Cumulant based maximum likelihood classification for overlapped signals

Huang, Sai; Yao, Yuanyuan; Yan, Xiao; Zhang, Feng

doi:10.1049/el.2016.2409

Cited by 18 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over the past few years, numerous methods for AMC were proposed in the literature [3]. They can be mainly divided into two categories, namely, Likelihood-Based (LB) methods [4]- [6] and Feature-Based (FB) methods [7]- [11]. The former treats AMC as a hypothesis testing problem, where the exact or approximated likelihood function of the incoming signal is calculated and compared with a threshold value.…”

Section: Introductionmentioning

confidence: 99%

“…Numerous features with their respective merits and defects were proposed. Among them, the most used are high-order cumulants [6]- [8], wavelet transform [9], and cyclic statistics [10]. As for the classifier, machine learning algorithms, such as support vector machines (SVM) [11], Knearest neighbor (KNN) [8], and artificial neural networks [10], have been widely studied for inference.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Training Images Generation for CNN Based Automatic Modulation Classification

2021

View full text Add to dashboard Cite

Convolutional neural network (CNN) models have recently demonstrated impressive classification and recognition performance on image and video processing scope. In this paper, we investigate the application of CNN to identifying modulation classes for digitally modulated signals. First, the received baseband data samples of modulated signal are gathered up and transformed to generate the constellationlike training images for convolutional networks. Among the resulting training images, the proposed convolutional gray image is preferred for network training and inference because of the lower computational burden. Second, we propose to use a multiple-scale convolutional neural network (MSCNN) as the classifier. The skip-connection technique is deployed for mitigating the negative effect of vanishing gradients and overfitting during the network training process. Numerical simulations have been carried out to validate the effectiveness of the proposed scheme, the results show that the proposed scheme outperforms the traditional algorithms in terms of classification accuracy.INDEX TERMS Convolutional neural network, automatic modulation classification, deep learning.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Training Images Generation for CNN Based Automatic Modulation Classification

2021

View full text Add to dashboard Cite

show abstract

“…Comparatively, FB methods deal with modulation classification straightforwardly without prior information [6]. Various features are widely utilized in FB methods including high-order statistics [7], cyclostationary spectrum, etc. Kim et al implemented the maximum of cyclostationary spectrum over frequency to reduce the computational complexity [8].…”

Section: Introductionmentioning

confidence: 99%

Automatic Modulation Classification Using Hybrid Convolutional Neural Network

Zhang¹,

Anping²,

Chai³

et al. 2020

Proceedings of the 13th EAI International Conference on Mobile Multimedia Communications, Mobimedia 2020, 27-28 August 2020, Cy

View full text Add to dashboard Cite

“…Better robustness to phase offset is achieved, but minimum distance criterion for decision making leads to sub-optimal classification performance [11]. Huang et al proposed a cumulant-based maximum likelihood classification scheme, where the sample estimate of cumulant is utilized for classification and classification decision is made by maximizing the asymptotic distribution function of the cumulant [12]. Gardner et al first implemented cyclostationary-based modulation classification method and it performs superior performance at low signal-to-noise (SNR) sense by exploiting the discrepancies on the cyclic spectrum features [13].…”

Section: Introductionmentioning

confidence: 99%

Automatic Modulation Classification Using Compressive Convolutional Neural Network

Huang

Chai

et al. 2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

The deep convolutional neural network has strong representative ability, which can learn latent information repeatedly from signal samples and improve the accuracy of automatic modulation classification (AMC). In this paper, a novel compressive convolutional neural network (CCNN) is proposed for AMC, where different constellation images, i.e., regular constellation images (RCs) and contrast enhanced grid constellation images (CGCs), are generated as network inputs from received signals. Moreover, a compressive loss constraint is proposed to train the CCNN, which aims at capturing high-dimensional features for modulation classification. Additionally, CCNN utilizes intra-class compactness and inter-class separability to enhance the classification and robustness performance for the different orders of modulations. The simulation results demonstrate that CCNN displays superior classification and robustness performance than existing AMC methods.INDEX TERMS Automatic modulation classification, compressive loss constraint, deep convolutional neural network, multiple constellation images.

show abstract

Cumulant based maximum likelihood classification for overlapped signals

Cited by 18 publications

References 10 publications

Training Images Generation for CNN Based Automatic Modulation Classification

Training Images Generation for CNN Based Automatic Modulation Classification

Automatic Modulation Classification Using Hybrid Convolutional Neural Network

Automatic Modulation Classification Using Compressive Convolutional Neural Network

Contact Info

Product

Resources

About