Brain imaging classification based On Learning Vector Quantization
Bahera H. Nayef, Shahnorbanun Sahran, Rizuana Iqbal Hussain, Siti Norul Huda Sheikh Abdullah · 2013
The performance accuracy of the Artificial Neural Network (ANN) is highly dependent on the class distribution. Data multi-randomization before classification is proposed in this paper in order to obtain a proper classification model, which guaranties well performance of the classifiers. Multi randomization aims to allocate the best class distribution by re-ordering the input dataset randomly. In this paper, Learning Vector Quantization (LVQ) which is a supervised ANN, Multilayer perceptron (MLP), unsupervised Self organizing Map (SOM) and Radial Base Function (RBF) are used to classify multi randomized brain Magnetic Resonance Imaging (MRI) dataset. The proposed method showed significant improvement in the stability of the classifiers.