Biometric sample extraction using Mahalanobis distance in cardioid based graph using electrocardiogram signals
In this paper, a person identification mechanism implemented with Cardioid based graph using electrocardiogram (ECG) is presented. Cardioid based graph has given a reasonably good classification accuracy in terms of differentiating between individuals. However, the current feature extraction method...
Saved in:
Main Authors: | , |
---|---|
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2012
|
Subjects: | |
Online Access: | http://irep.iium.edu.my/31998/1/embc2012.pdf http://irep.iium.edu.my/31998/ http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6346694 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.iium.irep.31998 |
---|---|
record_format |
dspace |
spelling |
my.iium.irep.319982013-09-11T06:56:32Z http://irep.iium.edu.my/31998/ Biometric sample extraction using Mahalanobis distance in cardioid based graph using electrocardiogram signals Sidek, Khairul Azami Khalil, Ibrahim TK7885 Computer engineering In this paper, a person identification mechanism implemented with Cardioid based graph using electrocardiogram (ECG) is presented. Cardioid based graph has given a reasonably good classification accuracy in terms of differentiating between individuals. However, the current feature extraction method using Euclidean distance could be further improved by using Mahalanobis distance measurement producing extracted coefficients which takes into account the correlations of the data set. Identification is then done by applying these extracted features to Radial Basis Function Network. A total of 30 ECG data from MITBIH Normal Sinus Rhythm database (NSRDB) and MITBIH Arrhythmia database (MITDB) were used for development and evaluation purposes. Our experimentation results suggest that the proposed feature extraction method has significantly increased the classification performance of subjects in both databases with accuracy from 97.50% to 99.80% in NSRDB and 96.50% to 99.40% in MITDB. High sensitivity, specificity and positive predictive value of 99.17%, 99.91% and 99.23% for NSRDB and 99.30%, 99.90% and 99.40% for MITDB also validates the proposed method. This result also indicates that the right feature extraction technique plays a vital role in determining the persistency of the classification accuracy for Cardioid based person identification mechanism. 2012-08-28 Conference or Workshop Item REM application/pdf en http://irep.iium.edu.my/31998/1/embc2012.pdf Sidek, Khairul Azami and Khalil, Ibrahim (2012) Biometric sample extraction using Mahalanobis distance in cardioid based graph using electrocardiogram signals. In: 34th Annual International Conference of the IEEE EMBS, 28th August - 1st September 2012, San Diego, California. http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6346694 |
institution |
Universiti Islam Antarabangsa Malaysia |
building |
IIUM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
International Islamic University Malaysia |
content_source |
IIUM Repository (IREP) |
url_provider |
http://irep.iium.edu.my/ |
language |
English |
topic |
TK7885 Computer engineering |
spellingShingle |
TK7885 Computer engineering Sidek, Khairul Azami Khalil, Ibrahim Biometric sample extraction using Mahalanobis distance in cardioid based graph using electrocardiogram signals |
description |
In this paper, a person identification mechanism implemented with Cardioid based graph using electrocardiogram (ECG) is presented. Cardioid based graph has given a reasonably good classification accuracy in terms of differentiating between individuals. However, the current feature extraction method using Euclidean distance could be further improved by using Mahalanobis distance measurement producing extracted coefficients which takes into account the correlations of the data set. Identification is then done by applying these extracted features to Radial Basis Function Network. A total of 30 ECG data from MITBIH Normal Sinus Rhythm database (NSRDB) and MITBIH Arrhythmia database (MITDB) were used for
development and evaluation purposes. Our experimentation results suggest that the proposed feature extraction method has significantly increased the classification performance of subjects in both databases with accuracy from 97.50% to 99.80% in NSRDB and 96.50% to 99.40% in MITDB. High sensitivity, specificity and positive predictive value of 99.17%, 99.91% and 99.23% for NSRDB and 99.30%, 99.90% and 99.40% for MITDB also validates the proposed method. This result also indicates that the right feature extraction technique plays a vital role in determining the persistency of the classification accuracy for Cardioid based person identification mechanism. |
format |
Conference or Workshop Item |
author |
Sidek, Khairul Azami Khalil, Ibrahim |
author_facet |
Sidek, Khairul Azami Khalil, Ibrahim |
author_sort |
Sidek, Khairul Azami |
title |
Biometric sample extraction using Mahalanobis distance in cardioid based graph using electrocardiogram signals |
title_short |
Biometric sample extraction using Mahalanobis distance in cardioid based graph using electrocardiogram signals |
title_full |
Biometric sample extraction using Mahalanobis distance in cardioid based graph using electrocardiogram signals |
title_fullStr |
Biometric sample extraction using Mahalanobis distance in cardioid based graph using electrocardiogram signals |
title_full_unstemmed |
Biometric sample extraction using Mahalanobis distance in cardioid based graph using electrocardiogram signals |
title_sort |
biometric sample extraction using mahalanobis distance in cardioid based graph using electrocardiogram signals |
publishDate |
2012 |
url |
http://irep.iium.edu.my/31998/1/embc2012.pdf http://irep.iium.edu.my/31998/ http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6346694 |
_version_ |
1643610107861270528 |
score |
13.160551 |