Heart sound segmentation
This project first aim to create a signal processing MATLAB program that segment heart sounds by detecting the first heart sound (S1) and second heart sound (S2) and the heart cycle boundaries. However, in this project, only the S1 and S2 sounds are detected using the envelope segmentation methods w...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
2017
|
Subjects: | |
Online Access: | http://hdl.handle.net/10356/71993 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-71993 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-719932023-07-07T17:58:19Z Heart sound segmentation Manalo Daisy Grace Rivera Soh Cheong Boon School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering This project first aim to create a signal processing MATLAB program that segment heart sounds by detecting the first heart sound (S1) and second heart sound (S2) and the heart cycle boundaries. However, in this project, only the S1 and S2 sounds are detected using the envelope segmentation methods which includes Shannon Energy, Hilbert and Shannon Entropy with thresholding. These methods create an envelope of the signal to find the start and stop points of both S1 and S2. The threshold value is determined by finding the lowest Root Mean Square (RMS) Error calculated in a range of 0.01 to 0.02. The RMS Error is computed based on a manually recorded start and stop point and it is also used to find the best among the envelope detection methods. The envelope detection method was implemented to a normal heart sound and a heart sound with split S1. The Shannon Entropy method was deemed the best envelope detection method as it recorded the lowest total RMS error for both the normal and split S1 signal. Bachelor of Engineering 2017-05-23T07:08:43Z 2017-05-23T07:08:43Z 2017 Final Year Project (FYP) http://hdl.handle.net/10356/71993 en Nanyang Technological University 80 p. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
DRNTU::Engineering::Electrical and electronic engineering |
spellingShingle |
DRNTU::Engineering::Electrical and electronic engineering Manalo Daisy Grace Rivera Heart sound segmentation |
description |
This project first aim to create a signal processing MATLAB program that segment heart sounds by detecting the first heart sound (S1) and second heart sound (S2) and the heart cycle boundaries. However, in this project, only the S1 and S2 sounds are detected using the envelope segmentation methods which includes Shannon Energy, Hilbert and Shannon Entropy with thresholding. These methods create an envelope of the signal to find the start and stop points of both S1 and S2. The threshold value is determined by finding the lowest Root Mean Square (RMS) Error calculated in a range of 0.01 to 0.02. The RMS Error is computed based on a manually recorded start and stop point and it is also used to find the best among the envelope detection methods. The envelope detection method was implemented to a normal heart sound and a heart sound with split S1. The Shannon Entropy method was deemed the best envelope detection method as it recorded the lowest total RMS error for both the normal and split S1 signal. |
author2 |
Soh Cheong Boon |
author_facet |
Soh Cheong Boon Manalo Daisy Grace Rivera |
format |
Final Year Project |
author |
Manalo Daisy Grace Rivera |
author_sort |
Manalo Daisy Grace Rivera |
title |
Heart sound segmentation |
title_short |
Heart sound segmentation |
title_full |
Heart sound segmentation |
title_fullStr |
Heart sound segmentation |
title_full_unstemmed |
Heart sound segmentation |
title_sort |
heart sound segmentation |
publishDate |
2017 |
url |
http://hdl.handle.net/10356/71993 |
_version_ |
1772825159370014720 |