The rolling element bearing is a key component in many mechanical installations, and diagnosing its faults is crucial in the field of predictive maintenance. The objective of this work is to propose a diagnostic technical method for rolling element bearing faults that employs Ensemble Learning model such as Adaptive Boosting (AdaBoost) classifier. The proposed method includes Preprocessing of vibration data with fast Kurtogram; Extracting statistical features such as Mean, Standard Deviation, and Kurtosis; Training the Ensemble Learning algorithms for classifying the various faults based on extracted features. the results verify the effectiveness of the method in extracting fault characteristics and diagnosing faults of bearings.