Unidimensional ACGAN Applied to Link Establishment Behaviors Recognition of a Short-Wave Radio Station
It is difficult to obtain many labeled Link Establishment (LE) behavior signals sent by non-cooperative short-wave radio stations. We propose a novel unidimensional Auxiliary Classifier Generative Adversarial Network (ACGAN) to get more signals and then use unidimensional DenseNet to recognize LE be...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/15/4270 |
| _version_ | 1797560689753063424 |
|---|---|
| author | Zilong Wu Hong Chen Yingke Lei |
| author_facet | Zilong Wu Hong Chen Yingke Lei |
| author_sort | Zilong Wu |
| collection | DOAJ |
| description | It is difficult to obtain many labeled Link Establishment (LE) behavior signals sent by non-cooperative short-wave radio stations. We propose a novel unidimensional Auxiliary Classifier Generative Adversarial Network (ACGAN) to get more signals and then use unidimensional DenseNet to recognize LE behaviors. Firstly, a few real samples were randomly selected from many real signals as the training set of unidimensional ACGAN. Then, the new training set was formed by combining real samples with fake samples generated by the trained ACGAN. In addition, the unidimensional convolutional auto-coder was proposed to describe the reliability of these generated samples. Finally, different LE behaviors could be recognized without the communication protocol standard by using the new training set to train unidimensional DenseNet. Experimental results revealed that unidimensional ACGAN effectively augmented the training set, thus improving the performance of recognition algorithm. When the number of original training samples was 400, 700, 1000, or 1300, the recognition accuracy of unidimensional ACGAN+DenseNet was 1.92, 6.16, 4.63, and 3.06% higher, respectively, than that of unidimensional DenseNet. |
| first_indexed | 2024-03-10T18:04:11Z |
| format | Article |
| id | doaj.art-6408d88949e1493a8d91397d73b753d0 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T18:04:11Z |
| publishDate | 2020-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-6408d88949e1493a8d91397d73b753d02023-11-20T08:36:21ZengMDPI AGSensors1424-82202020-07-012015427010.3390/s20154270Unidimensional ACGAN Applied to Link Establishment Behaviors Recognition of a Short-Wave Radio StationZilong Wu0Hong Chen1Yingke Lei2College of Electronic Countermeasures, National University of Defense Technology, Hefei 230037, ChinaCollege of Electronic Countermeasures, National University of Defense Technology, Hefei 230037, ChinaCollege of Electronic Countermeasures, National University of Defense Technology, Hefei 230037, ChinaIt is difficult to obtain many labeled Link Establishment (LE) behavior signals sent by non-cooperative short-wave radio stations. We propose a novel unidimensional Auxiliary Classifier Generative Adversarial Network (ACGAN) to get more signals and then use unidimensional DenseNet to recognize LE behaviors. Firstly, a few real samples were randomly selected from many real signals as the training set of unidimensional ACGAN. Then, the new training set was formed by combining real samples with fake samples generated by the trained ACGAN. In addition, the unidimensional convolutional auto-coder was proposed to describe the reliability of these generated samples. Finally, different LE behaviors could be recognized without the communication protocol standard by using the new training set to train unidimensional DenseNet. Experimental results revealed that unidimensional ACGAN effectively augmented the training set, thus improving the performance of recognition algorithm. When the number of original training samples was 400, 700, 1000, or 1300, the recognition accuracy of unidimensional ACGAN+DenseNet was 1.92, 6.16, 4.63, and 3.06% higher, respectively, than that of unidimensional DenseNet.https://www.mdpi.com/1424-8220/20/15/4270unidimensional ACGANsignal recognitiondata augmentationlink establishment behaviorsDenseNetshort-wave radio station |
| spellingShingle | Zilong Wu Hong Chen Yingke Lei Unidimensional ACGAN Applied to Link Establishment Behaviors Recognition of a Short-Wave Radio Station Sensors unidimensional ACGAN signal recognition data augmentation link establishment behaviors DenseNet short-wave radio station |
| title | Unidimensional ACGAN Applied to Link Establishment Behaviors Recognition of a Short-Wave Radio Station |
| title_full | Unidimensional ACGAN Applied to Link Establishment Behaviors Recognition of a Short-Wave Radio Station |
| title_fullStr | Unidimensional ACGAN Applied to Link Establishment Behaviors Recognition of a Short-Wave Radio Station |
| title_full_unstemmed | Unidimensional ACGAN Applied to Link Establishment Behaviors Recognition of a Short-Wave Radio Station |
| title_short | Unidimensional ACGAN Applied to Link Establishment Behaviors Recognition of a Short-Wave Radio Station |
| title_sort | unidimensional acgan applied to link establishment behaviors recognition of a short wave radio station |
| topic | unidimensional ACGAN signal recognition data augmentation link establishment behaviors DenseNet short-wave radio station |
| url | https://www.mdpi.com/1424-8220/20/15/4270 |
| work_keys_str_mv | AT zilongwu unidimensionalacganappliedtolinkestablishmentbehaviorsrecognitionofashortwaveradiostation AT hongchen unidimensionalacganappliedtolinkestablishmentbehaviorsrecognitionofashortwaveradiostation AT yingkelei unidimensionalacganappliedtolinkestablishmentbehaviorsrecognitionofashortwaveradiostation |