Analysis of Body Pressure Distribution on Car Seats by using Deep Learning

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, the authors 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.

• Record URL:
  • https://doi.org/10.1016/j.apergo.2018.08.023
• Record URL:
  • http://www.sciencedirect.com/science/article/pii/S0003687018303351
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/00036870
• Supplemental Notes:
  • © 2018 Elsevier Ltd. All rights reserved. Abstract reprinted with permission of Elsevier.
• Authors:
  • Mitsuya, Reiko
  • Kato, Kazuhito
  • Kou, Nei
  • Nakamura, Takeshi
  • Sugawara, Kohei
  • 0000-0003-3786-1771
  • Dobashi, Hiroki
  • 0000-0003-2608-927X
  • Sugita, Takuro
  • 0000-0002-7174-4205
  • Kawai, Takashi
• Publication Date: 2019-2

Language

• English

Media Info

• Media Type: Web
• Features: Figures; Photos; References; Tables;
• Pagination: pp 283-287
• Serial:
  • Applied Ergonomics
  • Volume: 75
  • Issue Number: 0
  • Publisher: Elsevier
  • ISSN: 0003-6870
  • EISSN: 1872-9126
  • Serial URL: http://www.sciencedirect.com/science/journal/00036870

Subject/Index Terms

• TRT Terms: Comfort; Human body size; Machine learning; Occupant kinetics; Pressure; Seats
• Uncontrolled Terms: Deep learning
• Subject Areas: Design; Highways; Vehicles and Equipment;

Filing Info

• Accession Number: 01690214
• Record Type: Publication
• Files: TRIS
• Created Date: Dec 28 2018 2:03PM