Abstract: Radial pulse waveform contains massive cardiovascular pathophysiological messages from the hemodynamic perspective, which makes it promising in intelligent monitoring of cardiovascular health status. However, the instability of signal sampling leads a series of morphologic distortion causing mistakes in further intelligent analysis. Towards wearable monitoring device to realize intelligent analysis of Sphygmogram (SPG) acquired from radial artery, a morphologic distortion percolator is purposed to obtain qualified SPG. The presented percolator takes advantage of waveform segmentation and similarity analysis through novel reverse order correlation method. 179 stored records of 83 subjects, including 13 normal people and 70 patients, which are collected from our research group and collaborative hospital, were used for evaluation. For the filtration result, the worst error rate and sensitivity of percolator were 11.53% and 96.15%, respectively.

• Publication Date: 02-Jun-2014
• DOI: 10.15224/978-1-63248-009-5-101
• Views: 0
• Downloads: 0

Abstract: 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.

• Publication Date: 02-Jun-2014
• DOI: 10.15224/978-1-63248-009-5-102
• Views: 0
• Downloads: 0