Analysis of body pressure distribution on car seats by using deep learning.

Journal: Applied ergonomics
PMID: 30509538

Abstract

This study aimed to extract information from body pressure distribution, including comfort, participant body size, and seat characteristics by using supervised deep learning, and body pressure characteristics corresponding to sensory evaluation by using unsupervised deep learning. Body pressure data of 18 participants and 19 kinds of car seats were used for the analysis. Sensory evaluation of 9 items concerning cushion characteristics and seat comfort was conducted. From the analysis, we determined that body size and car seats could be classified with high precision by using body pressure distribution data. For the sensory evaluation items, the correct answer rate was high. By examining the importance of the cells of the mat, the features of the body pressure mat at the seat cushion and backrest, body size, car seat, and parts related to sensory evaluation could be determined in detail. The study findings can be applied in the development of car seats.

Authors

  • Reiko Mitsuya
    Research Institute for Science and Engineering, Waseda University, Shinjuku, Tokyo, 169-8555, Japan. Electronic address: smitsuya@sa2.so-net.net.ne.jp.
  • Kazuhito Kato
    Seating Development, NHK Spring Co. Ltd, Kanazawa-ku, Yokohama, 236-0004, Japan.
  • Nei Kou
    Seating Development, NHK Spring Co. Ltd, Kanazawa-ku, Yokohama, 236-0004, Japan.
  • Takeshi Nakamura
    Seating Development, NHK Spring Co. Ltd, Kanazawa-ku, Yokohama, 236-0004, Japan.
  • Kohei Sugawara
    Department of Intermedia Art and Science, School of Fundamental Science and Engineering, Waseda University, Shinjuku, Tokyo, 169-8555, Japan.
  • Hiroki Dobashi
  • Takuro Sugita
    Department of Intermedia Art and Science, School of Fundamental Science and Engineering, Waseda University, Shinjuku, Tokyo, 169-8555, Japan.
  • Takashi Kawai
    Department of Intermedia Art and Science, School of Fundamental Science and Engineering, Waseda University, Shinjuku, Tokyo, 169-8555, Japan.

Keywords

External Resources

Popular Topics
Recent Journals