Analysis on dendritic deep learning model for AMR task
Abstract This study introduces a novel hybrid deep learning model featuring a dendritic layer for enhancing the performance of automatic modulation recognition (AMR). By replacing the fully connected layer, the proposed model demonstrates superior classification accuracy in AMR tasks. Comparative experiments with nine state-of-the-art deep learning models on the RadioML2016.10a dataset reveal its consistent superiority. Statistical analyses, including the Friedman test and Wilcoxon signed-rank test, confirm the significant advantage of the HDM-D model.
Authors
- Yang Yu (ORCID: https://orcid.org/0000-0002-4724-9933)
- Zhuangzhi Chen (ORCID: https://orcid.org/0000-0002-8736-8814)
- Peng Yin (ORCID: https://orcid.org/0000-0003-2407-4074)
- Ziqian Wang (ORCID: https://orcid.org/0000-0001-6675-6407)
- Shahong Zhu (ORCID: https://orcid.org/0000-0002-1640-8401)
Institutions
- Nanjing University of Posts and Telecommunications (CN)
- University of Chinese Academy of Sciences (CN)
- Zhejiang University of Technology (CN)
- National Defence University (PK)
Publication Details
- Journal
- Cybersecurity
- Published
- 2024-12-19
- DOI
- https://doi.org/10.1186/s42400-024-00306-9
- Citations
- 2
- Primary Topic
- Wireless Signal Modulation Classification
- Type
- article
- Field-Weighted Citation Impact
- 0.69
Funders
- National Natural Science Foundation of China