Adaptive Modulation Classification with Deep Learning for Various Number of Users and Performance Validation

The automatic modulation classification (AMC) is a key component of modern wireless frameworks. It is commonly used in various military and commercial applications such as electronic surveillance and cognitive radio. There are various regulation types that are considered when it comes to the classification of complex data. This paper presents an overview of the various features-based (FB) AMC techniques. They are mainly focused on the balance between speculation capacity and the constraints of the algorithm. A robust strategy is then presented for handling this test using the convolutional neural network (CNN). This paper presents a method that can be used to characterize the signals received by a system without the need for feature extraction. It can also take advantage of the features of the received signals. In addition, the confusion matrix is drawn and analyzed. The logistic regression algorithm performance is measured in terms of accuracy, sensitivity, specificity and F1_score for various users who are maintaining various distances from the base station.