Automatic Wheeze Detection using Dynamic Frequency Warping

• Main Authors: Kan-Ru Tsai, 蔡侃儒
• Other Authors: Kuo-Guau Wu
• Format: Others
• Language: zh-TW
• Published: 2011
• Online Access: http://ndltd.ncl.edu.tw/handle/26098489013069027947

碩士 === 國立中興大學 === 電機工程學系所 === 99 === Nowadays auscultation has been adopted by the physicians as easy, fast and noninvasive way to evaluate and diagnose patients with lung diseases, e.g. asthma (AS) and chronic obstructive pulmonary disease (COPD). Nevertheless, auscultation suffers from subjectivity and variability in the interpretation of its diagnostic information. In order to improve the quality of auscultation, automatic lung sound analysis employing digital signal processing techniques has attracted much attention recently. In this thesis, we will address the problem of automatic wheeze detection which is important for patients with AS. The main idea of the proposed algorithm is to employ the subband energy as the feature parameter and account for the frequency variation of the wheeze sound through dynamic frequency warping. Simulation results demonstrate that the proposed algorithm can achieve 100% wheeze detection for six lung sound databases.