2020
DOI: 10.1109/access.2020.3017641
|View full text |Cite
|
Sign up to set email alerts
|

Automatic Modulation Classification Scheme Based on LSTM With Random Erasing and Attention Mechanism

Abstract: Automatic modulation classification (AMC) is a key technology of cognitive radio used in non-cooperative communication. Recently, deep learning has been applied to AMC tasks. In this paper, an AMC scheme based on deep learning is proposed, which combines random erasing and attention mechanism to achieve high classification accuracy. Firstly, we propose two data augmentation methods, random erasing at sample level and random erasing at amplitude/phase (AP) channel level. The former replaces training samples wit… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
18
0
7

Year Published

2021
2021
2024
2024

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 45 publications
(25 citation statements)
references
References 18 publications
0
18
0
7
Order By: Relevance
“…Occlusion in MOT manifests itself due to the absence of some features of the target. We propose a simulated occlusion strategy based on random erasure [39] applicable to the training process of the LDAE model and simulate object occlusion on the training data. Random erasure is to randomly select a rectangular area in the image and use random values to erase its pixels.…”
Section: Proposed Methodsmentioning
confidence: 99%
See 1 more Smart Citation
“…Occlusion in MOT manifests itself due to the absence of some features of the target. We propose a simulated occlusion strategy based on random erasure [39] applicable to the training process of the LDAE model and simulate object occlusion on the training data. Random erasure is to randomly select a rectangular area in the image and use random values to erase its pixels.…”
Section: Proposed Methodsmentioning
confidence: 99%
“…Occlusion in MOT manifests itself due to the absence of some features of the target. We propose a simulated occlusion strategy based on random erasure [39]…”
Section: Simulated Occlusion Strategymentioning
confidence: 99%
“…where u i represents the i th word in the sequence of target language; c i represents the background vector of the word i [ 20 ]. Assume that the hidden layer state at the moment j of the encoder is H j , and its corresponding background vector can be calculated by …”
Section: Algorithm Designmentioning
confidence: 99%
“…W ITH the development of Deep Learning (DL), many DL-based models, such as Convolutional Neural Networks (CNN) [1]- [6], Long Short-Term Memory Recurrent Neural Networks (LSTM-RNN) [7]- [9], and models [10], [11] combined with CNN and LSTM-RNN, have been proposed for Automatic Modulation Classification (AMC). Although these deep models have achieved great successes and outperformed traditional classifiers, they also bring some hidden security problems.…”
Section: Introductionmentioning
confidence: 99%