Automatic Modulation Classification Based on Deep Learning for Software-Defined Radio

Abstract

With the development of artificial intelligence technology, deep learning has been applied to automatic modulation classification (AMC) and achieved very good results. In this paper, we introduced an improved deep neural architecture for implementing radio signal identification tasks, which is an important facet of constructing the spectrum-sensing capability required by software-defined radio. The architecture of the proposed network is based on the Inception-ResNet network by changing the several kernel sizes and the repeated times of modules to adapt to modulation classification. The modules in the proposed architecture are repeated more times to increase the depth of neural network and the model’s ability to learn features. The modules in the proposed network combine the advantages of Inception network and ResNet, which have faster convergence rate and larger receptive field. The proposed network is proved to have excellent performance for modulation classification through the experiment in this paper. The experiment shows that the classification accuracy of the proposed method is highest with the varying SNR among the six methods and it peaks at 93.76% when the SNR is 14 dB, which is 6 percent higher than that of LSTM and 13 percent higher than that of MentorNet, Inception, and ResNet purely. Besides, the average accuracy from 0 to 18 dB of the proposed method is 3 percent higher than that of GAN network. It will provide a new idea for modulation classification aiming at distraction time signal.

Communication Signal Modulation Mechanism Based on Artificial Feature Engineering Deep Neural Network Modulation Identifier

“…A simple method based on high-order cumulants [5] is proposed for the classification of digital modulation schemes. It is proposed that ten different types of digital modulation can be identified by using the multilayer perceptron method [6] in combination with the spectrum and statistical accumulative characteristic sets of signals. In recent years, the modulation recognition algorithms are becoming ever more diverse.…”

AMC2-Pyramid: Intelligent Pyramidal Feature Engineering and Multi-Distance Decision Making for Automatic Multi-Carrier Modulation Classification

“…The maximum likelihood technique provides optimal solutions in AMC. The threshold-based classification scheme is presented under an AMC architecture [7].…”

“…Hence, a deep learning (DL) algorithm is introduced in AMC. The main AMC works focus on the use of growing DL approaches [7]. Many works developed CNN for feature extraction and classification [8].…”

Deep Learning Radio Frequency Signal Classification with Hybrid Images

“…In the context of cognitive radio, for example, DL has been used in the form of a Convolutional Neural Network (CNN) to identify the presence of a Radar waveform against a background of Wi-Fi and LTE signals [2]. This approach allows a low-cost device to make a decision about the specific presence of a signal from the physical layer, which reduces control overhead [3]. The end result is that the listening device, termed a secondary user, will share the RF spectrum with the radar waveform and only transmit when it identifies the waveform is not present.…”

“…The main motivation of our work started from the observation that the classification of drone types and specific wireless technologies have mostly focused on frequencydomain representations of the RF signals [4], [6]- [12], while classifying unknown modulation schemes has focused on timedomain representations [3], [5], [12]- [14]. This is because distinguishing between many modulation schemes requires the phase information of the signal, which gets lost in common frequency domain representations such as the Power Spectral Density (PSD) and the Short-Time Fourrier Transform (STFT).…”