[논문]Design of ICA to Extract Respiration Signal From PPG Signal

Lee, Ju-Won; Lee, Byeong-Ro

doi:10.6109/jicce.2011.9.2.220

Design of ICA to Extract Respiration Signal From PPG Signal 원문보기

International journal of maritime information and communication sciences, v.9 no.2, 2011년, pp.220 - 223

Lee, Ju-Won (Department of Medical Engineering, Andong Science College) , Lee, Byeong-Ro (Department of Electronics Engineering, Gyeongnam National University of Science and Technology)

Abstract ▼ AI-Helper

Respiration signal of the vital signs is an important parameter in clinical parts. To extract the respiration signal from PPG signal for mobile healthcare system is difficult because the bands of the motion artifacts and respiration in the frequency domain are overlapped. This study to improve this problem suggested a respiration extraction method using the independent component analysis and evaluated its performances. In results of evaluation, the ICA method showed better performance than LPF suggested recently.

주제어

AI 본문요약
AI-Helper

* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.

가설 설정

In this study, we consider the number of sensors equal to the number of sources and the observations are zero-meaned signals. To update an unmixing matrix W, the used leaning rule that is Informax learning rule [11] is as follows:

제안 방법

These methods are difficult to apply in the mobile healthcare system because it leads to users’ complaint. In this study, we proposed an ICA method to extract respiratory signal from PPG signal and evaluated its performance. In evaluation, the ICA method showed better performance than LPF with cutoff frequency 0.
The proposed method consisted of a band pass filter with bandwidth of 0.04~2[Hz], two’s envelope detection filter, low pass filter (fc=0.8[Hz]), PPG kernel, ICA, and a maximum correlation selector for selecting optimal respiration signal.
The estimated output from ICA is multi-channel output. Therefore, in this study we used a maximum correlation selector to extract an optimal respiration signal. The maximum correlation selector is to find a channel with the maximum coefficient by comparing a reference respiration signal and each ICA output signal as following equations:
5[Hz]. Therefore, the proposed method will provide the stable performance in extracting respiration signal from PPG signal.
These methods shown the good performance on PPG signals of a rest state, but performance on PPG signals included the motion artifacts is reduced. Therefore, this study suggests a method using the independent component analysis to extract the respiration applicable to mobile healthcare, and evaluate its performances.
In this problem, the goal is to separate a series of individual signals from observed mixtures [10]. To extract the respiration signal in the measured PPG signal, this study proposes a method using the ICA as shown in Fig. 1. The proposed method consisted of a band pass filter with bandwidth of 0.

대상 데이터

The used PPG signals are two’s signal of PhysioBank’s MIMIC databases that are signal 05500001 and 23700002 known as the standard clinical data.

이론/모형

In the study, the performance of the proposed method is evaluated by the algorithm programmed using MATLAB.

성능/효과

In this study, we proposed an ICA method to extract respiratory signal from PPG signal and evaluated its performance. In evaluation, the ICA method showed better performance than LPF with cutoff frequency 0.5[Hz]. Therefore, the proposed method will provide the stable performance in extracting respiration signal from PPG signal.
3, signal distortion of proposed method was smaller than LPF method. For a more detailed evaluation, we calculated Pearson’s correlation coefficients between reference signal and each output of LPF and ICA, and showed in Table I. In the results, the ICA method was higher than LPF method. Thus, we are considered that the proposed method than LPF will provide a more stable performance.

참고문헌 (11)

M. Folke, L. Cernerud, M. Ekstrom, B. Hok, "Critical review of non-invasive respiratory monitoring in medical care," Medical & Biological Engineering & Computing, Vol. 41, 2003.

상세보기
J. Muhlsteff, O. Such, R. Schmidt, M. Perkuhn, H. Reiter, et al, "Wearable approach for continuous ECG and activity patientmonitoring," Engineering in Medicine and Biology Society, 26th Annual International Conference of the IEEE, Volume 1, Issue, 1-5 Sept. pp. 2184-2187, 2004.
Yoshimura Takahiro; Yonezawa Yoshiharu; Maki Hiromichi; Ogawa Hidekuni; Hahn Allen W; Thayer Julian F; Caldwell W Morton, "A compact ECG R-R interval, respiration and activity recording system," Biomedical sciences instrumentation Vol. 39, pp. 204-207, 2003.

상세보기
Anders Johansson, PerAke Oberg, and Gunnar Sedin, "Monitoring of Heart And Respiratory Rate in Newborn Infants Using a New Photoplethysmographic Technique," Journal of Clinical Monitoring and Computing 15, pp. 461-467, 1999.

상세보기
L. Nillson, A. Johansson, and S. Kalman, "Respiration can be monitored by photoplethysmography with high sensitivity and specificity regardless of anaesthesia and ventilatory mode," Acta Anaesthesiol Scand; Vol. 49, pp.1157-1162, 2005.

상세보기
K. Nakajima, T. Tamura, T. Ohta, H. Miike, and P.A. Oberg, "Photoplethysmographic Measure-ment of Heart and Respiratory Rates Using Digital Filters," Engineering in Medicine and Biology Society, Proceedings of the 15th Annual International Conference of the IEEE, Oct 28-31, pp. 1006-1007, 1993.
Jonghwa Kim, Mincheol Whang, Kichang Nam, "PPG Filtering Method for Respiration Measurement in U-Health Care System," Journal of the Ergonomics Society of Korea, Vol. 27, No. 4, pp. 95-101, 2008.

원문보기 상세보기
J.W. Lee, B.R. Lee, G.K. Lee, " Heart Rate Estimation Based on PPG signal and Histogram Filter for Mobile Healthcare," Int. Journal of Maritime Information and Communication Science, Vol. 8, No. 1, pp.112-115, 2010
Johansson, A., Oberg, P.A. and Sedin, G., "Monitoring of heart and respiratory rates in newborn infants using a new photoplethys mographic technique," Journal of Clinical Monitoring and Computing, Vol. 15, pp. 461-467, 1999.

상세보기
FastICA, http://www.cis.hut.fi/projects/ica/fastica/
Te-Won Lee, Mark Girolami and Terrence J. Sejnowski, "Independent Component Analysis Using an Extended Infomax Algorithm for Mixed Subgaussian and Supergaussian Sources," Neural Computation, February 15, Vol. 11, No. 2, Pages 417-441, 1999.

상세보기

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증