Designing of smart chair for monitoring of sitting posture using convolutional neural networks
| DOI | https://doi.org/10.1108/DTA-03-2018-0021 |
| Pages | 142-155 |
| Published date | 01 April 2019 |
| Date | 01 April 2019 |
| Author | Wonjoon Kim,Byungki Jin,Sanghyun Choo,Chang S. Nam,Myung Hwan Yun |
| Subject Matter | Library & information science,Librarianship/library management,Library technology,Information behaviour & retrieval,Metadata,Information & knowledge management,Information & communications technology,Internet |
Designing of smart chair for
monitoring of sitting posture using
convolutional neural networks
Wonjoon Kim and Byungki Jin
Department of Industrial Engineering and Institute for Industrial System Innovation,
SeoulNationalUniversity,Seoul,SouthKorea
Sanghyun Choo and Chang S. Nam
Department of Industrial and Systems Engineering,
North Carolina State University College of Engineering,
Raleigh, North Carolina, USA, and
Myung Hwan Yun
Department of Industrial Engineering and Institute for Industrial System Innovation,
SeoulNationalUniversity,Seoul,SouthKorea
Abstract
Purpose –Sitting in a chair is a typical act of modern people. Prolonged sitting and sitting with improper
postures can lead to musculoskeletal disorders. Thus, there is a need for a sitting posture classification
monitoring system that can predict a sitting posture. The purpose of this paper is to develop a system for
classifying children’s sitting postures for the formation of correct postural habits.
Design/methodology/approach –For the data analysis, a pressure sensor of film type was installed
on the seat of the chair, and image data of the postu. re were collected. A tota l of 26 children
participated in the e xperiment and collect ed image data for a total of seven postures. The authors used
convolutional neura l networks (CNN) algorit hm consisting of seven l ayers. In addition, to c ompare the
accuracy of classific ation, artificial n eural networks (ANN) te chnique, one of the mac hine learning
techniques, was used.
Findings –The CNN algorithm was used for the sitting position classification and the average accuracy
obtained by tenfold cross validation was 97.5 percent. The authors confirmed that classification accuracy
through CNN algorithm is superior to conventional machine learning algorithms such as ANN and DNN.
Through this study, we confirmed the applicability of the CNN-based algorithm that can be applied to the
smart chair to support the correct posture in children.
Originality/value –This study successfully performed the posture classification of children using
CNN technique, which has not been used in related studies. In addition, by focusing on children, we
have expanded the scope of the related research area and expected to contribute to the early postural habits
of children.
Keywords Deep learning, Data classification, IoT application, Convolutional neural network, Sensing cushion,
Sitting posture classification
Paper type Research paper
Introduction
Sitting in a chair is a typical act of modern people. In present society, most people sit in front
of computers due to the development of computer technology and software (Bao et al., 2013;
Boulay et al., 2005; Ciccarelli et al., 2015). As the time spent sitting and working is
prolonging, negative effects on health and productivity are increasing (Dunstan et al., 2010).
Furthermore, people often sit in chairs in improper postures due to electronic devices, such
as smartphone or laptops (Kim et al., 2018). Not only prolonged sitting but also poor posture
cause musculoskeletal disorders, such as herniated cervical/lumbar disc (O’sullivan et al.,
2002). An awkward sitting posture causes lumbar flexion and exerts a high compressive
force on lumbar (Huang et al., 2016). Disorders caused by prolonged sitting and awkward
postures could be prevented by monitoring and controlling the sitting behaviors. In order to
Data Technologies and
Applications
Vol. 53 No. 2, 2019
pp. 142-155
© Emerald PublishingLimited
2514-9288
DOI 10.1108/DTA-03-2018-0021
Received 27 March 2018
Revised 2 November 2018
Accepted 5 December 2018
The current issue and full text archive of this journal is available on Emerald Insight at:
www.emeraldinsight.com/2514-9288.htm
142
DTA
53,2
To continue reading
Request your trial