Classification of hierarchically clustered and homomorphic segmented heart sounds using neural networks
Cardiac auscultation is widely used by physicians to evaluate cardiac functions in patients and detect the presence of abnormalities. Phonocardiogram signals (PCG) are heart signals which contain vital information about the heart and can be used effectively in diagnosing various pathological conditi...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Theses and Dissertations |
| Published: |
2008
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/5663 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Summary: | Cardiac auscultation is widely used by physicians to evaluate cardiac functions in patients and detect the presence of abnormalities. Phonocardiogram signals (PCG) are heart signals which contain vital information about the heart and can be used effectively in diagnosing various pathological conditions of heart valves. Computer- based analysis of heart sounds can be used for diagnostic purposes. This present study embarks on the development of an automatic diagnostic system for characterization of phonocardiogram signals which were hierarchically clustered and homomorphically segmented and classified using neural networks. There are three core parts to the system: (1) segmentation, (2) feature extraction, (3) classification. |
|---|