Lightweight Deep Learning Model for Automatic Modulation Classification in Cognitive Radio Networks

Abstract

Automatic modulation classification (AMC) used in cognitive radio networks is an important class of methods apt to utilize spectrum resources efficiently. However, conventional likelihood-based approaches have high computational complexity. Thus, this paper proposes a novel convolutional neural network architecture for AMC. A bottleneck and asymmetric convolution structure are employed in the proposed model, which can reduce the computational complexity. The skip connection technique is used to solve the vanishing gradient problem and improve the classification accuracy. The dataset DeepSig:RadioML, which is composed of 24 modulation classes, is used for the performance analysis. Simulation results show that the classification accuracy performance of the proposed model is outstanding in the signal-to-noise ratio (SNR) range from-4 dB to 20 dB compared with MCNet that is the best model in the conventional models, where the proposed model achieves 5.52% and 5.92% improvement regarding classification accuracy at the SNRs of 0 dB and 10 dB, respectively. In terms of the computational complexity, the proposed model not only saves the trainable parameters by more than 67% but also reduces the prediction time for a signal by more than 54.4% compared with those of MCNet.

Deep Learning-Based Robust Automatic Modulation Classification for Cognitive Radio Networks

“…For training process 80% of the dataset is utilized and for testing the other is utilized, which is simulated by Matlab 2020b. The hardware specification for the simulation consists of an i5 2.9 VGG [27] ResNet [27] CNN-AMC [28] MCNet [29] LCNN [26] SCGNet [30] Proposed Model This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication.…”

“…GHz CPU, 32 GB RAM, and NVIDIA GeForce RTX 2080 Super GPU devices. To show the performance in terms of the classification accuracy and the computational complexity the proposed model is compared with the related works that includes latest models such as MCNet [29], LCNN [26] and SCGNet [30]. First of all, the performance evaluation of the proposd model is represented with respect to the conventional models shown in Fig.…”

“…• The accuracy performance of the proposed model outperforms the conventional models, which achieves 2.83% improvement at SNR 10 dB compared with the latest CNN model [26]. The rest of this paper is organized as follows: Section 2 describes the system model, Section 3 represents our proposed CNN architecture, Section 4 presents the simulation results and performance analysis, and Section 5 concludes the paper.…”

Dual-Determination of Modulation Types and Signal-to-Noise Ratios Using 2D-ASIQH Features for Next Generation of Wireless Communication Systems

“…In contrast to [38], a better performance of modulation recognition has been achieved in [39] via convolutional neural network (CNN) tool but considering 1024 samples per transmitted signal (i.e., larger size of dataset compared to [38]). Their model processed analog and digital modulation types under Rayleigh fading channel and obtained an average recognition accuracy of 91.48% at SNR value of 10 dB.…”

Training Images Generation for CNN Based Automatic Modulation Classification

“…Although the accuracy performance was good, thousands of parameters were used in the network, which is still large relative to the small IQ length. Kim et al [17] proposed a novel CNN architecture for AMC with low computational complexity compared with MCNet. The proposed model showed good performance in the SNR range from -4dB to 20dB.…”