Feature selection and classification of pro-TOF data based on soft information

Lin Zhang; Jian Qiu Zhang; Xiao Bo Zhou; Hong Hui Wang; Yu Fei Huang; Hui Liu; Stephen Wong

doi:10.1109/ICMLC.2008.4621105

Feature selection and classification of pro-TOF data based on soft information

Lin Zhang, Jian Qiu Zhang, Xiao Bo Zhou, Hong Hui Wang, Yu Fei Huang, Hui Liu, Stephen Wong

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

Abstract

In this paper, we introduce a feature selection and classification method for prOTOF Mass Spectrometry (MS) data profiles of diseased and healthy patients. The method is based on a special statistical measure, which quantifies the probability of the existence of peptidepeaks. A special ranking score that is based on the statistical measure is used for selecting features that can best distinguish diseased and healthy data profiles. Based on the selected features, we applied a variety of classification algorithms and the results are compared with that of a method which selects features only based on peak heights. The results show a significant improvement in classification error rate with our proposed method.

Original language	English (US)
Title of host publication	Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC
Pages	4018-4023
Number of pages	6
DOIs	https://doi.org/10.1109/ICMLC.2008.4621105
State	Published - 2008
Event	7th International Conference on Machine Learning and Cybernetics, ICMLC - Kunming, China Duration: Jul 12 2008 → Jul 15 2008

Publication series

Name	Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC
Volume	7

Other

Other	7th International Conference on Machine Learning and Cybernetics, ICMLC
Country/Territory	China
City	Kunming
Period	7/12/08 → 7/15/08

ASJC Scopus subject areas

Artificial Intelligence
Human-Computer Interaction
Control and Systems Engineering

Access to Document

10.1109/ICMLC.2008.4621105

Cite this

Zhang, L., Zhang, J. Q., Zhou, X. B., Wang, H. H., Huang, Y. F., Liu, H., & Wong, S. (2008). Feature selection and classification of pro-TOF data based on soft information. In Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC (pp. 4018-4023). [4621105] (Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC; Vol. 7). https://doi.org/10.1109/ICMLC.2008.4621105

Feature selection and classification of pro-TOF data based on soft information. / Zhang, Lin; Zhang, Jian Qiu; Zhou, Xiao Bo et al.

Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC. 2008. p. 4018-4023 4621105 (Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC; Vol. 7).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Zhang, L, Zhang, JQ, Zhou, XB, Wang, HH, Huang, YF, Liu, H & Wong, S 2008, Feature selection and classification of pro-TOF data based on soft information. in Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC., 4621105, Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC, vol. 7, pp. 4018-4023, 7th International Conference on Machine Learning and Cybernetics, ICMLC, Kunming, China, 7/12/08. https://doi.org/10.1109/ICMLC.2008.4621105

Zhang L, Zhang JQ, Zhou XB, Wang HH, Huang YF, Liu H et al. Feature selection and classification of pro-TOF data based on soft information. In Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC. 2008. p. 4018-4023. 4621105. (Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC). https://doi.org/10.1109/ICMLC.2008.4621105

@inproceedings{a83913f09f9c4c3fb327fbe04facf546,

title = "Feature selection and classification of pro-TOF data based on soft information",

abstract = "In this paper, we introduce a feature selection and classification method for prOTOF Mass Spectrometry (MS) data profiles of diseased and healthy patients. The method is based on a special statistical measure, which quantifies the probability of the existence of peptidepeaks. A special ranking score that is based on the statistical measure is used for selecting features that can best distinguish diseased and healthy data profiles. Based on the selected features, we applied a variety of classification algorithms and the results are compared with that of a method which selects features only based on peak heights. The results show a significant improvement in classification error rate with our proposed method.",

author = "Lin Zhang and Zhang, {Jian Qiu} and Zhou, {Xiao Bo} and Wang, {Hong Hui} and Huang, {Yu Fei} and Hui Liu and Stephen Wong",

year = "2008",

doi = "10.1109/ICMLC.2008.4621105",

language = "English (US)",

isbn = "9781424420964",

series = "Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC",

pages = "4018--4023",

booktitle = "Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC",

}

TY - GEN

T1 - Feature selection and classification of pro-TOF data based on soft information

AU - Zhang, Lin

AU - Zhang, Jian Qiu

AU - Zhou, Xiao Bo

AU - Wang, Hong Hui

AU - Huang, Yu Fei

AU - Liu, Hui

AU - Wong, Stephen

PY - 2008

Y1 - 2008

N2 - In this paper, we introduce a feature selection and classification method for prOTOF Mass Spectrometry (MS) data profiles of diseased and healthy patients. The method is based on a special statistical measure, which quantifies the probability of the existence of peptidepeaks. A special ranking score that is based on the statistical measure is used for selecting features that can best distinguish diseased and healthy data profiles. Based on the selected features, we applied a variety of classification algorithms and the results are compared with that of a method which selects features only based on peak heights. The results show a significant improvement in classification error rate with our proposed method.

AB - In this paper, we introduce a feature selection and classification method for prOTOF Mass Spectrometry (MS) data profiles of diseased and healthy patients. The method is based on a special statistical measure, which quantifies the probability of the existence of peptidepeaks. A special ranking score that is based on the statistical measure is used for selecting features that can best distinguish diseased and healthy data profiles. Based on the selected features, we applied a variety of classification algorithms and the results are compared with that of a method which selects features only based on peak heights. The results show a significant improvement in classification error rate with our proposed method.

UR - http://www.scopus.com/inward/record.url?scp=57749113709&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=57749113709&partnerID=8YFLogxK

U2 - 10.1109/ICMLC.2008.4621105

DO - 10.1109/ICMLC.2008.4621105

M3 - Conference contribution

AN - SCOPUS:57749113709

SN - 9781424420964

T3 - Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC

SP - 4018

EP - 4023

BT - Proceedings of the 7th International Conference on Machine Learning and Cybernetics, ICMLC

T2 - 7th International Conference on Machine Learning and Cybernetics, ICMLC

Y2 - 12 July 2008 through 15 July 2008

ER -

Feature selection and classification of pro-TOF data based on soft information

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this