检索结果-内蒙古大学图书馆

Artificial Intelligence-Driven Real-Time automatic modulation classification Scheme for Next-Generation Cellular Networks

引用

IEEE ACCESS 2021年 9卷 155584-155597页

作者： Kaleem, Zeeshan Ali, Muhammad Ahmad, Ishtiaq Khalid, Waqas Alkhayyat, Ahmed Jamalipour, Abbas COMSATS Univ Islamabad Elect & Comp Engn Dept Wah Campus Rawalpindi 47040 Wah Cantt Pakistan Gomal Univ Fac Engn & Technol Elect Engn Dept Dera Ismail Khan 29220 Pakistan Korea Univ Inst Ind Technol Sejong 30019 South Korea Islamic Univ Coll Tech Engn Najaf 7003 Iraq Univ Sydney Sch Elect & Informat Engn Sydney NSW 2006 Australia

automatic modulation classification (AMC) can play an important role in the timely identification of suspicious and unwanted signal activities to enable secure communication in future next-generation cellular networks. Moreover, AMC can detect the modulation scheme without even adding additional overhead in the signal. In this paper, we developed a universal software radio peripheral (USRP) based intelligent AMC system to detect and classify various digital modulation schemes in real-time. For each modulation scheme, we extracted different spectral features for different values of signal-to-noise ratio (SNR) values. Based on the extracted features, we train the neural network to classify the modulation schemes. Experimental results show that we achieve around 97% classification accuracy in real-time as compared to the existing offline classification schemes. Moreover, we also compare the performance of the proposed model with HisarMod2019.1 model in terms of various metrics such as cross-entropy and mean square error. Results clearly demonstrates the efficiency of the proposal for real-time implementation and classification.

关键词： modulation Signal to noise ratio Feature extraction Real-time systems Support vector machines Mathematical models Convolutional neural networks automatic modulation classification artificial intelligence deep learning real-time signal detection USRP

来源：评论

学校读者我要写书评

暂无评论

Deep Sparse Learning for automatic modulation classification Using Recurrent Neural Networks

引用

SENSORS 2021年第19期21卷 6410-6410页

作者： Zang, Ke Wu, Wenqi Luo, Wei Zhejiang Univ Coll Biomed Engn & Instrument Sci Yuquan Campus38 Zheda Rd Hangzhou 310027 Zhejiang Peoples R China Chinese Univ Hong Kong Dept Biomed Engn Shatin Hong Kong Peoples R China

Deep learning models, especially recurrent neural networks (RNNs), have been successfully applied to automatic modulation classification (AMC) problems recently. However, deep neural networks are usually overparameterized, i.e., most of the connections between neurons are redundant. The large model size hinders the deployment of deep neural networks in applications such as Internet-of-Things (IoT) networks. Therefore, reducing parameters without compromising the network performance via sparse learning is often desirable since it can alleviates the computational and storage burdens of deep learning models. In this paper, we propose a sparse learning algorithm that can directly train a sparsely connected neural network based on the statistics of weight magnitude and gradient momentum. We first used the MNIST and CIFAR10 datasets to demonstrate the effectiveness of this method. Subsequently, we applied it to RNNs with different pruning strategies on recurrent and non-recurrent connections for AMC problems. Experimental results demonstrated that the proposed method can effectively reduce the parameters of the neural networks while maintaining model performance. Moreover, we show that appropriate sparsity can further improve network generalization ability.

关键词： automatic modulation classification deep sparse learning recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Dense Layer Dropout Based CNN Architecture for automatic modulation classification 26

Dense Layer Dropout Based CNN Architecture for Automatic Mod...

引用

26th National Conference on Communications (NCC)

作者： Dileep, P. Das, Dibyajyoti Bora, Prabin Kumar IIT Guwahati Dept EEE Gauhati Assam India

ISBN: (纸本)9781728151205

automatic modulation classification (AMC) is an important part of signal identification for cognitive radio as well as military communication. The problem has been approached traditionally using either likelihood-based or feature-based methods. Since the problem is a classification task, a deep learning (DL) based approach can be an attractive solution. A number of convolutional neural network (CNN) based DL algorithms were introduced for AMC recently. The complex baseband signals that are represented as In-phase and Quadrature (IQ) samples are applied to train the CNN. We propose a new CNN architecture that significantly improves the classification accuracy over existing results in the literature while keeping the number of trainable parameters low. In this architecture, dropouts are applied only in the dense layers.

关键词： Deep learning Convolutional neural networks automatic modulation classification IQ samples Cognitive radio

来源：评论

学校读者我要写书评

暂无评论

A Two-fold Group Lasso based Lightweight Deep Neural Network for automatic modulation classification

A Two-fold Group Lasso based Lightweight Deep Neural Network...

