Variable Selection in Proteomic Profile Classification by Interval Support Vector Machines (iSVM)

Abstract:

For variable selection in proteomic profile classification, we present a new local modeling procedure called interval support vector machine (iSVM). This procedure builds a series of SVM models in a window that moves over the whole spectral region and then locates useful spectral intervals in terms of the least complexity of SVM models reaching a desired error level. We applied iSVM in variable selection for proteomic profile classification. The results show that the proposed procedure are very promising for classification target-based variable selection and obtain much better classification than full-spectrum SVM model.

• Periodical: Applied Mechanics and Materials (Volumes 556-562)
• Pages: 347-350
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.556-562.347
• Online since: May 2014
• Authors: Xiao Li Yang*, Huan Yun He
• Keywords: Classification, Interval SVM, Proteomic Profile, Variable Selection

References

[1] E.P. Diamandis: Clinical Chemistry Vol. 49(2003), p.1272.

[2] E.F. Petricoin and L.A. Liotta: Current Opinion in Biotechnology Vol. 15(2004), p.24.

[3] K.P. Rosenblatt, P.B. Greenwood, J.K. Killian and A. Mehta: Annual Review of Medicine Vol. 55(2004), p.97.

[4] K.R. Kozak, M.W. Amneus and S.M. Pusey: PNAS Vol. 100, p.12343.

[5] J.F. Timms, E.A. Low and A.G. Maharaj: Clinical Chemistry Vol. 53(2007), p.645.

[6] E.F. Petricoin and L.A. Liotta: Current Opinion in Biotechnoloty Vol. 15(2004), p.24.

[7] V. Centner, D. Massart and O.E. de Noord: Anal. Chem Vol. 68(1996), p.3851.

[8] L. Nørgaard, A. Saudland and J. Wagner: Applied Spectroscopy Vol. 54(2000), p.413.

[9] X. Yang and Y. Yang: Computers and Applied Chemistry Vol. 27(2010), p.1498.

[10] C. Cortes and V. Vapnik: Machine Learning Vol. 20(1995), p.273.

[11] J.A.K. Suykens and J. Vandewalle: Neural Processing Letters Vol. 9(1999), p.293.

[12] M. Kearns and D. Ron: Neural Computation Vol. 11 (1999), p.1427.