Presentation | 2022-03-04 A Study on Non-contact Blood Pressure Estimation Method based on Subject Classification by Machine Learning Shuzo Ishizaka, Kohei Yamamoto, Tomoaki Ohtsuki, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Non-contact Blood Pressure (BP) measurement is receiving a lot of interest for BP measurement on a daily basis. To realize non-contact BP measurement, the use of a Doppler radar has been investigated. A Doppler radar can detect the pulse wave caused by chest displacement due to heartbeat. BP can be estimated by constructing a BP estimation model using features that correlate with BP obtained from the pulse wave. However, compared to the case of modeling for each subject, the accuracy of BP estimation deteriorates significantly when modeling with multiple subjects other than the target subject. In this report, to improve the accuracy of BP estimation when modeling with multiple subjects, we proposed a non-contact BP estimation method using a Doppler radar based on subject classification. In the proposed method, subjects are classified by Principal Component Analysis (PCA) and hierarchical clustering. A BP estimation model that inputs the features that correlate with BP and outputs Systolic BP (Systolic Blood Pressure) is constructed for each classified cluster. The experimental results showed that when modeling with multiple subjects other than a testing subject, the proposed method achieved high the BP estimation accuracy, compared to the method without subject classification. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Doppler radar / Non-contact blood pressure estimation / Machine learning / Health care |
Paper # | MICT2021-101 |
Date of Issue | 2022-02-25 (MICT) |
Conference Information | |
Committee | MICT / EMCJ |
---|---|
Conference Date | 2022/3/4(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Healthcare and Medical Information Communication Technologies, EMC, etc |
Chair | Eisuke Hanada(Saga Univ.) / Atsuhiro Nishikata(Tokyo Inst. of Tech.) |
Vice Chair | Hirokazu Tanaka(Hiroshima City Univ.) / Daisuke Anzai(Nagoya Inst. of Tech.) / Kimihiro Tajima(NTT-AT) |
Secretary | Hirokazu Tanaka(Yokohama National Univ.) / Daisuke Anzai(KISTEC) / Kimihiro Tajima(NAIST) |
Assistant | Takahiro Ito(Hiroshima City Univ) / Kento Takabayashi(Okayama Pref. Univ.) / Takuya Nishikawa(National Cerebral and Cardiovascular Center Hospital) / Kiyoto Matsushima(Hitachi) / Hiroyoshi Shida(EMC Tech.) / Toru Matsushima(Kyushu Inst. of Tech.) |
Paper Information | |
Registration To | Technical Committee on Healthcare and Medical Information Communication Technology / Technical Committee on Electromagnetic Compatibility |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | A Study on Non-contact Blood Pressure Estimation Method based on Subject Classification by Machine Learning |
Sub Title (in English) | |
Keyword(1) | Doppler radar |
Keyword(2) | Non-contact blood pressure estimation |
Keyword(3) | Machine learning |
Keyword(4) | Health care |
1st Author's Name | Shuzo Ishizaka |
1st Author's Affiliation | Keio University(Keio Univ.) |
2nd Author's Name | Kohei Yamamoto |
2nd Author's Affiliation | Keio University(Keio Univ.) |
3rd Author's Name | Tomoaki Ohtsuki |
3rd Author's Affiliation | Keio University(Keio Univ.) |
Date | 2022-03-04 |
Paper # | MICT2021-101 |
Volume (vol) | vol.121 |
Number (no) | MICT-404 |
Page | pp.pp.1-6(MICT), |
#Pages | 6 |
Date of Issue | 2022-02-25 (MICT) |