working of the fifth generation intelligent radio that is Cognitive Radio (CR) system which works on predictive data rate and propose ANFIS based learning scheme to introduce intelligence in it. The testing data set is taken from training set. Validation data set is unseen data. RMSE and prediction accuracy are used as performance index. Two gaussian membership functions are taken for each input. Error goal was set for .001.Training was for 300 epochs. It is seen prediction accuracy was 91 percentages in testing case and 89 in validation. RMSE difference between validation and testing case very small. - working of the fifth generation intelligent radio that is Cognitive Radio (CR) system which works on predictive data rate and propose ANFIS based learning scheme to introduce intelligence in it. The testing data set is taken from training set. Validation data set is unseen data. RMSE and prediction accuracy are used as performance index. Two gaussian membership functions are taken for each input. Error goal was set for .001.Training was for 300 epochs. It is seen prediction accuracy was 91 percentages in testing case and 89 in　　 validation. RMSE difference between validation and testing case very small.