Yaxing Li

Bio: Yaxing Li is an academic researcher from Naval University of Engineering. The author has contributed to research in topics: Computer science & Single antenna interference cancellation. The author has an hindex of 1, co-authored 9 publications receiving 19 citations.

Convolutional neural network and multi-feature fusion for automatic modulation classification

Abstract: Automatic modulation classification (AMC) lies at the core of cognitive radio and spectrum sensing. In this Letter, the authors propose a novel convolutional neural network (CNN)-based AMC method with multi-feature fusion. First, the modulation signals are transformed into two image representations of cyclic spectra (CS) and constellation diagram (CD), respectively. Then, a two-branch CNN model is developed, a gradient decent strategy is adopted and a multi-feature fusion technique is exploited to integrate the features learned from CS and CD. The proposed method is computationally efficient, benefited from its simple neural network. Experimental results show that the proposed method can achieve identical or better results with much reduced learned parameters and training time, compared with the state-of-the-art deep learning-based methods.

Self-Interference Cancellation: A Comprehensive Review from Circuits and Fields Perspectives

Abstract: Increased demand for higher spectrum efficiency, especially in the space-limited chip, base station, and vehicle environments, has spawned the development of full-duplex communications, which enable the transmitting and receiving to occur simultaneously at the same frequency. The key challenge in this full-duplex communication paradigm is to reduce the self-interference as much as possible, ideally, down to the noise floor. This paper provides a comprehensive review of the self-interference cancellation (SIC) techniques for co-located communication systems from a circuits and fields perspective. The self-interference occurs when the transmitting antenna and the receiving antenna are co-located, which significantly degrade the system performance of the receiver, in terms of the receiver desensitization, signal masking, or even damage of hardwares. By introducing the SIC techniques, the self-interference can be suppressed and the weak desired signal from the remote transmitter can be recovered. This, therefore, enables the full-duplex communications to come into the picture. The SIC techniques are classified into two main categories: the traditional circuit-domain SICs and the novel field-domain SICs, according to the method of how to rebuild and subtract the self-interference signal. In this review paper, the field-domain SIC method is systematically summarized for the first time, including the theoretical analysis and the application remarks. Some typical SIC approaches are presented and the future works are outlooked.

Modulation Classification of VHF Communication System based on CNN and Cyclic Spectrum Graphs

Abstract: Modulation classification is the technological basis of adaptive interference mitigation in communication system. This paper proposes a modulation classification method for very high frequency (VHF) signals, which is based on deep convolutional neural network (CNN) and cyclic spectrum graphs. First, the cyclic spectrum of VHF signals is analyzed. Then, a deep learning method based on CNN is proposed, down-sampling and clipping technologies are used for preprocessing cyclic spectrum images, parameters of the proposed neural network are optimized, and finally the modulation classification is realized. The experimental results show that, the proposed method has high modulation classification accuracy and less computation burden in low SNR.

Multiple Kernel Independent Component Analysis for Anti-jamming of Communication Radio

Abstract: The anti-jamming of communication radio has attracted intensive attentions from communication community. The blind source separation (BSS) is much effective when the jamming has entered. The multiple kernel independent component analysis (MKICA) is proposed instead of a single one, which can not only combine multiple kernels corresponding to different notions of similarity or information from multiple feature subsets, but also fuse distinctions of multiple kernels. The core of algorithm is the kernel canonical correlation analysis (KCCA), where the efficient use of multiple kernel trick makes it more suitable for different sources and more robust for different distributions. Hence, there will be a remarkable improvement of separation accuracy. Numerical experiments based on the artificially synthesized data and intermediate frequency (IF) signal containing clear voice demonstrate state-of-the-art performances of proposed algorithm. It is ideal for separation of useful communication signals when confronting with various jamming in the anti-jamming field.

Channel Discrepancies Adaptive Modulation Recognition Using Domain Adversarial Training

Abstract: In this paper, we introduce a channel discrepancies adaptive automatic modulation recognition (AMR) method, which employs the domain adversarial training (DAT) to tackle the issue of wireless channel mismatch between training and testing conditions. The channel mismatch is a critical problem for deep learning (DL) based AMR systems. In realistic scenarios, the channel environment mismatch commonly happens and a large mismatch may seriously degrade the recognition accuracy of signals. The introduced channel discrepancies adaptive AMR method consists of a l-dimensional convolutional neural network (1-D CNN) based recognition model and a domain discriminator model. The DAT encourages the 1-D CNN to extract channel invariant features and increase the robustness of the AMR system to new channel environment. We evaluate the proposed method and competition approaches on the popular RadioML2016. 04c and RadioML2016.10a dataset. Experimental results shows that the introduced channel discrepancies adaptive AMR system produce notable better recognition performance than that of the methods without domain adaptation for the channel discrepancies of training and testing datasets.

