Classification of Proteomic Signals by Block Kriging Error Matching

Authors:
Tuan D. Pham;Dominik Beck;Miriam Brandl;Xiaobo Zhou
Affiliations:
Bioinformatics Applications Research Center, James Cook University, Townsville, Australia QLD 4811;Bioinformatics Applications Research Center, James Cook University, Townsville, Australia QLD 4811;Bioinformatics Applications Research Center, James Cook University, Townsville, Australia QLD 4811;HCNR Center for Bioinformatics Harvard Medical School, , Boston, USA MA 02115
Venue:
ICISP '08 Proceedings of the 3rd international conference on Image and Signal Processing
Year:
2008

Citing 6
Cited 0

Fundamentals of speech recognition

Fundamentals of speech recognition
Sample classification from protein mass spectrometry, by 'peak probability contrasts'

Bioinformatics
Feature extraction and quantification for mass spectrometry in biomedical applications using the mean spectrum

Bioinformatics
Ovarian cancer identification based on dimensionality reduction for high-throughput mass spectrometry data

Bioinformatics
A machine learning perspective on the development of clinical decision support systems utilizing mass spectra of blood samples

Journal of Biomedical Informatics
Computational Prediction Models for Early Detection of Risk of Cardiovascular Events Using Mass Spectrometry Data

IEEE Transactions on Information Technology in Biomedicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

One of recent advances in biotechnology offers high-throughput mass-spectrometry data for disease detection, prevention, and biomarker discovery. In fact proteomics has recently become an attractive topic of research in biomedicine. Signal processing and pattern classification techniques are inherently essential for analyzing proteomic data. In this paper the estimation method of block kriging is utilized to derive an error matching strategy for classifying proteomic signals with a particular application to the prediction of cardiovascular events using clinical mass spectrometry data. The proposed block kriging based classification technique has been found to be superior to other recently developed methods.