Shichuan Chen

Prof. Shichuan Chen

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 October 2021 in IEEE Transactions on Cognitive Communications and Networking
Verified
Journal Article
Closed access
ZCZhuangzhi Chen
Zhuangzhi Chen
HCHui Cui
Hui Cui
JXJingyang Xiang
Jingyang Xiang
KQKunfeng Qiu
Kunfeng Qiu
LHLiang Huang
Liang Huang
XYXiaoniu Yang
Xiaoniu Yang
Deep learning methods achieve great success in many areas due to their powerful feature extraction capabilities and end-to-end training mechanism, and recently they are also introduced for radio signal modulation classification. In this paper, we propose a novel deep learning framework called SigNet, where a signal-to-matrix (S2M) operator is adopted to convert the original signal into a square matrix first and is co-trained with a follow-up CNN architecture for classification. This model is further accelerated by integrating 1D convolution operators, leading to the upgraded model SigNet2.0. The simulations on two signal datasets show that both SigNet and SigNet2.0 outperform a number of well-known baselines. More interestingly, our proposed models behave extremely well in small-sample learning when only a small training dataset is provided. They can achieve a relatively high accuracy even when 1% training data are kept, while other baseline models may lose their effectiveness much more quickly as the datasets get smaller. Such result suggests that SigNet/SigNet2.0 could be extremely useful in the situations where labeled signal data are difficult to obtain. The visualization of the output features of our models demonstrates that our model can well divide different modulation types of signals in the feature hyper-space.

24 August 2020 in IEEE Transactions on Cognitive Communications and Networking
Verified
Journal Article
Closed access
SZShilian Zheng
Shilian Zheng
SCShichuan Chen
Shichuan Chen
XYXiaoniu Yang
Xiaoniu Yang
A canonical wireless communication system consists of a transmitter and a receiver. The information bit stream is transmitted after coding, modulation, and pulse shaping. Due to the effects of radio frequency (RF) impairments, channel fading, noise and interference, the signal arriving at the receiver will be distorted. The receiver needs to recover the original information from the distorted signal. In this paper, we propose a new receiver model, namely DeepReceiver, that uses a deep neural network to replace the traditional receiver’s entire information recovery process. We design a one-dimensional convolution DenseNet (1D-Conv-DenseNet) structure, in which global pooling is used to improve the adaptability of the network to different input signal lengths. Multiple binary classifiers are used at the final classification layer to achieve multi-bit information stream recovery. We also exploit the DeepReceiver for unified blind reception of multiple modulation and coding schemes (MCSs) by including signal samples of corresponding MCSs in the training set. Simulation results show that the proposed DeepReceiver performs better than traditional step-by-step serial hard decision receiver in terms of bit error rate under the influence of various factors such as noise, RF impairments, multipath fading, cochannel interference, dynamic environment, and unified reception of multiple MCSs.

4 December 2019 in IEEE Access
Verified
Journal Article
Open access
Huaji ZhouHuaji Zhou
Huaji Zhou
LJLicheng Jiao
Licheng Jiao
SZShilian Zheng
Shilian Zheng
SCShichuan Chen
Shichuan Chen
LYLifeng Yang
Lifeng Yang
XYXiaoniu Yang
Xiaoniu Yang
Deep learning is an important support for the development of cognitive communication in the cognitive Internet of Things (IoT). Deep convolution neural networks have powerful functional expression and feature extraction capabilities. Mallat et al. proposed a convolutional network model with strict mathematical theory support and excellent feature extraction ability in 2012, i.e., wavelet scattering convolution networks, which is widely used in audio and image classification. In this paper, we improve the wavelet scattering convolution networks and propose construct weight-variable scattering convolution networks by combining the scattering network and the deep convolution neural network organically. We select a variety of wavelet filters for filtering operations and add 1*1 convolution layers to enable the features extracted by different types of wavelet filters to be combined optimally. In order to verify the effectiveness of the proposed network structure, we conduct experiments on classification of typical electromagnetic signals. The experimental results show that the signal classification accuracy obtained by the weight-variable scattering convolution networks is significantly better than that of the traditional wavelet scattering convolution network, and the computational complexity is greatly reduced while the classification accuracy is close to the deep convolution neural network.