引用

IEEE International Conference on Communications (IEEE ICC) / Workshop on NOMA for 5G and Beyond

作者： Liu, Xiaofeng Wang, Qing Wang, Haozhi Tianijn Univ Sch Elect & Informat Engn Tianjin Peoples R China

ISBN: (纸本)9781728174402

automatic modulation classification (AMC) is a hot topic in modern wireless communication, which is a classification problem essentially. The deep learning methods have been applied to AMC gradually, for its excellent performance in classification, regression and decision-making tasks. However, the deep learning methods always come with complex network structure, vast training parameters and extra long training time, which seriously affected its application and promotion on power-limited and resource-constrained devices. In this paper, we propose a lightweight end-to-end AMC model named lightweight deep neural network (LDNN) via a novel group-level sparsity inducing norm, which can help network pruning itself automatically to obtain a highly compact network. In order to solve the problem of recognition confusing types, such as QAM16 and QAM 64 are always been confused in AMC task, a improved two-step training lightweight deep neural network (TLDNN) is well designed to improve the recognition accuracy. Experimental results shows the accuracy improvement of the proposed lightweight compact networks via two-fold group lasso regularization and two-step training schemes.

关键词： automatic modulation classification Group sparsity Lightweight Deep network

来源：评论

学校读者我要写书评

暂无评论

Radio Signal automatic modulation classification based on Deep Learning and Expert Features 4

Radio Signal Automatic Modulation Classification based on De...

引用

4th IEEE Information Technology, Networking, Electronic and Automation Control Conference (ITNEC)

作者： Yao, Tianyao Chai, Yuan Wang, Shuai Miao, Xiaqing Bu, Xiangyuan Beijing Inst Technol Sch Informat & Elect Beijing Peoples R China China Acad Space Technol Inst Telecommun Satellite Beijing Peoples R China

ISBN: (纸本)9781728143903

automatic modulation classification (AMC) becomes more and more important in the electronic reconnaissance. Recently, lots of researchers focus on deep learning architecture based AMC approach but the recognition rate of WBFM and QAM is less than desirable. In this paper, we proposed a joint AMC model of two expert features and CNN-LSTM networks. Before entering the deep learning network, the un-classified signal is first detected whether WBFM or not by the maximum of zero-center normalization amplitude spectrum density. Then the signal which is not WBFM will be inputted to the CNN-LSTM network, while QAM16 and QAM64 are regarded as the same class here. Finally, Haar-wavelet transform crest searching is used to classify QAM16 and QAM64. Compared with former CNN-LSTM architecture, the results of the experiment and deduction show the average recognition rate of the proposed model is increased by 11.5% at 10 dB SNR.

关键词： electronic reconnaissance automatic modulation classification CNN LSTM expert feature

来源：评论

学校读者我要写书评

暂无评论

An effective approach for low-complexity maximum likelihood based automatic modulation classification of STBC-MIMO systems

引用

Frontiers of Information Technology & Electronic Engineering 2020年第3期21卷 465-476页

作者： Maqsood H.SHAH Xiao-yu DANG College of Electronic and Information Engineering Nanjing University of Aeronautics and AstronauticsNanjing 211106China

A low-complexity likelihood methodology is proposed for automatic modulation classification of orthogonal space-time block code(STBC)based multiple-input multiple-output(MIMO)*** exploit the zero-forcing equalization technique to modify the typical average likelihood ratio test(ALRT)*** proposed ALRT function has a low computational complexity compared to existing ALRT functions for MIMO systems *** proposed approach is analyzed for blind channel scenarios when the receiver has imperfect channel state information(CSI).Performance analysis is carried out for scenarios with different numbers of ***-STBC systems with 2×2 and 2×1 and space-time transmit diversity with a 4×4 transmit and receive antenna configuration are considered to verify the proposed *** popular modulation schemes are used as the modulation test ***-Carlo simulations are performed to evaluate the proposed methodology,using the probability of correct classification as the *** results show that the proposed approach has high classification accuracy at low signal-to-noise ratios and exhibits robust behavior against high CSI estimation error variance.

关键词： Multiple-input multiple-output Space-time block code Maximum likelihood automatic modulation classification Zero-forcing

来源：评论

学校读者我要写书评

暂无评论

automatic modulation classification in α-stable noise using graph-based generalized second-order cyclic spectrum analysis

引用

PHYSICAL COMMUNICATION 2019年 37卷 100854-000页

作者： Yan, Xiao Zhang, Guoyu Wu, Hsiao-Chun Liu, Guannan Univ Elect Sci & Technol China Sch Aeronaut & Astronaut Chengdu 611731 Sichuan Peoples R China Louisiana State Univ Sch Elect Engn & Comp Sci Baton Rouge LA 70803 USA

An innovative automatic modulation classification using graph-based generalized second-order cyclic spectrum analysis in the background of alpha-stable noise is presented in this paper. In our proposed method, the three-dimensional generalized second-order cyclic spectrum of the modulated signal is first constructed from the nonlinear Hilbert transform. According to the generalized second-order cyclic spectrum, the signal is mapped onto a set of direct weighted rings in the graph domain. Then, the graph features of the modulated signal are extracted from the lower-upper decomposition of the corresponding adjacency matrices. The Hamming distance is employed to measure the distinctions between the feature parameters derived from the training and test data, and the modulation scheme can be identified thereby. Monte Carlo simulation results demonstrate that the proposed approach can achieve better classification accuracy than other existing methods for the alpha-stable noise scenario. (C) 2019 Elsevier B.V. All rights reserved.

