Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/40685
Title: Automatic bio sound detection and classification
Authors: Chua, Bor Jenq.
Keywords: DRNTU::Engineering::Electrical and electronic engineering::Electronic systems
Issue Date: 2010
Abstract: 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.
URI: http://hdl.handle.net/10356/40685
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
E5066-091.pdf
  Restricted Access
1.37 MBAdobe PDFView/Open

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.