Machine Learning in DNA Microarray Analysis for Cancer Classification
S. Cho, und H. Won. Proceedings of the First Asia-Pacific bioinformatics conference on Bioinformatics, (2003)
Zusammenfassung
The development of microarray technology has supplied a large
volume of data to many fields. In particular, it has been applied
to prediction and diagnosis of cancer, so that it expectedly helps
us to exactly predict and diagnose cancer. To precisely classify
cancer we have to select genes related to cancer because
extracted genes from microarray have many noises. In this paper,
we attempt to explore many features and classifiers using three
benchmark datasets to systematically evaluate the performances
of the feature selection methods and machine learning classifiers.
Three benchmark datasets are Leukemia cancer dataset, Colon
cancer dataset and Lymphoma cancer data set. Pearson’s and
Spearman’s correlation coefficients, Euclidean distance, cosine
coefficient, information gain, mutual information and signal to
noise ratio have been used for feature selection. Multi-layer
perceptron, k-nearest neighbour, support vector machine and
structure adaptive self–organizing map have been used for
classification. Also, we have combined the classifiers to improve
the performance of classification. Experimental results show that
the ensemble with several basis classifiers produces the best
recognition rate on the benchmark dataset.
%0 Journal Article
%1 citeulike:1154929
%A Cho, Sung-Bae
%A Won, Hong-Hee
%D 2003
%J Proceedings of the First Asia-Pacific bioinformatics conference on Bioinformatics
%K unread
%P 189--198
%T Machine Learning in DNA Microarray Analysis for Cancer Classification
%U http://delivery.acm.org.ezproxy.lib.unimelb.edu.au/10.1145/830000/820213/p189-cho.pdf?key1=820213&key2=0643963711&coll=GUIDE&dl=GUIDE,ACM&CFID=13428846&CFTOKEN=25868078
%V 19
%X The development of microarray technology has supplied a large
volume of data to many fields. In particular, it has been applied
to prediction and diagnosis of cancer, so that it expectedly helps
us to exactly predict and diagnose cancer. To precisely classify
cancer we have to select genes related to cancer because
extracted genes from microarray have many noises. In this paper,
we attempt to explore many features and classifiers using three
benchmark datasets to systematically evaluate the performances
of the feature selection methods and machine learning classifiers.
Three benchmark datasets are Leukemia cancer dataset, Colon
cancer dataset and Lymphoma cancer data set. Pearson’s and
Spearman’s correlation coefficients, Euclidean distance, cosine
coefficient, information gain, mutual information and signal to
noise ratio have been used for feature selection. Multi-layer
perceptron, k-nearest neighbour, support vector machine and
structure adaptive self–organizing map have been used for
classification. Also, we have combined the classifiers to improve
the performance of classification. Experimental results show that
the ensemble with several basis classifiers produces the best
recognition rate on the benchmark dataset.
@article{citeulike:1154929,
abstract = {The development of microarray technology has supplied a large
volume of data to many fields. In particular, it has been applied
to prediction and diagnosis of cancer, so that it expectedly helps
us to exactly predict and diagnose cancer. To precisely classify
cancer we have to select genes related to cancer because
extracted genes from microarray have many noises. In this paper,
we attempt to explore many features and classifiers using three
benchmark datasets to systematically evaluate the performances
of the feature selection methods and machine learning classifiers.
Three benchmark datasets are Leukemia cancer dataset, Colon
cancer dataset and Lymphoma cancer data set. Pearson’s and
Spearman’s correlation coefficients, Euclidean distance, cosine
coefficient, information gain, mutual information and signal to
noise ratio have been used for feature selection. Multi-layer
perceptron, k-nearest neighbour, support vector machine and
structure adaptive self–organizing map have been used for
classification. Also, we have combined the classifiers to improve
the performance of classification. Experimental results show that
the ensemble with several basis classifiers produces the best
recognition rate on the benchmark dataset.},
added-at = {2007-03-12T11:26:06.000+0100},
author = {Cho, Sung-Bae and Won, Hong-Hee},
biburl = {https://www.bibsonomy.org/bibtex/23a33f9ab910165e04558e4c0d5ebbd47/hohkhkh1},
citeulike-article-id = {1154929},
interhash = {87a37f7cfcb2ea5a00f301bf3a7b3654},
intrahash = {3a33f9ab910165e04558e4c0d5ebbd47},
journal = {Proceedings of the First Asia-Pacific bioinformatics conference on Bioinformatics},
keywords = {unread},
pages = {189--198},
priority = {3},
timestamp = {2007-03-12T11:37:46.000+0100},
title = {Machine Learning in DNA Microarray Analysis for Cancer Classification},
url = {http://delivery.acm.org.ezproxy.lib.unimelb.edu.au/10.1145/830000/820213/p189-cho.pdf?key1=820213\&key2=0643963711\&coll=GUIDE\&dl=GUIDE,ACM\&CFID=13428846\&CFTOKEN=25868078},
volume = 19,
year = 2003
}