A Timbre Model Based on Multidimensional Features for Analyzing Heart Sound

BINBIN, FU and GUANGPEI, LI and HAIYANG, WANG and MINGCHUI, DONG (2014) A Timbre Model Based on Multidimensional Features for Analyzing Heart Sound. In: International Conference on Advances in Bio-Informatics, Bio-Technology and Environmental Engineering - ABBE 2014, 01 - 02 June,2014, Westminster, London, UK.

20140708_054003.pdf - Published Version

Download (667kB) | Preview
Official URL: https://www.seekdl.org/conferences/paper/details/3...


Cardiovascular diseases (CVDs) are currently the leading cause of deaths worldwide. The traditional auscultation is cost-effective and time-saving for the public to diagnose CVDs early. While many approaches in analysis of the heart sound (HS) signal from auscultation have been utilized successfully, few studies are focused on acoustic perspective to interpret the HS signal. This paper creatively proposes a timbre model to interpret HS with much more attentions on feature extractions combined with medical knowledge. The timbre model based on multidimensional features has three dimensions, which are spectral centroid (SC), log attack time (LAT) and temporal centroid (TC). The simulation experiments indicate that the proposed model is of use in HS feature extraction and its following CVD diagnosis.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: acoustics, feature extraction, Hilbert transform, spectral centroid, temporal centroid
Depositing User: Mr. John Steve
Date Deposited: 15 May 2019 12:35
Last Modified: 15 May 2019 12:35
URI: http://publications.theired.org/id/eprint/2372

Actions (login required)

View Item View Item