Data mining techniques for feature selection in blood cell recognition

The paper presents and compares the data mining techniques for selection of the diagnostic features in the problem of blood cell recognition in leukemia. Different techniques are compared, including the linear SVM ranking, correlation and statistical analysis of centers and variances of clusters corresponding to different classes. We have applied radial kernel SVM as the classifier. The results of recognition of 10 classes of cells are presented and discussed.

• Type: Conference
• Year: 2006
• Where: ESANN
• Authors: Tomasz Markiewicz, Stanislaw Osowski
• Keywords: Blood Cell Recognition, Data Mining Techniques, ESANN 2006, ESANN 2007, Radial Kernel Svm