AMSCN: A Novel Dual-Task Model for Automatic Modulation Classification and Specific Emitter Identification
Specific emitter identification (SEI) and automatic modulation classification (AMC) are generally two separate tasks in the field of radio monitoring. Both tasks have similarities in terms of their application scenarios, signal modeling, feature engineering, and classifier design. It is feasible and...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/5/2476 |
| _version_ | 1797614396135964672 |
|---|---|
| author | Shanchuan Ying Sai Huang Shuo Chang Jiashuo He Zhiyong Feng |
| author_facet | Shanchuan Ying Sai Huang Shuo Chang Jiashuo He Zhiyong Feng |
| author_sort | Shanchuan Ying |
| collection | DOAJ |
| description | Specific emitter identification (SEI) and automatic modulation classification (AMC) are generally two separate tasks in the field of radio monitoring. Both tasks have similarities in terms of their application scenarios, signal modeling, feature engineering, and classifier design. It is feasible and promising to integrate these two tasks, with the benefit of reducing the overall computational complexity and improving the classification accuracy of each task. In this paper, we propose a dual-task neural network named AMSCN that simultaneously classifies the modulation and the transmitter of the received signal. In the AMSCN, we first use a combination of DenseNet and Transformer as the backbone network to extract the distinguishable features; then, we design a mask-based dual-head classifier (MDHC) to reinforce the joint learning of the two tasks. To train the AMSCN, a multitask cross-entropy loss is proposed, which is the sum of the cross-entropy loss of the AMC and the cross-entropy loss of the SEI. Experimental results show that our method achieves performance gains for the SEI task with the aid of additional information from the AMC task. Compared with the traditional single-task model, our classification accuracy of the AMC is generally consistent with the state-of-the-art performance, while the classification accuracy of the SEI is improved from 52.2% to 54.7%, which demonstrates the effectiveness of the AMSCN. |
| first_indexed | 2024-03-11T07:11:51Z |
| format | Article |
| id | doaj.art-bd7d1697a4e5484c9edeb24615ad42a6 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T07:11:51Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-bd7d1697a4e5484c9edeb24615ad42a62023-11-17T08:35:19ZengMDPI AGSensors1424-82202023-02-01235247610.3390/s23052476AMSCN: A Novel Dual-Task Model for Automatic Modulation Classification and Specific Emitter IdentificationShanchuan Ying0Sai Huang1Shuo Chang2Jiashuo He3Zhiyong Feng4Key Laboratory of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaKey Laboratory of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaKey Laboratory of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaKey Laboratory of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaKey Laboratory of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSpecific emitter identification (SEI) and automatic modulation classification (AMC) are generally two separate tasks in the field of radio monitoring. Both tasks have similarities in terms of their application scenarios, signal modeling, feature engineering, and classifier design. It is feasible and promising to integrate these two tasks, with the benefit of reducing the overall computational complexity and improving the classification accuracy of each task. In this paper, we propose a dual-task neural network named AMSCN that simultaneously classifies the modulation and the transmitter of the received signal. In the AMSCN, we first use a combination of DenseNet and Transformer as the backbone network to extract the distinguishable features; then, we design a mask-based dual-head classifier (MDHC) to reinforce the joint learning of the two tasks. To train the AMSCN, a multitask cross-entropy loss is proposed, which is the sum of the cross-entropy loss of the AMC and the cross-entropy loss of the SEI. Experimental results show that our method achieves performance gains for the SEI task with the aid of additional information from the AMC task. Compared with the traditional single-task model, our classification accuracy of the AMC is generally consistent with the state-of-the-art performance, while the classification accuracy of the SEI is improved from 52.2% to 54.7%, which demonstrates the effectiveness of the AMSCN.https://www.mdpi.com/1424-8220/23/5/2476specific emitter identification (SEI)automatic modulation classification (AMC)deep learningmultitask learning |
| spellingShingle | Shanchuan Ying Sai Huang Shuo Chang Jiashuo He Zhiyong Feng AMSCN: A Novel Dual-Task Model for Automatic Modulation Classification and Specific Emitter Identification Sensors specific emitter identification (SEI) automatic modulation classification (AMC) deep learning multitask learning |
| title | AMSCN: A Novel Dual-Task Model for Automatic Modulation Classification and Specific Emitter Identification |
| title_full | AMSCN: A Novel Dual-Task Model for Automatic Modulation Classification and Specific Emitter Identification |
| title_fullStr | AMSCN: A Novel Dual-Task Model for Automatic Modulation Classification and Specific Emitter Identification |
| title_full_unstemmed | AMSCN: A Novel Dual-Task Model for Automatic Modulation Classification and Specific Emitter Identification |
| title_short | AMSCN: A Novel Dual-Task Model for Automatic Modulation Classification and Specific Emitter Identification |
| title_sort | amscn a novel dual task model for automatic modulation classification and specific emitter identification |
| topic | specific emitter identification (SEI) automatic modulation classification (AMC) deep learning multitask learning |
| url | https://www.mdpi.com/1424-8220/23/5/2476 |
| work_keys_str_mv | AT shanchuanying amscnanoveldualtaskmodelforautomaticmodulationclassificationandspecificemitteridentification AT saihuang amscnanoveldualtaskmodelforautomaticmodulationclassificationandspecificemitteridentification AT shuochang amscnanoveldualtaskmodelforautomaticmodulationclassificationandspecificemitteridentification AT jiashuohe amscnanoveldualtaskmodelforautomaticmodulationclassificationandspecificemitteridentification AT zhiyongfeng amscnanoveldualtaskmodelforautomaticmodulationclassificationandspecificemitteridentification |