透過您的圖書館登入
IP:18.190.155.49
  • 期刊

以呼吸聲頻之數位訊號作哮喘病徵之辨識

The Use of the Digital Breathing Frequency Signal for Wheezing Recognition

摘要


氣喘,又稱為哮喘,是一種慢性支氣管發炎的病症。一般常以聽診器經過醫師等專業的醫護人員聽取肺音作診斷,就肺音而言,常以哮喘音為典型的氣喘發作特徵。臺灣醫護人員的人力不足以及看護工或家庭照顧者並沒有氣喘方面的專業知識,因此,本研究的目的在於建立一套可以應用於居家照護或長時間監測氣喘發作的小型裝置。本研究藉由工研院所開發之軟性駐極體裝置,經由頸部擷取肺音訊號,再加上來自於網路資源的哮喘音檔案,利用數位訊號處理之時頻分析,偵測出異常的肺音,進而判斷哮喘發作之特徵。在時頻分析方面,本研究採用了希爾伯特黃轉換(Hilbert-Huang Transform)、短時傅立葉轉換(Short-Time Fourier Transform)及自相關函數(AutoCorrelation Function),三種方法去分析並比較其結果。由於本研究的目的在於居家照護與監測氣喘發作,故需要在短時間內辨識出結果,然而本研究所使用的肺音檔案取樣頻率過大亦即時間點數過多,造成龐大的計算量,因此,經由帶通濾波器濾除雜訊並重新取樣後降低計算量,取樣頻率統一為2,000 Hz,大大加快了辨識的計算時間。本論文主要以電腦呼吸音分析(ComputerizedRespiratory Sound Analysis, CORSA)定義哮喘音之標準為基礎,正確率分別為希爾伯特黃轉換法94.83%,自相關函數法93.1%,短時傅立葉轉換法91.38%。

關鍵字

肺音 哮喘音 HHT STFT ACF

並列摘要


Asthma is a common chronic inflammatory disease. Through the stethoscope the characteristics of lung sounds are taken for diagnosis by physicians usually. Wheezing is a typical feature of asthma attack. The purpose of this study is to establish a small device for asthma attack monitoring in long-term care. In these study three methods, say, the Hilbert-Huang Transform (HHT), the Auto Correlation Function (ACF) and the Short Time Fourier Transform (STFT) are used to detect the threshold of Wheezing for medical alarm. The criterion for wheezing suggested by the Computerized Respiratory Sound Analysis (CORSA) was adopted in this study. The experimental result shows that the identification rate is about 94.83% for HHT, 93.1% for ACF and 91.38% for STFT respectively. In the future we can make a homecare service embedded system and monitoring patients as long as possible.

並列關鍵字

Lung Sound Wheeze HHT STFT ACF

延伸閱讀