以獨立成份分析技術應用在心肺音分離之探討

Abstract

在醫院，聽診是內科醫生看診最常使用的行為。 最近， 為了發展遠端醫療和居家看護系統並且幫助內科醫生能有更正確診斷，電子聽診器和電腦軟體分析已經成為一個不可避免的趨勢。 不過，心音和肺音的兩信號不僅從同時由胸腔傳出而且有一些重疊範圍。 因此，為了避免這兩個聲音在分析計算時受到影響；分離心音與肺音變得必要而重要。獨立成分分析(ICA)是從1990發展起來的算法； 它高效率的能分開兩個聲音。 在這篇文章裡，我們使用兩個聽筒從左和右胸收集信號。 我們以ICA 算法成功分離模擬的心音和肺音。 它能幫助內科醫生檢查以及在遠距醫療和居家看護上使用。

In hospital, physician examine emphasizes with percussion and auscultations; and auscultation is the most common way for physical exam. Recently, in order to develop Tele-medicine and Home care system and to assist physician can have more correct diagnose by auscultation; electric stethoscope and computer analysis have become an inevitable trend. However, two physical signals which include with Heart sound and lung sound are both appear from chest and also have some overlapped spectrum diagram. So, in order avoid to users misplace or untrained of stethoscope using and makes these two sounds will effect each other during with computer analysis; to separate heart sound and lung sound become necessary and important. Independent component analysis (also called ICA) is an algorithm which developed from 1990; it can separate two sounds even above efficiency. In this paper, we use two microphones to collect signals from left and right chest. And we have successfully divide heart and lung sounds by Fast ICA algorithm. And it can assist physician examine and also using on Tele-medicine and Home care by this way.