Data clustering using Bat Algorithm

The two matlab files, namely, Main.m and Bat_Algorithm.m are used to perform data clustering using Bat Algorithm.
The proposed novel partitional clustering approach extracts information in the form of optimal cluster centers from training samples. The extracted cluster centers are then validated on test samples.
Main.m is the file which needs to be executed. This loads the dataset and extract the cluster centers using training dataset. Post the training phase, clustering is carried out on test dataset and results are displayed.

Bat_Algorithm.m is the file called from Main.m for extracting the optimal cluster centers from training dataset using Bat Algorithm. The file takes in training dataset with the upper & lower limits from each attributes as the input to the algorithm. The file returns the optimal cluster center to the Main.m

In this illustration, a synthetic data is generated with predefined mean and standard deviation. The users can vary these parameters. If the users want to test on there own datasets, then the dataset have to be segregated into the corresponding training and testing portion. The lines 20 to 53 needs to be modified accordingly by assigning related dataset to the variables xdata (complete dataset), ftrain (traning dataset) and ftest (testing dataset) in the file Main.m

The result of clustering can be visualized in the command prompt through the confusion matrix.