support vector machine (SVM);
multiclass classification by error correcting output code (ECOC);
rejection;
fluorescence in situ hybridization (FISH);
genetics;
D O I:
10.1016/j.patrec.2004.09.048
中图分类号:
TP18 [人工智能理论];
学科分类号:
081104 ;
0812 ;
0835 ;
1405 ;
摘要:
We implement structural risk minimization and cross-validation in order to optimize kernel and parameters of a support vector machine (SVM) and multiclass SVM-based image classifiers, thereby enabling the diagnosis of genetic abnormalities. By thresholding the distance of patterns from the hypothesis separating the classes we reject a percentage of the miss-classified patterns reducing the expected risk. Accurate performance of the SVM in comparison to other state-of-the-art classifiers demonstrates the benefit of SVM-based genetic syndrome diagnosis. (c) 2004 Elsevier B.V. All rights reserved.