bullet Sensors & Transducers Journal

    (ISSN: 2306-8515, e-ISSN 1726-5479)


    About this Journal

   Information for Authors

   Editorial Board

   Editorial Calendar

   Current Issue

   Browse Journal

S&T journal's cover

Submit Press Release

Submit White Paper

25 Top Downloaded Articles (2007-2012)


Contact Us





Vol. 252, Issue 5, October 2021, pp. 42-49




Deep Learning-Based Detection of Abnormal Respiration Based on Abdominal 3D Shape
Dynamically Measured by Moiré Topography

1 Yuki MOCHIZUKI and 1, *Norio TAGAWA

1 Tokyo Metropolitan University, 6-6 Asahigaoka, Hino, Tokyo, 191-0065, Japan
1 Tel.: +81-42-585-8416, fax: +81-42-583-5119

* E-mail: tagawa@tmu.ac.jp


Received: 2021 /Accepted: 2021 /Published: 31 October 2021



Abstract: Currently, paramedics cannot make triage judgments in ambulances during emergency transport of infants. If this can be done, it will be possible to select an appropriate destination hospital to provide the most suitable medical care. In this study, we developed a system to detect abnormal respiration by measuring and analyzing three-dimensional abdominal movement using moiré topography and a deep learning model. The performance of the model used in this system was evaluated, and the model was found to be more robust than conventional machine learning models with respect to changes in camera viewpoint.


Keywords: Moiré topography, Active stereo, Deep learning, LSTM, Abdomen shape, Triage, Abnormal respiration.


Acrobat reader logo Click <here> or title of paper to download the full pages article in pdf format



This work is licensed under a Creative Commons 4.0 International License


 Creative Commons License





1999 - 2021 Copyright ©, International Frequency Sensor Association (IFSA) Publishing, S.L. All Rights Reserved.

Home - News - Links - Archives - Tools - Voltage-to-Frequency Converters - Standardization - Patents - Marketplace - Projects - Wish List - e-Shop - Sensor Jobs - Membership - Videos - Publishing - Site Map - Subscribe - Search

 Members Area -Sensors Portal -Training Courses - S&T Digest - For advertisers - Bookstore - Forums - Polls - Submit Press Release - Submit White Paper - Testimonies - Twitter - Facebook - LinkedIn