Automatic Modulation Classification: A Deep Architecture Survey

Abstract: Automatic modulation classification (AMC), which aims to blindly identify the modulation type of an incoming signal at the receiver in wireless communication systems, is a fundamental signal processing technique in the physical layer to improve the spectrum utilization efficiency. Motivated by deep learning (DL) high-impact success in many informatics domains, including radio signal processing for communications, numerous recent AMC methods exploiting deep networks have been proposed to overcome the existing drawbacks of traditional approaches. DL is capable of learning the underlying characteristics of radio signals effectively for modulation pattern recognition, which in turn improves the modulation classification performance under the presence of channel impairments. In this work, we first provide the fundamental concepts of various architectures, such as neural networks, recurrent neural networks, long short-term memory, and convolutional neural networks as the necessary background. We then convey a comprehensive study of DL for AMC in wireless communications, where technical analysis is deliberated in the perspective of state-of-the-art deep architectures. Remarkably, several sophisticated structures and advanced designs of convolutional neural networks are investigated for different data types of sequential radio signals, spectrum images, and constellation images to deal with various channel impairments. Finally, we discuss some primary research challenges and potential future directions in the area of DL for modulation classification.

Multisignal Modulation Classification Using Sliding Window Detection and Complex Convolutional Network in Frequency Domain

Abstract: With the development of the Internet of Things (IoT), the IoT devices are increasing day by day, resulting in increasingly scarce spectrum resources. At the same time, many IoT devices are facing inevitable malicious attacks. The cognitive Radio-enabled IoT (CR-IoT) is proposed as an effective method for spectrum resource allocation and risk monitoring in the IoT. The signal detection and modulation recognition are the key technologies for CR-IoT, addressing the problem of multisignal detection and automatic modulation classification (AMC) is one of the prerequisites for realizing secure dynamic spectrum access. Based on sliding window and deep learning (DL), this study proposes a multisignal frequency domain detection and recognition method. The frequency spectrum of the time-domain overlapping signal is obtained through the fast Fourier transform (FFT), and the frequency spectrum is segmented based on the signal energy detection method. Finally a complex convolutional neural network (CNN) is constructed for the identification of signal spectrum information. The proposed method can recognize 264 time-domain aliasing and frequency-closed signals with an accuracy of 97.3% under the influence of −2 dB corresponding to the noise of the calibration signal. In addition, the proposed method eliminates the influence of bandwidth, which can effectively detect and recognize the signal types of each component in the frequency band. This method has wide applicability and provides an effective scheme for the IoT cognitive technology.

Intelligent Radio Signal Processing: A Survey

Abstract: Intelligent signal processing for wireless communications is a vital task in modern wireless systems, but it faces new challenges because of network heterogeneity, diverse service requirements, a massive number of connections, and various radio characteristics. Owing to recent advancements in big data and computing technologies, artificial intelligence (AI) has become a useful tool for radio signal processing and has enabled the realization of intelligent radio signal processing . This survey covers four intelligent signal processing topics for the wireless physical layer, including modulation classification, signal detection, beamforming, and channel estimation. In particular, each theme is presented in a dedicated section, starting with the most fundamental principles, followed by a review of up-to-date studies and a summary. To provide the necessary background, we first present a brief overview of AI techniques such as machine learning, deep learning, and federated learning. Finally, we highlight a number of research challenges and future directions in the area of intelligent radio signal processing. We expect this survey to be a good source of information for anyone interested in intelligent radio signal processing, and the perspectives we provide therein will stimulate many more novel ideas and contributions in the future.

Jammer Classification in GNSS Bands Via Machine Learning Algorithms.

Abstract: This paper proposes to treat the jammer classification problem in the Global Navigation Satellite System bands as a black-and-white image classification problem, based on a time-frequency analysis and image mapping of a jammed signal. The paper also proposes to apply machine learning approaches in order to sort the received signal into six classes, namely five classes when the jammer is present with different jammer types and one class where the jammer is absent. The algorithms based on support vector machines show up to 94.90 % accuracy in classification, and the algorithms based on convolutional neural networks show up to 91.36 % accuracy in classification. The training and test databases generated for these tests are also provided in open access.

A Novel Attention Cooperative Framework for Automatic Modulation Recognition

Abstract: Modulation recognition plays an indispensable role in the field of wireless communications. In this paper, a novel attention cooperative framework based on deep learning is proposed to improve the accuracy of the automatic modulation recognition (AMR). Within this framework, a convolutional neural network (CNN), a recurrent neural network (RNN), and a generative adversarial network (GAN) are constructed to cooperate in AMR. A cyclic connected CNN (CCNN) is designed to extract spatial features of the received signal, and a bidirectional RNN (BRNN) is constructed for obtaining temporal features. To take full advantage of the complementarity and relevance between the spatial and temporal features, a fusion strategy based on global average and max pooling (GAMP) is proposed. To deal with different influence levels of the signal feature maps, we present the attention mechanism in this framework to realize recalibration. Besides, modulation recognition based on deep learning requires numerous data for training purposes, which is difficult to achieve in practical AMR applications. Therefore, an auxiliary classification GAN (ACGAN) is developed as a generator to expand the training set, and we modify the loss function of ACGAN to accommodate the processing of the actual in-phase and quadrature (I/Q) signal data. Considering the difference in distribution between generated data and real data, we propose a novel auxiliary weighing loss function to achieve higher recognition accuracy. Experimental results on the dataset RML2016.10a show that the proposed framework outperforms existing deep learning-based approaches and achieves 94% accuracy at high signal to noise ratio (SNR).