Cause-effect relationships and partially defined Boolean functions
Annals of Operations Research
Neural networks for pattern recognition
Neural networks for pattern recognition
An introduction to support Vector Machines: and other kernel-based learning methods
An introduction to support Vector Machines: and other kernel-based learning methods
An Implementation of Logical Analysis of Data
IEEE Transactions on Knowledge and Data Engineering
Pattern Classification (2nd Edition)
Pattern Classification (2nd Edition)
| Hi-index | 0.00 |
A parallel implementation of proteomic ovarian cancer diagnosis system based on logical analysis of data is shown. The implementation is based on computational cluster elaborated in System Engineering Group at Silesian University of Technology. For verification of algorithm and software Ovarian Dataset 8-7-02 (which can be found at http://clinicalproteomics.steem.com) was used. This mass spectrometry data contains intensity levels of 15 154 peptides defined by their mass/charge ratios (m/z) in serum of 162 ovarian cancer and 91 control cases. A Seti-like and OpenMosix with PVM cluster technology was used to construct in LAD a fully reproducible models (1) using full range and (2) using only 700-12000 of m/z values of peptides and proved in multiple cross-validation leave-one-out tests to guarantee sensitivities and specificities of up to 100 %.