Half-Against-Half Multi-Class Support Vector Machines in classification of benthic macroinvertebrate images

In this paper we investigated how Half-Against-Half Support Vector Machine (HAH-SVM) succeed in the classification of the benthic macroinvertebrate images. Automated taxa identification of benthic macroinvertebrates is a slightly researched area and in this paper HAH-SVM was for the first time applied to this application area. The main problem in HAH-SVM is to find the right way to divide the classes in a node. We solved the problem by using two different approaches. Firstly, we applied the Scatter method which is a novel approach for the class division problem. Secondly, we formed the class divisions in an HAH-SVM by a random choice. We performed extensive experimental tests with four different feature sets and tested every feature set with seven different kernel functions. The tests showed that by the Scatter method and random choice formed HAH-SVMs performed from classification problem very well obtaining over 95% accuracy. Moreover, the 7D and 15D feature sets together with the RBF kernel function are good choices for this classification task. Generally speaking, HAH-SVM is a promising strategy for automated benthic macroinvertebrate identification.