Despite the popularity of SVMs in the data mining and machine learning communities, applying them to real world classification problems often confronts another obstacle, that is, the barrier of understanding and interpreting the results. For example, physicians may want to use the classification techniques of SVM for early diagnosis of diabetic patients. However, if the classification model generates the diagnosis result without an explanation of why or how, physicians may not appreciate or trust the result. As another example, pharmacologists are given an SVM model that accurately classifies active drugs from non-active drugs for a symptom, but the model may not be useful to them if it does not explain which components in the drug play the key roles.
Our proposed technique discovers discriminative feature combinations using SVM models. It effectively captured the feature combinations on a drug activity dataset. We also developed Localized Radial Basis Function (L-RBF) kernels to visualize discriminative features for nonlinear SVM models. Our system captures and visualizes important factors for a disease, which presents valuable information to physicians.
H. Yu, J. Yang, W. Wang & J. Han, "Discovering Compact and Highly Discriminative Features or Feature Combinations of Drug Activities Using Support Vector Machines", Proc. of IEEE Computer Society Bioinformatics Conf., 2003. (CSB'03 full paper, 18.5% accepted) [pdf]
DM - Data Mining Lab, Department of Computer Science and Engineering, Pohang University of Science and Technology
Copyright (c) 2008-2009 POSTECH Data Mining Lab, All Rights Reserved.