One-Dimensional Deep Attention Convolution Network (ODACN) for Signals Classification
Handcraft features are commonly used for signal classification, which is a time-consuming feature engineering. In order to develop a general and robust feature learning method for radio signals, a novel One-dimensional Deep Attention Convolution Network (ODACN) is proposed to automatically extract d...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8926472/ |
| _version_ | 1818922310111854592 |
|---|---|
| author | Shuyuan Yang Chen Yang Dongzhu Feng Xiaoyang Hao Min Wang |
| author_facet | Shuyuan Yang Chen Yang Dongzhu Feng Xiaoyang Hao Min Wang |
| author_sort | Shuyuan Yang |
| collection | DOAJ |
| description | Handcraft features are commonly used for signal classification, which is a time-consuming feature engineering. In order to develop a general and robust feature learning method for radio signals, a novel One-dimensional Deep Attention Convolution Network (ODACN) is proposed to automatically extract discriminative features and classify various kinds of signals. First, one-dimensional (1-D) sparse filters are designed to learn hierarchical features of raw signals. Second, an attention layer is constructed to weight and assemble feature maps, to derive more context-relevant representation. By using simple 1-D filtering, ODACN is characteristic of less parameters and lower computation complexity than traditional Convolutional Neural Networks (CNNs). Moreover, feature attention can mimic a succession of partial glimpses of humans and focus on context parts of signals, thus helps in recognizing signals even at low Signal-to-Noise Ratio (SNR). Some experiments are taken to classify 31 kinds of signals with different modulation and channel coding types, and the results show that ODACN can achieve accurate classification of very similar signals, without any prior knowledge and manual operation. |
| first_indexed | 2024-12-20T01:51:30Z |
| format | Article |
| id | doaj.art-5a67743271b54f1aae46cb22d0c33abc |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T01:51:30Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-5a67743271b54f1aae46cb22d0c33abc2022-12-21T19:57:38ZengIEEEIEEE Access2169-35362020-01-0182804281210.1109/ACCESS.2019.29581318926472One-Dimensional Deep Attention Convolution Network (ODACN) for Signals ClassificationShuyuan Yang0https://orcid.org/0000-0002-4796-5737Chen Yang1https://orcid.org/0000-0003-0034-2265Dongzhu Feng2https://orcid.org/0000-0001-5467-2759Xiaoyang Hao3https://orcid.org/0000-0002-6062-841XMin Wang4https://orcid.org/0000-0002-7571-1662School of Artificial Intelligence, Xidian University, Xi’an, ChinaSchool of Artificial Intelligence, Xidian University, Xi’an, ChinaSchool of Aerospace Science and Technology, Xidian University, Xi’an, ChinaSchool of Artificial Intelligence, Xidian University, Xi’an, ChinaKey Laboratory of Radar Signal Processing, Xidian University, Xi’an, ChinaHandcraft features are commonly used for signal classification, which is a time-consuming feature engineering. In order to develop a general and robust feature learning method for radio signals, a novel One-dimensional Deep Attention Convolution Network (ODACN) is proposed to automatically extract discriminative features and classify various kinds of signals. First, one-dimensional (1-D) sparse filters are designed to learn hierarchical features of raw signals. Second, an attention layer is constructed to weight and assemble feature maps, to derive more context-relevant representation. By using simple 1-D filtering, ODACN is characteristic of less parameters and lower computation complexity than traditional Convolutional Neural Networks (CNNs). Moreover, feature attention can mimic a succession of partial glimpses of humans and focus on context parts of signals, thus helps in recognizing signals even at low Signal-to-Noise Ratio (SNR). Some experiments are taken to classify 31 kinds of signals with different modulation and channel coding types, and the results show that ODACN can achieve accurate classification of very similar signals, without any prior knowledge and manual operation.https://ieeexplore.ieee.org/document/8926472/Signal classificationfeature learningone-dimensional convolution neural networkattention layer |
| spellingShingle | Shuyuan Yang Chen Yang Dongzhu Feng Xiaoyang Hao Min Wang One-Dimensional Deep Attention Convolution Network (ODACN) for Signals Classification IEEE Access Signal classification feature learning one-dimensional convolution neural network attention layer |
| title | One-Dimensional Deep Attention Convolution Network (ODACN) for Signals Classification |
| title_full | One-Dimensional Deep Attention Convolution Network (ODACN) for Signals Classification |
| title_fullStr | One-Dimensional Deep Attention Convolution Network (ODACN) for Signals Classification |
| title_full_unstemmed | One-Dimensional Deep Attention Convolution Network (ODACN) for Signals Classification |
| title_short | One-Dimensional Deep Attention Convolution Network (ODACN) for Signals Classification |
| title_sort | one dimensional deep attention convolution network odacn for signals classification |
| topic | Signal classification feature learning one-dimensional convolution neural network attention layer |
| url | https://ieeexplore.ieee.org/document/8926472/ |
| work_keys_str_mv | AT shuyuanyang onedimensionaldeepattentionconvolutionnetworkodacnforsignalsclassification AT chenyang onedimensionaldeepattentionconvolutionnetworkodacnforsignalsclassification AT dongzhufeng onedimensionaldeepattentionconvolutionnetworkodacnforsignalsclassification AT xiaoyanghao onedimensionaldeepattentionconvolutionnetworkodacnforsignalsclassification AT minwang onedimensionaldeepattentionconvolutionnetworkodacnforsignalsclassification |