A major public health concern has arisen due to  the Monkeypox’s rapid spread throughout various countries. Timely diagnosis and identification are essential for the effective management and treatment of this zoonotic disease. The purpose of this work is to use deep learning techniques and Bagging classification models to discover and assess the best model for diagnosing of this disease. In this study, we have used two publicly available datasets, i.e., MSID and MSLD. We have proposed a model which is an integration of two best-performed CNN models, i.e., DenseNet121 and MobileNetV2, for feature extraction task and rather than using a CNN classifier, we have used Bagging classifiers for classification tasks. The performance of the proposed model was evaluated using metrics such as accuracy, recall, precision, and F1-score. Our experimental results demonstrate that the integrated proposed model had the best classification performance on the datasets used.