The performance of Genetic Algorithm Learning Vector Quantization 2 Neural Network on identification of the types of Attention Deficit Hyperactivity Disorder

Attention Deficit Hyperactivity Disorder (ADHD) is the most commonly diagnosed mental disorder in children. They may be hyperactive and unable control their impulses, or they may have trouble paying attention. Detection the types of ADHD is necessary inorder to handle the patient appropriately. This research implements Genetic Algorithm Learning Vector Quantization 2 Neural Network (GA-LVQ2NN) to classify the type of ADHD. The advantages of LVQ2 can set the weight vectors on the process of supervised learning. But if the initialize weight vector is not precise then the classification results will not be optimal. Genetic Algorithm (GA) is used to optimizing the weight vectors on the LVQ2 training process. This research tries to find out the performance comparison between using GA on LVQ2NN and without GA on LVQ2. The testing is done by calculating the accuracy of 80 training data and 20 testing data. Based on 10 experiments, they showed that the GA-LVQ2NN method gives higher accuracy, that is 89.5% compared to the LVQ2 method which is 80%.