i use matlab,and this question is about obsering the impact of diversity on balanced and imbalanced dataset and investigate how the performance measures behave along with the diversity degrees in depth,we build ensembles on several two dimensional artificial data sets with different degrees of class imbalance.how can I make an artificial data from two gaussian distributions with equal covariance and small overlapping area close to the separating line.three different data size are considered:while one class contains 200 training points,the size of the other class is set to 10(very imbalance),50(imbalance),200(balance).after generating these data ,i want to use it in bagging