Classifier Learning for Imbalanced Data with Varying Misclassification Costs A Comparison of kNN, SVM and Decision Tree Learning

This thesis theoretically discusses the abilities of three commonly used classifier learning methods and optimization techniques to copewith characteristics of real-world classification problems, more specifically varying misclassification costs, imbalanced data sets and varying degrees of hardness of class boundaries. From these discussions a universally applicable optimization framework is derived that successfully corrects the error-based inductive bias of classifier learning methods on image data within the domain of medical diagnosis. The framework was designed considering several points for improvement of common optimization techniques, such as modifying the optimization procedure for inducer-specific parameters, modifying input data implemented by an arcing algorithm, and combining classifiers of several classifier learning methods with different settings according to locally-adaptive, cost-sensitive voting schemes. The framework is designed to make the learning process cost-sensitive and enforcing more balanced misclassification costs between classes. Results on the evaluated domain are promising, while further improvements can be expected after some modifications to the framework.