| Paper: | BIO-P4.7 | ||
| Session: | Biomedical Signal Processing II | ||
| Time: | Friday, May 19, 14:00 - 16:00 | ||
| Presentation: | Poster | ||
| Topic: | Bio Imaging and Signal Processing: Biomedical signal processing | ||
| Title: | A NEW ALGORITHM FOR DETECTION OF S1 AND S2 HEART SOUNDS | ||
| Authors: | Dinesh Kumar, Paulo Carvalho, University of Coimbra, Portugal; Manual Antunes, University Hospital of Coimbra, Portugal; Paulo Gil, Jorge Henriques, University of Coimbra, Portugal; Luis Eugénio, University Hospital of Coimbra, Portugal | ||
| Abstract: | This paper presents a new algorithm for segmentation and classification of S1 and S2 heart sounds without ECG reference. The proposed approach is composed of three main stages. In the first stage the fundamental heart sound lobes are previously identified using a fast wavelet transform and the Shannon energy. Next, these lobes are validated and classified into S1 and S2 classes based on Mel-frequency coefficients and on a non supervised neural network. Finally, regular heart cycles are identified in a post-processing stage by a heart rhythm criterion. This approach was tested using sound samples collected from valve implanted patients. Results are comparable with ECG based approaches. | ||
©2018 Conference Management Services, Inc. -||- email: webmaster@icassp2006.org -||- Last updated Friday, August 17, 2012