检索结果-内蒙古大学图书馆

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

ELECTRONICS LETTERS 2019年第16期55卷 895-+页

作者： Wu, Hao Li, Yaxing Zhou, Liang Meng, Jin Naval Univ Engn Natl Key Lab Sci & Technol Vessel Integrated Powe Wuhan 430033 Hubei Peoples R China

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.

关键词： cognitive radio signal classification modulation signal detection image representation feature extraction learning (artificial intelligence) pattern classification convolutional neural nets automatic modulation classification cognitive radio spectrum sensing modulation signals CS constellation diagram CD two-branch CNN model gradient decent strategy multifeature fusion technique simple neural network state-of-the-art deep learning-based methods convolutional neural network-based AMC method

来源：评论

学校读者我要写书评

暂无评论

Deep Hierarchical Network for automatic modulation classification

引用

IEEE ACCESS 2019年 7卷 94604-94613页

作者： Nie, Jinbo Zhang, Yan He, Zunwen Chen, Shiyao Gong, Shouliang Zhang, Wancheng Beijing Inst Technol Sch Informat & Elect Beijing 100081 Peoples R China

In non-cooperative communication scenarios, automatic modulation classification (AMC) is the premise of information acquisition. It has been a difficult issue for decades due to the attenuation and interference during wireless transmission. In this paper, a novel deep hierarchical network (DHN) based on convolutional neural network (CNN) is proposed for the AMC. The model is designed to combine the shallow features with high-level features. Thus, it can simultaneously have global receptive field and location information through multi-level feature extraction and does not require any transformation of the raw data. To make full use of limited data, a new method is proposed to use signal-to-noise ratio (SNR) as a weight in training instead of working as an indicator of system robustness. Furthermore, some other deep learning methods have been used to explore whether they could improve the performance of the proposed model. Several new techniques have been chosen to be applied in the DHN at last. Then, a detailed analysis of the improvement in network performance is provided. Combination of the DHN and the weighted-loss can achieve more than 93% classification accuracy which is the best performance in an open source dataset.

关键词： automatic modulation classification deep hierarchical network receptive field signal-to-noise ratio weight

来源：评论

学校读者我要写书评

暂无评论

Robust automatic modulation classification based on convolutional and recurrent fusion network

引用

PHYSICAL COMMUNICATION 2020年 43卷 101213-101213页

作者： Lyu, Zhichao Wang, Yu Li, Wenmei Guo, Liang Yang, Jie Sun, Jinlong Liu, Miao Gui, Guan Nanjing Univ Posts & Telecommun Coll Telecommun & Informat Engn Nanjing 210003 Peoples R China Nanjing Univ Posts & Telecommun Sch Geog & Biol Informat Nanjing 210023 Peoples R China China Acad Informat & Commun Technol Beijing 100191 Peoples R China

automatic modulation classification (AMC) is a critical step to recognize the unknown signal modulation types. It is widely applied in non-cooperative communication systems with diverse modulation types and complex communication environments. In recent years, existing deep learning based AMC methods have been developed to improve the performance of classification in additive white Gaussian noise (AWGN) or Rayleigh channel. However, these methods do not consider the interference problem caused by the Doppler shift in high mobile communication environment. In this paper, we propose a deep learning based robust AMC (RAMC) method to effectively suppress the Doppler shift and achieve classification performance. The proposed convolutional and recurrent fusion network (CRFN) consists of the combination of convolutional neural network (CNN) and simple recurrent unit (SRU) to classify eight types of modulation signal under additive white Gaussian noise (AWGN) and different Doppler shifts. We consider four kinds of fusion networks, i.e., SRU series CNN (SSC), CNN series SRU (CSS), CNN parallel SRU (CPS) and weight average (WA). Simulation results show that the proposed CRFN-CSS method achieves the best performance and brings better performance than either CNN or SRU in 100 Hz Doppler shift. What is more, CRFN-CSS is also robust in the small range of Doppler shifts. (c) 2020 Elsevier B.V. All rights reserved.

关键词： automatic modulation classification Deep learning Rayleigh channel Doppler shift Convolutional and recurrent fusion network (CRFN)

来源：评论

学校读者我要写书评

暂无评论

A comparison of clustering algorithms for automatic modulation classification

引用

EXPERT SYSTEMS WITH APPLICATIONS 2020年 151卷 113317-113317页

作者： Mouton, Jacques P. Ferreira, Melvin Helberg, Albertus S. J. North West Univ Sch Elect Elect & Comp Engn ZA-2531 Potchefstroom South Africa

In this paper, the k-means, k-medoids, fuzzy c-means, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), Ordering Points To Identify the Clustering Structure (OPTICS), and hierarchical clustering algorithms (with the addition of the elbow method) are examined for the purpose of automatic modulation classification (AMC). This study compares these algorithms in terms of classification accuracy and execution time for either estimating the modulation order, determining centroid locations, or both. The best performing algorithms are combined to provide a simple AMC method which is then evaluated in an Additive White Gaussian Noise (AWGN) channel with M-Quadrature Amplitude modulation (QAM) and M-Phase Shift Keying (PSK). Such an AMC method does not rely on any thresholds to be set by a human or machine learning algorithm, resulting in a highly flexible system. The proposed method can be configured to not give false positives, making it suitable for applications such as spectrum monitoring and regulatory enforcement. (C) 2020 Published by Elsevier Ltd.

