Abstract | ||
---|---|---|
Mass spectrometry is being used to generate protein profiles from human serum, and proteomic data obtained from mass spectrometry have attracted great interest for the detection of early-stage cancer. However, high dimensional mass spectrometry data cause considerable challenges. In this paper a set of wavelet detail coefficients at different levels is used to characterize the localized changes of mass spectrometry data and reduce dimensionality of mass spectra. The experiments are performed on high resolution ovarian dataset. A highly competitive accuracy compared to the best performance of other kinds of classification models is achieved. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1007/978-3-540-74771-0_22 | LSMS (2) |
Keywords | Field | DocType |
high dimensional mass spectrometry,competitive accuracy,feature extraction,classification model,considerable challenge,high resolution ovarian dataset,mass spectrum,mass spectrometry,best performance,proteomic data,mass spectrometry data,mass spectra,high resolution | Analytical chemistry,Pattern recognition,Support vector machine,Mass spectrum,Chemistry,Feature extraction,Curse of dimensionality,Artificial intelligence,Discrete wavelet transform,Mass spectrometry,Linear discriminant analysis,Wavelet | Conference |
Volume | ISSN | ISBN |
4689 | 0302-9743 | 3-540-74770-2 |
Citations | PageRank | References |
3 | 0.44 | 9 |
Authors | ||
1 |