关键词： automatic modulation classification Generalized second-order cyclic spectrum Graph mapping Adjacency matrix Hamming distance

来源：评论

学校读者我要写书评

暂无评论

automatic modulation classification of Overlapped Sources Using Multi-Gene Genetic Programming With Structural Rick Minimization principle

引用

IEEE ACCESS 2018年 6卷 48827-48839页

作者： Huang, Sai Jiang, Yizhou Qin, Xiaoqi Gao, Yue Feng, Zhiyong Zhang, Ping Beijing Univ Posts & Telecommun Key Lab Universal Wireless Commun Minist Educ Beijing 100876 Peoples R China Nanjing Univ Aeronaut & Astronaut Key Lab Dynam Cognit Syst Electromagnet Spectrum Minist Ind & Informat Technol Nanjing 211106 Jiangsu Peoples R China Queen Mary Univ London Sch Elect Engn & Comp Sci London E1 4NS England

As the spectrum environment becomes increasingly crowded and complicated, primary users may be interfered by secondary users and other illegal users. automatic modulation classification (AMC) of a single source cannot recognize the overlapped sources. Consequently, the AMC of overlapped sources attracts much attention. In this paper, we propose a genetic programming-based modulation classification method for overlapped sources (GPOS). The proposed GPOS consists of two stages, the training stage, and the classification stage. In the training stage, multi-gene genetic programming (MGP)-based feature engineering transforms sample estimates of cumulants into highly discriminative MGP-features iteratively, until optimal MGP-features (OMGP-features) are obtained, where the structural risk minimization principle (SRMP) is employed to evaluate the classification performance of MGP-features and train the classifier. Moreover, a self-adaptive genetic operation is designed to accelerate the feature engineering process. In the classification stage, the classification decision is made by the trained classifier using the OMGP-features. Through simulation results, we demonstrate that the proposed scheme outperforms other existing methods in terms of classification performance and robustness in case of varying power ratios and fading channel.

关键词： automatic modulation classification cumulant multi-gene genetic programming overlapped signal classification structural risk minimization principle

来源：评论

学校读者我要写书评

暂无评论

automatic modulation classification: A Deep Learning Enabled Approach

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2018年第11期67卷 10760-10772页

作者： Meng, Fan Chen, Peng Wu, Lenan Wang, Xianbin Southeast Univ Sch Informat Sci & Engn Nanjing 210096 Jiangsu Peoples R China Southeast Univ State Key Lab Millimeter Waves Nanjing 210096 Jiangsu Peoples R China Western Univ Dept Elect & Comp Engn London ON N6A 3K7 Canada

automatic modulation classification (AMC), which plays critical roles in both civilian and military applications, is investigated in this paper through a deep learning approach. Conventional AMCs can be categorized into maximum likelihood (ML) based (ML-AMC) and feature-based AMC. However, the practical deployment of ML-AMCs is difficult due to its high computational complexity, and the manually extracted features require expert knowledge. Therefore, an end-to-end convolution neural network (CNN) based AMC (CNN-AMC) is proposed, which automatically extracts features from the long symbol-rate observation sequence along with the estimated signal-to-noise ratio (SNR). With CNN-AMC, a unit classifier is adopted to accommodate the varying input dimensions. The direct training of CNN-AMC is challenging with the complicated model and complex tasks, so a novel two-step training is proposed, and the transfer learning is also introduced to improve the efficiency of retraining. Different digital modulation schemes have been considered in distinct scenarios, and the simulation results show that the CNN-AMC can outperform the feature-based method, and obtain a closer approximation to the optimal ML-AMC. Besides, CNN-AMCs have the certain robustness to estimation error on carrier phase offset and SNR. With parallel computation, the deep-learning-based approach is about 40 to 1700 times faster than the ML-AMC regarding inference speed.

关键词： automatic modulation classification convolution neural network deep learning two-step training

来源：评论

学校读者我要写书评

暂无评论

automatic modulation classification Using Moments and Likelihood Maximization

引用

IEEE COMMUNICATIONS LETTERS 2018年第5期22卷 938-941页

作者： Abu-Romoh, Mohannad Aboutaleb, Ahmed Rezki, Zouheir Univ Idaho Dept Elect & Comp Engn Moscow ID 83844 USA

Motivated by the fact that moments of the received signal are easy to compute and can provide a simple way to automatically classify the modulation of the transmitted signal, we propose a hybrid method for automatic modulation classification that lies in the intersection between likelihood-based and feature-based classifiers. Specifically, the proposed method relies on statistical moments along with a maximum likelihood engine. We show that the proposed method offers a good trade-off between classification accuracy and complexity relative to the maximum likelihood classifier. Furthermore, our classifier outperforms state-of-the-art machine learning classifiers, such as genetic programming-based K-nearest neighbor classifiers, the linear support vector machine classifier and the fold-based Kolmogorov-Smirnov algorithm.

关键词： automatic modulation classification support vector machines genetic programming machine learning moments-based classification

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：