Improving the Classifiers Performance Using Best Feature selection method (VM) and Meta Classifier

In the last decades many classification methods and fusers have been developed. Considerable gains have been achieved in the classification performance by fusing and combining different classifiers. In these we can select the best feature selection method for the feature selection. The variance mean based feature filtering method will be give better performance than other methods. We experiment a new method for ship infrared imagery recognition based on the fusion of individual results in order to obtain a more reliable decision. To optimize the results of every class of ship, we implemented individual classifiers using Dempster-Shafer (DS) method for each class. Here combine the classifiers we can use Dempster- Shafer method. We compare the result of the combination of classifiers with the results of the individual classifier. The improvement recognition varies between 3% to 20% for a class. The objective of a good fuser is to perform at least as good as the best classifier in any situation and best feature selection methods also improve the classifiers performance. For this purpose, we consider five classifiers: DS classifier, SVM, Lsquare (7), Bayes classifier (5), Decision tree and nearest neighbor classifier and one fuser: feed forward neural network fuser. The fuser gives a performance equal or superior to the best classifier. Using these two efficient techniques called best feature selection method and fuser of classifier will be increase the classifiers performance and accuracy.