Relationship between Structural Diversity and Performance of Multiple Classifiers for Decision Support

The paper presents the investigation and implementation of the relationship between diversity and the performance of multiple classifiers on classification accuracy. The study is critical as to build classifiers that are strong and can generalize better. The parameters of the neural network within the committee were varied to induce diversity; hence structural diversity is the focus for this study. The number of hidden nodes and the output activation function are the parameters that were varied. The diversity measures that were adopted from ecology such as Shannon and Simpson were used to quantify diversity. Genetic algorithm is used to find the optimal ensemble by using the accuracy as the cost function. The results observed shows that there is a relationship between structural diversity and accuracy. It is observed that the classification accuracy of an ensemble increases as the diversity increases. However, there is a point where as diversity increases, the accuracy does not increase. Furthermore, the paper also presents the effect of ensemble size on the prediction accuracy. This investigation is necessary in order to know and ensure the optimal size of classifiers that can be used in an ensemble. It has been observed that as the size of the ensemble increases, the accuracy increases.