以往國人對於醫療的認知還是停留在醫院內醫生必須直接面對病人做診斷，但近年來，國人對於醫療與人性化的概念有了更深一層的認識，並且將這兩者做了結合，所以對病人而言，他們的生活空間並不僅僅被侷限在醫院內，更可以是在家中或是戶外，而這些進步大大的改善了病人的生活方式，但此進步必須建立於遠端醫療與居家看護系統的發展上，有鑑於此，最重要的就是要精確的知道病人的現在身體狀況以供遠端醫院的醫生做即時診斷，以患有心血管疾病的人來說，要知道他的心臟狀況,就必須靠著心電圖(Electrocardiogram，ECG)讓醫生做判斷，但是由於人體在活動中會產生許多訊號，例如:肌電訊號(Electromyography，EMG）等，甚至機器等會帶有電力線的雜訊干擾，所以要如何從量測到的訊號中正確的分離出ECG訊號或其他生理訊號則是此篇文章的重點。
獨立成份分析法(Independent Component Analysis，ICA)[1]最初發展出來約在1990年，在這裡我們使用獨立成份分析法即時的對於所量測到的訊號作來源訊號的分離與重建，量測訊號取得我們使用六個電極貼片分別貼在兩隻手前臂前端內側，期間我們嘗試做簡單的擺動手臂，拿東西等一些動作，然後使用獨立成份分析法去作即時分離我們所量測到的訊號，結果我們成功的分離出正確的ECG訊號，相信此舉對於遠端醫療與居家看護系統的發展相信能提供一大助力。

With the developments of advanced medical instruments in recent years, the remote medicine and homecare system have been recognized as a new trend in the interaction between patients and doctors. This trend changes the life style of care medicine. Patients can use advanced nursing systems to record their physiological data at home and transmit these data to hospital network for necessarily monitoring. Nevertheless, these achievements require the novel developments of medical instruments, especially the noise-proof performance of these instruments.
In this study, we aim to develop an Independent Component Analysis (ICA)-based ECG care system. ICA is a multi-variable technique which has been validated as a powerful tool for separating different signals according to their distinct statistical distributions. With the benefit of ICA, physiological and environmental ECG-unrelated noise can be removed so that the ECG signals can be extracted in low signal-to-noise (SNR) situation, even during uses’s limb movements. In order to validate the performance of the proposed ICA-based system, we attached six ECG electrodes (three on left hand and the other three on right hand) to extract the surface ECG of a user. ECG-unrelated noise and physiological signals, such as 60 Hz electricity noise, low frequency drifts and electromyogram contaminations can be identified and removed. Currently, we have implemented the ICA-based ECG care system on Labview platform for real-time processing. Further developments are required to realize the technique using dsPIC microprocessor for portable homecare purposes..

參考文獻
[1].T .W. Lee, Independent Component Analysis: Theory and Applications, Kluwer Academic Publishers, Boston, MA, 1998.
[2].行政院衛生署國民健康局，。http://www.bhp.doh.gov.tw/BHPnet/Portal/.
[3].A. Hyvärinen, J. Karhunen and E. Oja, Independent Component Analysis, John Wiley & Sons, Inc., New York, 2001.
[4].R. Vigário, J. Särelä, V. Jousmäki, M. Hämäläinen, and E. Oja, “Independent Component Approach to the Analysis of EEG and MEG Recording,” IEEE Trans. Biomed. Eng., vol. 47, pp.589-593, 2000.
[5].Koredianto Usman et al, “A Study of Heartbeat Sound Separation Using Independent Component Analysis Technique”, IEEE 6th International Workshop on
[6].L. De Lathauwer, B. De Moor, and J. Vandewalle, “Fetal Electrocardio- gram Extraction by Blind Source Subspace Separation,” IEEE Trans. Biomed. Eng., vol. 47, pp.567-572, 2000.
[7].馬偕紀念院, http//www.mmh.org.tw/taitam/csc/doc/ekgbasic.htm.
[8].Frank G. Yanowitz, M.D.,1997. http://www.pharmacology2000.com/Cardio/Cardio_risk/adult_cardiac_procedures/anatomy3.htm.
[9].李玉菁 何杏棻等人，人體解剖學，文京圖書有限公司，1996。
[10].A. Hyvarinene and E. Oja, “Independent Component Analysis: Algorithms and Applications Neural Networks”, vol. 13, pp. 411-430, 2000.
[11].T. W. Lee, M. S. Lewicki and T. J. Sejnowski, “ICA mixture models for unsupervised classification of non-gaussian classes and automatic context switching in blind signal separation”, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, pp.1078-1089, 2000.
[12].Roy D. Yates and David J. Goodman, PROBILITY AND STOCHASTIC PROCESS, John Wiley & Sons, Inc., New York, 1999.
[13].生訊科技股份有限公司, http://www.bios ensetek.com/Cindex.html.
[14].12導心電圖機, ensetek.com/productECG.html.
[15].http://search.ni.com/nise arch/main/p?q=USB+6259.
[16].NI USB-6259, http://sine.ni.com/nips/cds/view/p/lang/en/nid/202598.