Feature extraction of blood pressure from facial skin temperature distribution using deep learning

被引：0

作者：

Oiwa K. ^{[1
]}

Nozawa A. ^{[1
]}

机构：

[1] College of Science and Engineering, Aoyama Gakuin University, 5-10-1, Fuchinobe, Chuo-ku, Sagamihara, Kanagawa

来源：

IEEJ Transactions on Electronics, Information and Systems | 2019年 / 139卷 / 07期

关键词：

Blood pressure sensing; Convolutional neural network; Deep learning; Facial skin temperature distribution; Feature extraction; Non-contact sensing;

D O I：

10.1541/ieejeiss.139.759

中图分类号：

学科分类号：

摘要：

Vital sign monitoring in daily life is very important for the early detection of hypertension, which causes cerebrovascular and cardiovascular diseases. A non-contact vital sign sensing is essential for vital sign monitoring in daily life. Our previous studies have constructed linear regression models for estimating blood pressure, using nasal skin temperature and photoplethysmogram components in the nasal region, which were obtained using a non-contact method. Feature extraction from the whole facial area is expected improve the accuracy in estimating blood pressure. In this study, feature extraction related to blood pressure levels from facial skin temperature distribution using a deep learning algorithm was performed. As the result, features at nasal and lip regions were extracted as common features related to blood pressure levels. Furthermore, a possibility for proposal of a general model for estimating blood pressure levels using the common features was shown. © 2019 The Institute of Electrical Engineers of Japan.

引用

页码：759 / 765

页数：6

共 23 条

[1]

Nishimura R.A., Otto C.M., Bonow R.O., Carabello B.A., Erwin J.P., Fleisher L.A., Jneid H., Mack M.J., McLeod C.J., O'Gara P.T., Rigolin V.H., Sundt T.M., Thompson A., 2017 AHA/ACC focused update of the 2014 AHA/ACC guideline for the management of patients with valvular heart disease, Journal of the American College of Cardiology, 70, 2, pp. 252-289, (2017)

[2]

Cobos B., Haskard-Zolnierek K., White coat hypertension: Improving the Patient-health Care Practitioner Relationship, Psychology Research and Behavior Management, 8, pp. 133-141, (2015)

[3]

Stergiou G.S., Selgami E.V., Tzamourains D.G., Roussias L.G., Masked hypertension assessed by ambulatory blood pressure versus home blood pressure monitoring: Is it the same phenomenon?, American Journal of Hypertension, 18, 6, pp. 772-778, (2005)

[4]

Jonathan E., Leahy M., Investigating a smartphone imaging unit for photoplethysmography, Physiological Measurement, 31, (2010)

[5]

Scully C.G., Lee J., Meyer J., Gorbach A.M., Granquist-Fraser D., Mendel-Son Y., Chon K.H., Physiological parameter monitoring from optical recordings with a mobile phone, IEEE Transactions on Biomedical Engineering, 59, pp. 303-306, (2012)

[6]

Chandrasekaran V., Dantu R., Jonnada S., Thiyagaraja S., Subbu K.P., Cuffless differential blood pressure estimation using smart phones, IEEE Transactions on Biomedical Engineering, 60, pp. 1080-1089, (2013)

[7]

Peng R.C., Zhou X.L., Lin W.H., Zhang Y.T., Extraction of heart rate variability from smartphone photoplethysmograms, Computational and Mathematical Methods in Medicine, 2015, (2015)

[8]

Jain M., Deb S., Subramanyam A.V., Face video based touchless blood pressure and heart rate estimation, Multimedia Signal Processing (MMSP), 2016 IEEE 18th International Workshop on, pp. 1-5, (2016)

[9]

Uppal G., Prakash N.R., Kalra P., Heart rate measurement using facial videos, Advances in Computational Sciences and Technology, 10, 8, pp. 2343-2357, (2017)

[10]

Nozawa A., Karita K., Emotion spectrum analysis for a daily repetitive mental workload, Arti Cial Life and Robotics, 15, pp. 316-319, (2010)

← 1 2 3 →