Non-contact Breathing Patterns Recognition with FMCW Radar by Processing Temporal Information using Transformer Network

This paper proposed non-contact monitoring by classifying breathing patterns using a frequency-modulated continuous wave (FMCW) radar sensor. First, the data were from the subject to conducting breathing pattern: normal, quick, hold, deep, deep quick. Second, we extract the breath wave patterns by e...

Full description

Saved in:
Bibliographic Details
Published in2023 Asia-Pacific Microwave Conference (APMC) pp. 420 - 422
Main Authors Avian, Cries, Leu, Jenq-Shiou, Ali, Erfansyah, Putro, Nur Achmad Sulistyo, Song, Hang, Takada, Jun-Ichi, Prakosa, Setya Widyawan, Purnomo, Ariana Tulus
Format Conference Proceeding
LanguageEnglish
Published IEEE 05.12.2023
Subjects
Breathing Pattern
Data mining
Feature extraction
FMCW
Microwave theory and techniques
Monitoring
Non-contact monitoring
Radar
Radar signal processing
Transformer
Transformers
Online AccessGet full text

Cover

More Information
Summary:This paper proposed non-contact monitoring by classifying breathing patterns using a frequency-modulated continuous wave (FMCW) radar sensor. First, the data were from the subject to conducting breathing pattern: normal, quick, hold, deep, deep quick. Second, we extract the breath wave patterns by employing several block preprocessing and extracting its temporal information that was not investigated by our previous work. Then, to distinguish those five breath wave conditions, the designated Transformer architecture is proposed. Finally, we compared our previous work and demonstrated that our model could enhance accuracy and attained 98.6% of F1-Scores.
DOI:10.1109/APMC57107.2023.10439834