CNN-Based Automatic Modulation Recognition of Wireless Signal

Ma, Kai; Zhou, Yongbin; Chen, Jianyun

doi:10.1109/iciscae51034.2020.9236934

Cited by 12 publications

(13 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Modulation classification problem has been tackled in multiple research works. In [7][8][9], an effective modulation classifier has been developed using convolutional neural networks (CNN). The authors of [10][11][12] demonstrated higher performance and faster convergence for NN-based decoders for BCH and polar code channel decoding.…”

Section: A Related Workmentioning

confidence: 99%

Deep Learning-Based SC-FDMA Channel Equalization

Mohamed

2024

IJEETC

View full text Add to dashboard Cite

It is very challenging to design an effective wireless communication system. That’s because of numerous factors affecting the performance of a typical wireless communication system, such as nonlinear channel distortions and impairments. single carrier frequency division multiple access (SC-FDMA) is a multiple access scheme that is an important part of the long-term evolution (LTE) standard for uplink transmission. An advanced mobile radio system’s multiple access schemes should indeed meet stringent requirements, such as a low bit error rate (BER). In this article, we investigate the equalization problem for nonlinear channel distortions and impairments using deep neural networks (NN). We introduce a novel combined deep neural network channel equalization and symbol detection scheme based on a deep learning (DL) recurrent feedback (RF) long short-term memory (LSTM) neural network to achieve blind equalization and decoding for SC-FDMA systems without knowing the channel state information (CSI). To train the model efficiently, the training data is gathered by simulation, with channel effects and noise treated as a complete black box. CSI and constellation demapping are learned by a deep neural network (DNN) model. Then, the frequency-domain sequences that have been corrupted are implicitly equalized to get the broadcasted signal back. Our specified SC-FDMA system, which uses a quadrature phase-shift keying (QPSK) modulation method and the suggested Deep Learning-based model channel equalizer, performs better than the existing equalizers by an average of 1 to 4 dB at moderate signal-to-noise (SNR) ratios, according to simulation data. A complexity comparison between the proposed and the conventional equalizers was conducted in terms of training time, execution time, and number of operations. On combined channel equalization and symbol detection, the suggested system delivers state-of-the-art performance.

show abstract

Section: A Related Workmentioning

confidence: 99%

Deep Learning-Based SC-FDMA Channel Equalization

Mohamed

2024

IJEETC

View full text Add to dashboard Cite

show abstract

“…The performance of our proposed method is compared with the methods proposed in references [11], [14], and [15] through experiments. The study in reference [14] investigates the performance comparison between training a single model with data mixed under different SNR and training different models with separate inputs, but it only considered 11 SNR levels and a single channel fading scenario. where the original generated IQ data is used, and the CNN model structure from reference [14] is employed.…”

Section: Deep Learning Frameworkmentioning

confidence: 99%

Modulation classification method integrating knowledge graph and deep learning

Yang,

Chen,

2024

Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024)

View full text Add to dashboard Cite

In the field of modulation classification, training complex deep learning models incurs high costs. And the overall algorithm's generalization is generally low, which indicates that the models trained by signal data with specific fading channel and signal-to-noise ratio(SNR) struggle to classify modulation schemes under different fading channel and SNR conditions. In this paper, a novel modulation classification method combining knowledge graphs and deep learning is proposed. Artificial neural network(ANN) models with simple structures are used to reduce model complexity. The system can select the appropriate model for modulation classification based on the signal-to-noise ratio and fading channel using a knowledge graph. The experimental results demonstrate that the entire system can accurately classify the modulation schemes of signals under multiple fading channels and SNR conditions. By integrating knowledge graph and deep learning model, the model structure is greatly simplified, training latency is significantly reduced and the overall generalization of the system is improved.

show abstract

“…These methods, specifically deep Convolutional Neural Networks (CNNs), offer a direct approach to signal identification and classification, eliminating the need for human-defined features. Such advances have led to significant improvements in modulation recognition accuracy [17][18][19][20][21]. For example, Ying et al [19].…”

Section: Introductionmentioning

confidence: 99%

On-Chip Acceleration of RF Signal Modulation Classification With Short-Time Fourier Transform and Convolutional Neural Network

Jung,

Woo,

Mukhopadhyay

2023

IEEE Access

View full text Add to dashboard Cite

Automatic Modulation Classification (AMC) is a technique used in wireless communication systems to identify the modulation type of received signals at the receiver. Improving spectrum utilization efficiency is essential for AMC and is carried out by fundamental signal processing methods within the physical layer. Convolutional Neural Networks (CNN) based deep-learning models have recently been employed in AMC systems, demonstrating superior performance. However, the large size of CNN models, floating-point weights, and activations make deploying such systems with limited hardware resources quite complex. In this paper, we propose a hybrid Radio Frequency-based Machine Learning (RFML) model that combines Short-time Fourier Transform and Convolutional Neural Network (STFT-CNN) for AMC. Simulations on RadioML2016.10a demonstrate an average recognition accuracy of 79% for a Signal-to-Noise Ratio of 0dB or higher when using 16-bit fixed-point operations. An on-chip accelerator for the STFT-CNN, designed and synthesized in 28nm CMOS, offers 19 times lower power consumption, 34 times smaller area, 1.3 times higher bandwidth, and 50 times less memory than a time-domain CNN accelerator utilizing 32-bit floating-point operations.

show abstract

CNN-Based Automatic Modulation Recognition of Wireless Signal

Cited by 12 publications

References 4 publications

Deep Learning-Based SC-FDMA Channel Equalization

Deep Learning-Based SC-FDMA Channel Equalization

Modulation classification method integrating knowledge graph and deep learning

On-Chip Acceleration of RF Signal Modulation Classification With Short-Time Fourier Transform and Convolutional Neural Network

Contact Info

Product

Resources

About