Hybrid SVM - Random Forest classication system for oral cancer screening using LIF spectra

Rahul Kumar Singh, Sarif Kumar Naik, Lalit Gupta, Srinivasan Balakrishnan, C. Santhosh, Keerthilatha M. Pai

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

In this paper, a system for oral cancer screening using Laser Induced Fluorescence(LIF) has been developed. A hybrid approach of classication using Support Vector Machine (SVM) and Random Forest (RF) classier's is proposed. Performance of the classier is evaluated using several features types such as Wavelet, DFT, LDFT, ILDFT, DCT, LDCT and Slopes features. The most discriminating features are selected using Recursive Feature Elimination(RFE). Analysis of the problem of subset selection from SVM-RFE ranked list is also performed. The hybrid approach has been compared with stand-alone SVM, SVM-RFE and RF classiers. The proposed technique improves the performance of the classication system signicantly. The novelty of the approach lies in the way the most signicant features are exstracted in separate modules to arrive at a decision and how the decision are then fused in an intelligent fashion to arrive at a final classication.

Original languageEnglish
Title of host publication2008 19th International Conference on Pattern Recognition, ICPR 2008
Publication statusPublished - 01-12-2008
Event2008 19th International Conference on Pattern Recognition, ICPR 2008 - Tampa, FL, United States
Duration: 08-12-200811-12-2008

Conference

Conference2008 19th International Conference on Pattern Recognition, ICPR 2008
CountryUnited States
CityTampa, FL
Period08-12-0811-12-08

Fingerprint

Support vector machines
Screening
Fluorescence
Lasers
Discrete Fourier transforms

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Cite this

Singh, R. K., Naik, S. K., Gupta, L., Balakrishnan, S., Santhosh, C., & Pai, K. M. (2008). Hybrid SVM - Random Forest classication system for oral cancer screening using LIF spectra. In 2008 19th International Conference on Pattern Recognition, ICPR 2008 [4761357]
Singh, Rahul Kumar ; Naik, Sarif Kumar ; Gupta, Lalit ; Balakrishnan, Srinivasan ; Santhosh, C. ; Pai, Keerthilatha M. / Hybrid SVM - Random Forest classication system for oral cancer screening using LIF spectra. 2008 19th International Conference on Pattern Recognition, ICPR 2008. 2008.
@inproceedings{a98b82a7e7fd44b2b63ad5fb0fc69e2c,
title = "Hybrid SVM - Random Forest classication system for oral cancer screening using LIF spectra",
abstract = "In this paper, a system for oral cancer screening using Laser Induced Fluorescence(LIF) has been developed. A hybrid approach of classication using Support Vector Machine (SVM) and Random Forest (RF) classier's is proposed. Performance of the classier is evaluated using several features types such as Wavelet, DFT, LDFT, ILDFT, DCT, LDCT and Slopes features. The most discriminating features are selected using Recursive Feature Elimination(RFE). Analysis of the problem of subset selection from SVM-RFE ranked list is also performed. The hybrid approach has been compared with stand-alone SVM, SVM-RFE and RF classiers. The proposed technique improves the performance of the classication system signicantly. The novelty of the approach lies in the way the most signicant features are exstracted in separate modules to arrive at a decision and how the decision are then fused in an intelligent fashion to arrive at a final classication.",
author = "Singh, {Rahul Kumar} and Naik, {Sarif Kumar} and Lalit Gupta and Srinivasan Balakrishnan and C. Santhosh and Pai, {Keerthilatha M.}",
year = "2008",
month = "12",
day = "1",
language = "English",
isbn = "9781424421756",
booktitle = "2008 19th International Conference on Pattern Recognition, ICPR 2008",

}

Singh, RK, Naik, SK, Gupta, L, Balakrishnan, S, Santhosh, C & Pai, KM 2008, Hybrid SVM - Random Forest classication system for oral cancer screening using LIF spectra. in 2008 19th International Conference on Pattern Recognition, ICPR 2008., 4761357, 2008 19th International Conference on Pattern Recognition, ICPR 2008, Tampa, FL, United States, 08-12-08.

Hybrid SVM - Random Forest classication system for oral cancer screening using LIF spectra. / Singh, Rahul Kumar; Naik, Sarif Kumar; Gupta, Lalit; Balakrishnan, Srinivasan; Santhosh, C.; Pai, Keerthilatha M.

2008 19th International Conference on Pattern Recognition, ICPR 2008. 2008. 4761357.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Hybrid SVM - Random Forest classication system for oral cancer screening using LIF spectra

AU - Singh, Rahul Kumar

AU - Naik, Sarif Kumar

AU - Gupta, Lalit

AU - Balakrishnan, Srinivasan

AU - Santhosh, C.

AU - Pai, Keerthilatha M.

PY - 2008/12/1

Y1 - 2008/12/1

N2 - In this paper, a system for oral cancer screening using Laser Induced Fluorescence(LIF) has been developed. A hybrid approach of classication using Support Vector Machine (SVM) and Random Forest (RF) classier's is proposed. Performance of the classier is evaluated using several features types such as Wavelet, DFT, LDFT, ILDFT, DCT, LDCT and Slopes features. The most discriminating features are selected using Recursive Feature Elimination(RFE). Analysis of the problem of subset selection from SVM-RFE ranked list is also performed. The hybrid approach has been compared with stand-alone SVM, SVM-RFE and RF classiers. The proposed technique improves the performance of the classication system signicantly. The novelty of the approach lies in the way the most signicant features are exstracted in separate modules to arrive at a decision and how the decision are then fused in an intelligent fashion to arrive at a final classication.

AB - In this paper, a system for oral cancer screening using Laser Induced Fluorescence(LIF) has been developed. A hybrid approach of classication using Support Vector Machine (SVM) and Random Forest (RF) classier's is proposed. Performance of the classier is evaluated using several features types such as Wavelet, DFT, LDFT, ILDFT, DCT, LDCT and Slopes features. The most discriminating features are selected using Recursive Feature Elimination(RFE). Analysis of the problem of subset selection from SVM-RFE ranked list is also performed. The hybrid approach has been compared with stand-alone SVM, SVM-RFE and RF classiers. The proposed technique improves the performance of the classication system signicantly. The novelty of the approach lies in the way the most signicant features are exstracted in separate modules to arrive at a decision and how the decision are then fused in an intelligent fashion to arrive at a final classication.

UR - http://www.scopus.com/inward/record.url?scp=77957966709&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77957966709&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:77957966709

SN - 9781424421756

BT - 2008 19th International Conference on Pattern Recognition, ICPR 2008

ER -

Singh RK, Naik SK, Gupta L, Balakrishnan S, Santhosh C, Pai KM. Hybrid SVM - Random Forest classication system for oral cancer screening using LIF spectra. In 2008 19th International Conference on Pattern Recognition, ICPR 2008. 2008. 4761357