Automatic bio sound detection and classification

The use of ambulatory devices to detect heart diseases can help to save lives in times of a heart attack. The project investigates the use of the Support Vector Machine (SVM) and the Gaussian Mixture Model (GMM) classifiers to classify sound samples accurately, with the aim of producing an accurate...

Descrizione completa

Dettagli Bibliografici
Autore principale: Chua, Bor Jenq.
Altri autori: Li Xuejun
Natura: Final Year Project (FYP)
Lingua:English
Pubblicazione: 2010
Soggetti:
Accesso online:http://hdl.handle.net/10356/40685
_version_ 1826126482734317568
author Chua, Bor Jenq.
author2 Li Xuejun
author_facet Li Xuejun
Chua, Bor Jenq.
author_sort Chua, Bor Jenq.
collection NTU
description The use of ambulatory devices to detect heart diseases can help to save lives in times of a heart attack. The project investigates the use of the Support Vector Machine (SVM) and the Gaussian Mixture Model (GMM) classifiers to classify sound samples accurately, with the aim of producing an accurate ambulatory device in medical diagnosis. Features of sound data are extracted using the Mel-frequency cepstrum coefficients to be used in machine learning. Two of the top classifiers used in data mining technology today are the SVM and GMM. The SVM classifier makes use of a linearly separable hyperplane to classify data into different classes, while the GMM works by using a probabilistic model for density estimation, using probability density functions. This report investigates the accuracy of manually collected sound samples by running the programs of SVM and GMM through the use of Matlab.
first_indexed 2024-10-01T06:53:24Z
format Final Year Project (FYP)
id ntu-10356/40685
institution Nanyang Technological University
language English
last_indexed 2024-10-01T06:53:24Z
publishDate 2010
record_format dspace
spelling ntu-10356/406852023-07-07T17:08:59Z Automatic bio sound detection and classification Chua, Bor Jenq. Li Xuejun School of Electrical and Electronic Engineering A*STAR Institute for Infocomm Research Tran Huy Dat DRNTU::Engineering::Electrical and electronic engineering::Electronic systems The use of ambulatory devices to detect heart diseases can help to save lives in times of a heart attack. The project investigates the use of the Support Vector Machine (SVM) and the Gaussian Mixture Model (GMM) classifiers to classify sound samples accurately, with the aim of producing an accurate ambulatory device in medical diagnosis. Features of sound data are extracted using the Mel-frequency cepstrum coefficients to be used in machine learning. Two of the top classifiers used in data mining technology today are the SVM and GMM. The SVM classifier makes use of a linearly separable hyperplane to classify data into different classes, while the GMM works by using a probabilistic model for density estimation, using probability density functions. This report investigates the accuracy of manually collected sound samples by running the programs of SVM and GMM through the use of Matlab. Bachelor of Engineering 2010-06-18T01:49:23Z 2010-06-18T01:49:23Z 2010 2010 Final Year Project (FYP) http://hdl.handle.net/10356/40685 en Nanyang Technological University 59 p. application/pdf
spellingShingle DRNTU::Engineering::Electrical and electronic engineering::Electronic systems
Chua, Bor Jenq.
Automatic bio sound detection and classification
title Automatic bio sound detection and classification
title_full Automatic bio sound detection and classification
title_fullStr Automatic bio sound detection and classification
title_full_unstemmed Automatic bio sound detection and classification
title_short Automatic bio sound detection and classification
title_sort automatic bio sound detection and classification
topic DRNTU::Engineering::Electrical and electronic engineering::Electronic systems
url http://hdl.handle.net/10356/40685
work_keys_str_mv AT chuaborjenq automaticbiosounddetectionandclassification