Automatic Modulation Classification Based on Deep Residual Networks With Multimodal Information

Qi, Peihan; Zhou, Xiaoyu; Zheng, Shilian; Li, Zan

doi:10.1109/tccn.2020.3023145

Cited by 103 publications

(46 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The conventional AMC methods using FFT magnitude achieved satisfactory performance on modulation classification [15]. However, the proposed FWB-based model aims to extract features of OFDM useful symbol length.…”

Section: A Classification Results Under Awgn Environmentsmentioning

confidence: 99%

“…Meng et al [33] proposed an end-to-end trainable AMC system based on CNN by approximate the maximum likelihood (ML)-AMC with minimal performance loss and a twostep training method using 9-HOC features for fine-tuning. Peihan et al [15] proposed a DL-based AMC system that extracts features by utilizing various input information such as IQ, AP, and FFT magnitude into ResNet, and classified modulation methods through DenseNet. Yashashwi et al [34] proposed a correction module (CM)-CNN system that applies a correction module with CNN for estimating and compensating the synchronization offset and improved performance in an inconsistent synchronization environment.…”

Section: Related Workmentioning

confidence: 99%

“…The proposed FWB-CNN model can learn features for discriminating the OFDM useful symbol lengths of the received signal, and thus achieve remarkable classification accuracy performance. Furthermore, we adopt IQ signal and FWB simultaneously as input by adapting the principles of the WSMF [15] model using multimodality to improve the classification accuracy as shown in Fig. 4.…”

Section: Proposed Cnn Model Using Both Iq and Fwbmentioning

confidence: 99%

“…Furthermore, they proposed the classifier consists of multiple CNNs in the first part, and a bidirectional LSTM (BiLSTM) and a deep neural network (DNN) in the other two parts, referred to as multiple CNN based BiLSTM and DNN (MCBLDN). Peihan et al [15] proposed a waveform-spectrum multimodal fusion (WSMF) method that extracts features from multiple information using ResNet. The aforementioned DL-based AMC systems have improved performance for classifying between single-carrier-based modulation classification and multi-carrier signals.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Deep Learning-Based Automatic Modulation Classification With Blind OFDM Parameter Estimation

Park

Han

2021

IEEE Access

View full text Add to dashboard Cite

Automatic modulation classification (AMC) is an essential factor in dynamic spectrum access to fulfill the spectrum demand of 5G wireless communications for achieving high data rate and low latency. Many deep learning (DL)-based AMC methods have achieved improved accuracy performance for classifying analog modulation schemes, single-carrier-based modulation schemes, and multi-carrier signals using several DL architectures such as the convolutional neural network (CNN) and long-short term memory (LSTM). However, most conventional DL-based AMC methods have confused the orthogonal frequency multiplexing division (OFDM)-based signals with different OFDM useful symbol lengths. To resolve the issue, we propose a CNN model operating on the fast Fourier transformation window banks (FWB) to extract the useful symbol length in OFDM, which represent the identification of each OFDMbased wireless communication technology. After extracting the OFDM useful symbol length, we propose a DL-based AMC system combined with FWB and in-phase and quadrature phase (IQ) signals to classify the OFDM symbol length and single-carrier modulation schemes simultaneously. Furthermore, we explore the constraints of the FWB parameters according to the length and the FFT size of the OFDM signal to achieve good classification accuracy through the experiment. We constructed a dataset by generating OFDM signals of different lengths while changing the FFT size in a fixed bandwidth and by selecting only quadrature amplitude modulation (QAM) schemes from RadioML2016.10a. Experimental results show the improved performance of the classification accuracy by about 30% over conventional classifiers in additive white Gaussian noise, synchronization impairments, and fading environments.

show abstract

Section: A Classification Results Under Awgn Environmentsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Proposed Cnn Model Using Both Iq and Fwbmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning-Based Automatic Modulation Classification With Blind OFDM Parameter Estimation

Park

Han

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Artificial intelligence (AI) and other advanced ML approaches have significantly improved state-of-the-art outcomes in computer vision, speech recognition [ 22 ], drug discovery, genomics, and, most recently, physical layer communication [ 23 ]. MC algorithms [ 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 ] focused on various ML algorithms. In [ 24 ], the MC technique is evaluated using genetic programming (GP) and K-nearest neighbor (KNN).…”

Section: Introductionmentioning

confidence: 99%

A Survey of Blind Modulation Classification Techniques for OFDM Signals

Kumar

Majhi

Gui

et al. 2022

Sensors

View full text Add to dashboard Cite

Blind modulation classification (MC) is an integral part of designing an adaptive or intelligent transceiver for future wireless communications. Blind MC has several applications in the adaptive and automated systems of sixth generation (6G) communications to improve spectral efficiency and power efficiency, and reduce latency. It will become a integral part of intelligent software-defined radios (SDR) for future communication. In this paper, we provide various MC techniques for orthogonal frequency division multiplexing (OFDM) signals in a systematic way. We focus on the most widely used statistical and machine learning (ML) models and emphasize their advantages and limitations. The statistical-based blind MC includes likelihood-based (LB), maximum a posteriori (MAP) and feature-based methods (FB). The ML-based automated MC includes k-nearest neighbors (KNN), support vector machine (SVM), decision trees (DTs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), and long short-term memory (LSTM) based MC methods. This survey will help the reader to understand the main characteristics of each technique, their advantages and disadvantages. We have also simulated some primary methods, i.e., statistical- and ML-based algorithms, under various constraints, which allows a fair comparison among different methodologies. The overall system performance in terms bit error rate (BER) in the presence of MC is also provided. We also provide a survey of some practical experiment works carried out through National Instrument hardware over an indoor propagation environment. In the end, open problems and possible directions for blind MC research are briefly discussed.

show abstract

Automatic Modulation Classification Based on Multimodal Coordinated Integration Architecture and Feature Fusion

Zhang

Lin

2021

Mobile Multimedia Communications

View full text Add to dashboard Cite

Automatic Modulation Classification Based on Deep Residual Networks With Multimodal Information

Cited by 103 publications

References 38 publications

Deep Learning-Based Automatic Modulation Classification With Blind OFDM Parameter Estimation

Deep Learning-Based Automatic Modulation Classification With Blind OFDM Parameter Estimation

A Survey of Blind Modulation Classification Techniques for OFDM Signals

Automatic Modulation Classification Based on Multimodal Coordinated Integration Architecture and Feature Fusion

Contact Info

Product

Resources

About