Using the time-domain characterization for estimation continuous blood pressure via neural network method

Paul C.-P. Chao; Tse Yi Tu

doi:10.1115/ISPS2017-5471

Using the time-domain characterization for estimation continuous blood pressure via neural network method

Paul C.-P. Chao, Tse Yi Tu

Institute of Electrical and Control Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

The new method with back-propagation neural network is expected to be capable of continuous measurement of blood pressures with noninvasive, cuffless strain blood pressure sensor. The eight time-domain characterizations estimate systolic blood pressure and diastolic blood pressure via BPNN leading to a satisfactory accuracy of the BP sensor. The BP sensor is used on human wrist to collect the continuously pulse signal for measuring blood pressures. To assist the sensor, a readout circuit is devised with a Wheatstone bridge, amplifier, filter, and a digital signal processor. The results of SBP and DBP are 4.27±4.98 mmHg and 3.86±5.35 mmHg, respectively. The errors of blood pressure pass the criteria for Association for the Advancement of Medical Instrumentation (AAMI) method 2 and the British Hypertension Society (BHS) Grade B.

Original language	English
Title of host publication	ASME 2017 Conference on Information Storage and Processing Systems, ISPS 2017
Publisher	American Society of Mechanical Engineers
ISBN (Electronic)	9780791858103
DOIs	https://doi.org/10.1115/ISPS2017-5471
State	Published - 1 Jan 2017
Event	ASME 2017 Conference on Information Storage and Processing Systems, ISPS 2017 - San Francisco, United States Duration: 29 Aug 2017 → 30 Aug 2017

Publication series

Name	ASME 2017 Conference on Information Storage and Processing Systems, ISPS 2017

Conference

Conference	ASME 2017 Conference on Information Storage and Processing Systems, ISPS 2017
Country	United States
City	San Francisco
Period	29/08/17 → 30/08/17

Access to Document

10.1115/ISPS2017-5471

Fingerprint Dive into the research topics of 'Using the time-domain characterization for estimation continuous blood pressure via neural network method'. Together they form a unique fingerprint.

Cite this

Chao, P. C-P., & Tu, T. Y. (2017). Using the time-domain characterization for estimation continuous blood pressure via neural network method. In ASME 2017 Conference on Information Storage and Processing Systems, ISPS 2017 (ASME 2017 Conference on Information Storage and Processing Systems, ISPS 2017). American Society of Mechanical Engineers. https://doi.org/10.1115/ISPS2017-5471

@inproceedings{a08364d88af44bedb9eae718b7300c1c,

title = "Using the time-domain characterization for estimation continuous blood pressure via neural network method",

abstract = "The new method with back-propagation neural network is expected to be capable of continuous measurement of blood pressures with noninvasive, cuffless strain blood pressure sensor. The eight time-domain characterizations estimate systolic blood pressure and diastolic blood pressure via BPNN leading to a satisfactory accuracy of the BP sensor. The BP sensor is used on human wrist to collect the continuously pulse signal for measuring blood pressures. To assist the sensor, a readout circuit is devised with a Wheatstone bridge, amplifier, filter, and a digital signal processor. The results of SBP and DBP are 4.27±4.98 mmHg and 3.86±5.35 mmHg, respectively. The errors of blood pressure pass the criteria for Association for the Advancement of Medical Instrumentation (AAMI) method 2 and the British Hypertension Society (BHS) Grade B.",

author = "Chao, {Paul C.-P.} and Tu, {Tse Yi}",

year = "2017",

month = jan,

day = "1",

doi = "10.1115/ISPS2017-5471",

language = "English",

series = "ASME 2017 Conference on Information Storage and Processing Systems, ISPS 2017",

publisher = "American Society of Mechanical Engineers",

booktitle = "ASME 2017 Conference on Information Storage and Processing Systems, ISPS 2017",

note = "null ; Conference date: 29-08-2017 Through 30-08-2017",

}

Chao, PC-P & Tu, TY 2017, Using the time-domain characterization for estimation continuous blood pressure via neural network method. in ASME 2017 Conference on Information Storage and Processing Systems, ISPS 2017. ASME 2017 Conference on Information Storage and Processing Systems, ISPS 2017, American Society of Mechanical Engineers, ASME 2017 Conference on Information Storage and Processing Systems, ISPS 2017, San Francisco, United States, 29/08/17. https://doi.org/10.1115/ISPS2017-5471

Using the time-domain characterization for estimation continuous blood pressure via neural network method. / Chao, Paul C.-P.; Tu, Tse Yi.

ASME 2017 Conference on Information Storage and Processing Systems, ISPS 2017. American Society of Mechanical Engineers, 2017. (ASME 2017 Conference on Information Storage and Processing Systems, ISPS 2017).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Using the time-domain characterization for estimation continuous blood pressure via neural network method

AU - Chao, Paul C.-P.

AU - Tu, Tse Yi

PY - 2017/1/1

Y1 - 2017/1/1

N2 - The new method with back-propagation neural network is expected to be capable of continuous measurement of blood pressures with noninvasive, cuffless strain blood pressure sensor. The eight time-domain characterizations estimate systolic blood pressure and diastolic blood pressure via BPNN leading to a satisfactory accuracy of the BP sensor. The BP sensor is used on human wrist to collect the continuously pulse signal for measuring blood pressures. To assist the sensor, a readout circuit is devised with a Wheatstone bridge, amplifier, filter, and a digital signal processor. The results of SBP and DBP are 4.27±4.98 mmHg and 3.86±5.35 mmHg, respectively. The errors of blood pressure pass the criteria for Association for the Advancement of Medical Instrumentation (AAMI) method 2 and the British Hypertension Society (BHS) Grade B.

AB - The new method with back-propagation neural network is expected to be capable of continuous measurement of blood pressures with noninvasive, cuffless strain blood pressure sensor. The eight time-domain characterizations estimate systolic blood pressure and diastolic blood pressure via BPNN leading to a satisfactory accuracy of the BP sensor. The BP sensor is used on human wrist to collect the continuously pulse signal for measuring blood pressures. To assist the sensor, a readout circuit is devised with a Wheatstone bridge, amplifier, filter, and a digital signal processor. The results of SBP and DBP are 4.27±4.98 mmHg and 3.86±5.35 mmHg, respectively. The errors of blood pressure pass the criteria for Association for the Advancement of Medical Instrumentation (AAMI) method 2 and the British Hypertension Society (BHS) Grade B.

UR - http://www.scopus.com/inward/record.url?scp=85034823290&partnerID=8YFLogxK

U2 - 10.1115/ISPS2017-5471

DO - 10.1115/ISPS2017-5471

M3 - Conference contribution

AN - SCOPUS:85034823290

T3 - ASME 2017 Conference on Information Storage and Processing Systems, ISPS 2017

BT - ASME 2017 Conference on Information Storage and Processing Systems, ISPS 2017

PB - American Society of Mechanical Engineers

Y2 - 29 August 2017 through 30 August 2017

ER -

Chao PC-P, Tu TY. Using the time-domain characterization for estimation continuous blood pressure via neural network method. In ASME 2017 Conference on Information Storage and Processing Systems, ISPS 2017. American Society of Mechanical Engineers. 2017. (ASME 2017 Conference on Information Storage and Processing Systems, ISPS 2017). https://doi.org/10.1115/ISPS2017-5471