Title :
Combined Support Vector Novelty Detection for Multi-channel Combustion Data
Author :
Clifton, Lei A. ; Yin, Hujun ; Clifton, David A. ; Zhang, Yang
Author_Institution :
Manchester Univ., Manchester
Abstract :
Multi-channel combustion data, consisting of gas pressure and two combustion chamber luminosity measurements, are investigated in the prediction of combustion instability. Wavelet analysis is used for feature extraction. A SVM approach is applied for novelty detection and the construction of a model of normal system operation. Novelty scores generated by classifiers from different channels are combined to give a final decision of data novelty. We compare four novelty score combination mechanisms, and illustrate their complementary relationship in assessing data novelty.
Keywords :
combustion; mechanical engineering computing; support vector machines; wavelet transforms; SVM; combustion chamber; combustion instability; data novelty; feature extraction; gas pressure; luminosity measurement; multichannel combustion data; novelty score combination mechanism; support vector novelty detection; wavelet analysis; Cameras; Combustion; Data engineering; Feature extraction; Fuels; Power generation; Support vector machine classification; Support vector machines; Wavelength measurement; Wavelet analysis;
Conference_Titel :
Networking, Sensing and Control, 2007 IEEE International Conference on
Conference_Location :
London
Print_ISBN :
1-4244-1076-2
Electronic_ISBN :
1-4244-1076-2
DOI :
10.1109/ICNSC.2007.372828