关键词： automatic modulation classification Constellation diagram I/Q plane Clustering algorithm Centroid estimation

来源：评论

学校读者我要写书评

暂无评论

Identifying physical-layer attacks for IoT security: An automatic modulation classification approach using multi-module fusion neural network

引用

PHYSICAL COMMUNICATION 2020年 43卷 101180-101180页

作者： Huang, Sai Lin, Chunsheng Zhou, Kai Yao, Yuanyuan Lu, Hua Zhu, Fusheng Beijing Univ Posts & Telecommun Key Lab Universal Wireless Commun Beijing 100876 Peoples R China GuangDong Commun Networks Inst Guangzhou 510700 Guangdong Peoples R China Beijing Informat Sci & Technol Univ Sch Informat & Commun Engn Beijing 100101 Peoples R China NUAA Minist Ind & Informat Technol Key Lab Dynam Cognit Syst Electromagnet Spectrum Nanjing 211106 Peoples R China

The Internet of Things (IoT) is increasingly flourishing with establishing ubiquitous connections in every aspect of our daily lives and industrial production. However, the active physical-layer threats such as spoofing and jamming largely degrades the communication performance and makes the IoT network messy. automatic modulation classification (AMC), which identifies the modulation formats of the active attack, plays a vital role in physical-layer security of IoT. In this paper, a multi-module fusion neural network (MMFN) is proposed to identify the signal modulations using a novel feature named pixel-coloring constellation images (PCCs). Specifically, a pixel-coloring constellation projection algorithm (PCCP) is proposed to convert raw modulated signals into PCCs, which are the inputs of the following MMFN. The MMFN is proposed to extract discriminative features and make the final classification decisions. In MMFN, multi-module fusion strategy is adopted to possess a strong representation ability and the characterization module is designed to balance the tradeoff between the number of parameters and the dimensions of extracted representative features. Simulation results exhibit that the proposed MMFN scheme achieves 90% classification accuracy at 1 dB signal to noise ratio (SNR) when the symbol length is set as 2048, and it outperforms the recent deep learning based AMC methods, which demonstrates its superior classification performance. (c) 2020 Elsevier B.V. All rights reserved.

关键词： automatic modulation classification Deep learning Internet of Things security Multi-module fusion neural network Pixel-coloring constellation images

来源：评论

学校读者我要写书评

暂无评论

automatic modulation classification of Radar Signals Using the Pseudo Margenau-Hill Distribution 2018

Automatic Modulation Classification of Radar Signals Using t...

引用

10th International Conference on Computer and Automation Engineering (ICCAE)

作者： Zeng, Xiaodong China Elect Technol Grp Corp Res Inst 10 Beijing Peoples R China

ISBN: (纸本)9781450364102

In a non-cooperative environment, it is difficult for an electronic intelligence (ELINT) receiver to implement intra-pulse modulation classification. This paper presents an approach based on the Pseudo Margenau-Hill distribution (PMHD). The algorithm computes the PMHD of the detected radar signals and extracts the ridges. Then, it defines three characteristic features, namely, the coefficient of piecewice linear fitting, the hop number of the ridge and the coefficient of inverted V Shape and realises the automatic modulation classification (AMC) of four kinds of radar signals under negative signal to noise ratio (SNR). The probability of successful recognition (PSR) is greater than 90%.

关键词： Pseudo Margenau-Hill distribution automatic modulation classification Radar

来源：评论

学校读者我要写书评

暂无评论

Accuracy Analysis of Feature-based automatic modulation classification with Blind modulation Detection

Accuracy Analysis of Feature-based Automatic Modulation Clas...

