zhang Miao, Lu Yatian, Zhang Hong. The relationship between physical activity and mental health of the elderly [J]. Modern Health, 2019(14):171-172.
[4] Mh A, Mia B, Ds C. Learning architecture for the recognition of walking and prediction of gait period using wearable sensors. 2022.
[5] Jegham I, Khalifa A B, Alouani I, et al. Vision-based human action recognition: An overview and real world challenges [J]. Digital Investigation, 2020, 32:200901.
[6] Zhang Shaohua. Research on wearable devices and data transmission technology for monitoring human physiological characteristics [D]. Beijing University of Technology, 2015.
[7] Yang Weidu. Research on human behavior recognition and state monitoring method based on wearable devices [D]. Harbin Institute of Technology, 2016.
[8] Pei Lishen, Zhao Xuezhuan, Zhang Guohua. Research on group behavior analysis model based on multi-level deep network architecture [J/OL]. Computer Application Research. 2020: 1-8.
[9] Paliyawan P, Nukoolkit C, Mongkolnam P. Prolonged sitting detection for office workers syndrome prevention using Kinect [C]., International Conference on Electrical Engineering/electronics. IEEE, 2014:1-6.
[10] Mallare, John Cloie T., Pineda, Dianne Faye G., et al. Sitting Posture Assessment using Computer Vision [J]. IEEE HNICEM, 2017, 
[11] Lan Mu, Ke Li, Chunhong Wu. A Sitting Posture Surveillance System Based on Image Processing Technology [A]. 2010 2nd International Conference on Computer Engineering and Technology ICCET 2010 [C]. 2010
[12] Jiang Yongxiang, Duan Jingle, et al. Sitting posture recognition by body pressure distribution and airbag regulation strategy based on seat comfort evaluation [J]. .The Journal of Engineering, 2019, Vol. 2019(23): 8910-8914
[13] Ma C, Li W, Gravina R, et al. Posture Detection Based on Smart Cushion for Wheelchair Users[J]. Sensors, 2017, Vol. 17
[14] C. Ma, W. Li, R. Gravina, G. Fortino, Activity recognition and monitoring for smart wheelchair users, in: 2016 IEEE 20th Int. Conf. Comput. Support. Coop. Work Des. CSCWD, IEEE, Nanchang, China, 2016, pp. 664–669
[15] Guanqing Liang, Jiannong Cao, Xuefeng Liu, Smart cushion: a practical system for fine-grained sitting posture recognition, in: 2017 IEEE Int. Conf. Pervasive Comput. Commun. Workshop PerCom Workshop, IEEE, Kona, HI, 2017, pp. 419 424.
[16] J. Roh, H. Park, K. Lee, J. Hyeong, S. Kim, B. Lee, Sitting posture monitoring system based on a low-cost load cell using machine learning, Sensors 18 (2018) 208.
[17] Xu Ran, Cong Wang, Yao Xiao, Xuliang Gao, Zhiyuan Zhu, Bin Chen. A portable sitting posture monitoring sysrem based on a pressure sensor array and machine learning, Sensors and Actuators A: Physical, 2021, vol. 331.
[18] Dean T, Cox, et al. Neural Networks and Neuroscience-Inspired Computer Vision [J]. Current Biology: CB, 2014.
[19] Iu A, Mw B. Quality assessment of compressed and resized medical images based on pattern recognition using a convolutional neural network—Science Direct [J]. Communications in Nonlinear Science and Numerical Simulation, 2020, 95.
[20] Zhou Liping, Liu Jinghao. A gait analysis method based on the trajectory of human center of gravity [J]. Information Technology, 2016(08):147-150+154.
[21] Liu Gang, Lu Ying, Shen Ying. Numerical simulation study of static body surface pressure distribution in human sitting posture [J]. Computer Engineering and Design, 2009, 30(10):2486-2488+2492.
[22] Joo Y, Byun J, Seong N, et al. Silver nanowire-embedded PDMS with a multiscale structure for a highly sensitive and robust flexible pressure sensor [J]. Nanoscale, 2015, 7(14):6208-6215.
[23] Kumar S, Bijender, Yadav S, et al. Flexible microhyperboloids facets giant sensitive ultra-low-pressure sensor[J]. Sensors and Actuators A Physical, 2021:112767.
[24] Yu Jiangtao, Sun Lei, Xiao Yao, Jiang Shuwen, Zhang Wanli. Research progress of piezoresistive flexible pressure sensors [J]. Electronic Components and Materials, 2019, 38(06):1-11.
[25] Jianzhong Qiu, Guoyong Wan, Jun Wu*, et al. A Target Detection and Evaluation Method for Safety Protection Equipment [J]. Journal of Physics, 2021, 1966(1): 012035.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 5879
Visits: 179359

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.