Genetic Algorithm Based Approach in Attribute Weighting for a Medical Data Set
Table 6
The starting point of the genetic algorithm using ONE inference (GA ONE), the attribute weighted -nearest neighbour method with neighbour’s class-based attribute weighting (GA cwk-NN) and with OVA classifiers (GA wk-NN OVA) as evaluation method. The true positive rates (TPR) of seven disease classes and the total classification accuracies of the best individual from the starting population are given in percentages (%) from 10 times (five times with GA wk-NN OVA) repeated 10-fold cross-validation.