引用

International Conference on Computing, Networking and Communications (ICNC)

作者： Ghasemzadeh, Pejman Banerjee, Subharthi Hempel, Michael Sharif, Hamid Univ Nebraska Lincoln Dept Elect & Comp Engn Lincoln NE 68588 USA

ISBN: (纸本)9781538692233

The process of automatic classification of a detected signal's employed modulation type has gained importance in recent years. The goal of such an approach is to maximize the achievable throughput for intelligent receiver designs in civilian applications as well as jamming malicious signals in military applications. automatic modulation classification (AMC) increases in difficulty since there is no a-priori knowledge of transmitted signal properties, such as signal power, carrier frequency, or bandwidth, nor any associated link properties such as channel state information (CSI), noise characteristics, signal-to-noise ratio (SNR) or any offset in frequency and phase. The most complex, albeit also most realistic, scenarios for AMC are faced when considering Non-Gaussian noise with multipath fading in frequency selective and time-varying channels. Different methods have been proposed in the literature to estimate unknown signals and channel parameters for AMC. However, a key consideration in selecting among them is attaining low computational complexity in order for AMC to become a technique feasible for real-time applications. Predominantly, blind AMC and associated parameter estimation utilizes feature-based approaches, owing to their low-complexity calculations of statistical values. In this work, we have analyzed the accuracy of High-order Statistics-based (HoS) methods utilizing feature extraction approaches, Support Vector Machine classifiers, and estimation techniques to determine an optimized framework for different real-time applications.

关键词： automatic modulation classification Blind modulation classification Feature-based modulation classification High-order Statistic-based (HoS) Features Channel State Information (CSI)

来源：评论

学校读者我要写书评

暂无评论

Developing RFML Intuition: An automatic modulation classification Architecture Case Study

Developing RFML Intuition: An Automatic Modulation Classific...

引用

IEEE Military Communications Conference (MILCOM)

作者： Clark, William H. Arndorfer, Vanessa Tamir, Brook Kim, Daniel Vives, Cristian Morris, Hunter Wong, Lauren Headley, William C. Virginia Tech Ted & Karyn Hume Ctr Natl Secur & Technol Blacksburg VA 24061 USA

ISBN: (纸本)9781728142807

The application of machine learning to automatic modulation classification (AMC) has typically used transfer learning from architectures found in the image classification domain. This work examines deviations from the image classification architectures by drawing from traditional expert feature systems within the AMC domain. Two types of 'expert architectures' are contrasted against the traditional image processing architectures;the first utilizes a more traditional one-versus-all binary classification with decision fusion approach, while the second inherits a hierarchical decision tree structure that leverages expert knowledge of the classes. When compared with a typical image processing architecture there are marginal classifier performance gains associated with the structures taken from expert AMC systems;however, the expert architectures allow for greater intuition, adaptability, and future-proofing in general.

关键词： automatic modulation classification AMC machine learning convolutional neural network CNN

来源：评论

学校读者我要写书评

暂无评论

automatic modulation classification of Cochannel Signals using Deep Learning 23

Automatic Modulation Classification of Cochannel Signals usi...

引用

23rd IEEE International Conference on Digital Signal Processing (DSP)

作者： Sun, Jiajun Wang, Guohua Lin, Zhiping Razul, Sirajudeen Gulam Lai, Xiaoping Nanyang Technol Univ Sch Elect & Elect Engn Singapore Singapore Nanyang Technol Univ Sensor Array TL NTU Singapore Singapore Hangzhou Dianzi Univ Inst Informat & Control Hangzhou Zhejiang Peoples R China

ISBN: (纸本)9781538668122;9781538668115

This paper presents a new approach to the automatic modulation classification (AMC) of cochannel signals based on deep learning techniques using convolutional neural network (CNN). Conventional approaches to this problem use features from higher order statistics and cyclic statistics. Data with long length is required to achieve good feature estimation and high classification rate. However, data with long length may cause problems such as latency to practical operations. By applying deep learning techniques based on CNN, AMC can be conducted directly by exploring raw features itself. Meanwhile, oversampled data is reshaped to a two-dimensional data matrix in order to take advantages of the image processing capability of CNN. One main advantage of this method is that much shorter data length is required to achieve good classification rate as compared to conventional approaches. Simulation results are provided to demonstrate the effectiveness of the proposed methods.

关键词： automatic modulation classification machine learning deep learning cochannel signal CNN

来源：评论

学校读者我要写书评

暂无评论

Effective Feature-Based automatic modulation classification Method Using DNN Algorithm 1

Effective Feature-Based Automatic Modulation Classification ...

引用

1st International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Lee, Sang Hoon Kim, Kwang-Yul Kim, Jae Hyun Shin, Yoan Soongsil Univ Sch Elect Engn Seoul 06978 South Korea Ajou Univ Dept Elect & Comp Engn Suwon 16499 South Korea

ISBN: (纸本)9781538678220

In this paper, we propose an effective feature-based automatic modulation classification (AMC) method using a deep neural network (DNN). In order to classify the modulation type, we consider effective features according to the modulation signals. The proposed method removes the meaningless features that have little influence on the classification and only uses the effective features that have high influence by analyzing the correlation coefficients. From the simulation results, we observe that the proposed method can make the AMC system low complexity.

关键词： automatic modulation classification deep neural network cumulant correlation effective features

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：