Luxin Zhang

Luxin Zhang

Auto-generated profile, based on publicly available information

Luxin Zhang

National Key Laboratory of Electromagnetic Space Security, Jiaxing, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
31 January 2024 in IEEE Transactions on Cognitive Communications and Networking
Verified
Journal Article
Open access
SZShilian Zheng
Shilian Zheng
ZYZhuang Yang
Zhuang Yang
WSWeiguo Shen
Weiguo Shen
LZLuxin Zhang
Luxin Zhang
JZJiawei Zhu
Jiawei Zhu
XYXiaoniu Yang
Xiaoniu Yang
Direction-of-arrival (DOA) estimation is a vital research topic in array signal processing, with extensive applications in many fields. In recent years, deep learning has been applied to DOA estimation to improve the performance. However, most existing deep learning-based DOA estimation methods extract DOA information from the covariance matrix (CM) input. In this paper, we introduce a novel deep learning-based DOA estimation scheme that utilizes the raw in-phase (I) and quadrature (Q) components of the signal as the input. We formulate the problem as single-label classification and multi-label classification based on the number of signal sources. We design a convolutional neural network to solve the problems and to adapt to different number of snapshots. We also propose a deep learning regression-based method to overcome the limitations of classify-based methods in dealing with off-grid angles. We conduct extensive experiments with simulations and over-the-air collected signals to analyze the performance of the proposed method in various scenarios including different SNRs, additive generalized Gaussian noise (AGGN) and extreme multi-source DOA estimation. Results demonstrate that our proposed method outperforms the existing deep learning-based DOA estimation methods.

10 February 2023 in IEEE Transactions on Cognitive Communications and Networking
Verified
Journal Article
Open access
SZShilian Zheng
Shilian Zheng
XZXiaoyu Zhou
Xiaoyu Zhou
LZLuxin Zhang
Luxin Zhang
PQPeihan Qi
Peihan Qi
KQKunfeng Qiu
Kunfeng Qiu
XYXiaoniu Yang
Xiaoniu Yang
Automatic modulation classification (AMC) can generally be divided into knowledge-based methods and data-driven methods. In this paper, we explore combining the knowledge-based method and data-driven technology to take full advantage of both and propose a hybrid knowledge and data-driven deep learning framework (HKDD) for AMC. To make the handcrafted features more discriminative, various traditional features are adopted, including instantaneous features, statistical features, and spectral features. In the HKDD framework, a feature fusion mechanism is proposed to integrate the features learned from the original signal with those processed by a fully connected network from the handcrafted features. Besides, an attention mechanism is implemented on the fused features to neglect immature features and highlight important features. To evaluate the performance of the proposed method, we construct two modulation classification datasets containing both traditional features and raw IQ data. The bigger one contains 36 modulation categories, which is greater than the number of categories of any AMC dataset currently available. Simulation results show that our proposed method has significant performance gain in both adequate-sample classification scenario and few-shot classification scenario.

29 December 2020 in IEEE Communications Letters
Verified
Journal Article
Closed access
LHLiang Huang
Liang Huang
LZLuxin Zhang
Luxin Zhang
SYShicheng Yang
Shicheng Yang
Liping QianLiping Qian
Liping Qian
YWYuan Wu
Yuan Wu

8 June 2023 in IEEE Transactions on Wireless Communications
Verified
Journal Article
Open access
KQKunfeng Qiu
Kunfeng Qiu
SZShilian Zheng
Shilian Zheng
LZLuxin Zhang
Luxin Zhang
CLCaiyi Lou
Caiyi Lou
XYXiaoniu Yang
Xiaoniu Yang
Deep learning has been widely used in automatic modulation classification (AMC) recently. Most of deep learning-based AMC uses a single network model to deal with radio signals with a single input format. In this paper, we propose a hybrid heterogeneous modulation classification architecture named DeepSIG, which integrates Recurrent Neural Network (RNN), Convolutional Neural Network (CNN) and Graph Neural Network (GNN) models in a single framework to process radio signals with heterogeneous input formats, i.e., in-phase (I) and quadrature (Q) sequences, images mapped from IQ signals and graphs converted from IQ signals, to extract and integrate the features from different perspectives. A fusion training mechanism is presented to train DeepSIG. We use three different radio signal datasets for simulations. Results show that our proposed DeepSIG performs the best in terms of classification accuracy compared with the three methods with single input, i.e., sequence, image or graph. The performance gain is larger in few-shot scenarios.

12 May 2022 in IEEE Transactions on Cognitive Communications and Networking
Verified
Journal Article
Closed access
FWFei Wei
Fei Wei
SZShilian Zheng
Shilian Zheng
XZXiaoyu Zhou
Xiaoyu Zhou
LZLuxin Zhang
Luxin Zhang
CLCaiyi Lou
Caiyi Lou
XYXiaoniu Yang
Xiaoniu Yang
Direct spread spectrum communication has the advantages of strong anti-jamming ability and low probability of interception, which plays an essential role in both civil and military communications. The detection of direct sequence spread spectrum (DSSS) signal becomes very difficult because of its low power spectral density. In this paper, the detection of DSSS signals under non-cooperative conditions is carried out based on the classification technology of deep learning. Firstly, a detection scheme based on convolutional neural network (CNN) is proposed, in which the neural network is used to learn the features of DSSS signal and noise automatically without extracting the features in advance. In addition, we also propose a hybrid CNN-correlation (CORR)-based detection scheme in order to reduce the computational complexity. In this scheme, the autocorrelation of the received signal is truncated and used as the input of the neural network for training and inference. A large number of simulation results show that the detection performance of the proposed two schemes is significantly better than the traditional autocorrelation-based detection method in various scenarios.

13 June 2024 in IEEE Journal on Selected Areas in Communications
Verified
Journal Article
Open access
SZShilian Zheng
Shilian Zheng
JHJiacheng Hu
Jiacheng Hu
LZLuxin Zhang
Luxin Zhang
KQKunfeng Qiu
Kunfeng Qiu
JCJie Chen
Jie Chen
XYXiaoniu Yang
Xiaoniu Yang
Frequency Modulation (FM) broadcast signals, regarded as opportunistic signals, hold significant potential for indoor and outdoor positioning applications. The existing FM-based positioning methods primarily rely on Received Signal Strength (RSS) for positioning, the accuracy of which needs improvement. In this paper, we introduce FM-Pnet, an end-to-end FM-based positioning method that leverages deep learning. This method utilizes the time-frequency representation of FM signals as network input, enabling automatically learning of deep features for positioning. We also propose two strategies, noise injection and enriching training samples, to enhance the model’s generalization performance over long time spans. We construct datasets for both indoor and outdoor scenarios and conduct extensive experiments to validate the performance of our proposed method. Experimental results demonstrate that FM-Pnet significantly outperforms traditional RSS-based positioning methods in terms of both positioning accuracy and stability.