24 June 2021 in IEEE Access
Verified
Journal Article
Open access
MXMeng Xia
Meng Xia
SCShichuan Chen
Shichuan Chen
XYXiaoniu Yang
Xiaoniu Yang
Owing to advances in the overall performance and anti-interception capability of radars, the designs of radar waveforms with good correlation properties have been a concern for researchers. In this paper, we propose a novel method based on convolutional neural networks (CNNs) for designing single or multiple unimodular sequences with good auto- and cross-correlation or weighted correlation properties. The framework of the neural networks for sequence optimization is constructed using group convolution and identity mapping, and three different loss functions are presented using different optimization objectives. To illustrate the performance of the proposed method, we present numerous examples, including the design of sequences with low autocorrelation sidelobes in a specified lag interval and a sequence set with good auto- and cross-correlation properties. Moreover, an analysis of the simulations shows that the sequences designed through our method demonstrate better correlation properties than classic algorithms.

9 October 2020 in Electronics
Verified
Journal Article
Open access
PDF file
SCShichuan Chen
Shichuan Chen
KQKunfeng Qiu
Kunfeng Qiu
SZShilian Zheng
Shilian Zheng
QXQi Xuan
Qi Xuan
XYXiaoniu Yang
Xiaoniu Yang
Radio modulation classification is widely used in the field of wireless communication. In this paper, in order to realize radio modulation classification with the help of the existing ImageNet classification models, we propose a radio–image transformer which extracts the instantaneous amplitude, instantaneous phase and instantaneous frequency from the received radio complex baseband signals, then converts the signals into images by the proposed signal rearrangement method or convolution mapping method. We finally use the existing ImageNet classification network models to classify the modulation type of the signal. The experimental results show that the proposed signal rearrangement method and convolution mapping method are superior to the methods using constellation diagrams and time–frequency images, which shows their performance advantages. In addition, by comparing the results of the seven ImageNet classification network models, it can be seen that, except for the relatively poor performance of the architecture MNASNet1_0, the modulation classification performance obtained by the other six network architectures is similar, indicating that the proposed methods do not have high requirements for the architecture of the selected ImageNet classification network models. Moreover, the experimental results show that our method has good classification performance for signal datasets with different sampling rates, Orthogonal Frequency Division Multiplexing (OFDM) signals and real measured signals.

10 October 2022 in IEEE Access
Verified
Journal Article
Open access
MXMeng Xia
Meng Xia
SCShichuan Chen
Shichuan Chen
XYXiaoniu Yang
Xiaoniu Yang
This study exploits high-order p-norm to uniformly represent the peak sidelobe level (PSL) and integrated sidelobe level (ISL) commonly used in waveform optimization, and presents a unified optimization objective function by considering the requirement that waveforms have good correlation properties in radar and communication systems. A novel and efficient waveform optimization algorithm is then proposed, which tackles the waveform and waveform set optimization of the PSL, the weighted sidelobe level, the ISL, and the weighted ISL. Applying the unified optimization objective function, the iteration factors are dynamically adjusted based on the quasi-Newton algorithm; in addition, the objective function is optimized with the gradient descent search algorithm and includes the optimization of autocorrelation and cross-correlation. Because certain application scenarios involve the Doppler sensitivity of waveforms, the problem is converted to cross-correlation optimization via channel division of Doppler frequency, and waveform with anti-Doppler sensitivity can be obtained. Multiple numerical simulations illustrate the positive performance of the proposed method. Furthermore, compared with certain traditional algorithms, the waveforms designed by this algorithm demonstrate improved correlation properties.