Wei Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Wei Sun has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
Haozheng Zhang
School of Information Science and Engineering, Yunnan University, Kunming, China
1 shared publicationJingjing Yang
School of Information Science and Engineering, Yunnan University, Kunming, China
1 shared publication- Ming Huang
School of Information Science and Engineering, Yunnan University, Kunming, China
1 shared publication
Latest Publications
- 14 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 25 (4) , 1206-1210
A Data Preprocessing Method for Automatic Modulation Classification Based on CNN
As a backbone of deep learning models, convolutional neural networks (CNNs) are widely used in the field of automatic modulation classification. Nevertheless, we speculate that the forms of signal samples make them inefficient for direct use as a CNN input. In this letter, a novel data preprocessing method is proposed to markedly improve CNN-based automatic modulation classification. The benchmark dataset used in this research is the well-known RadioML2016.10a dataset. The experimental results show that using the proposed method gains approximately 10% accuracy improvement in a simple CNN. Furthermore, according to the form of the preprocessed data, we designed a CNN with residual blocks to reach a maximum accuracy of 93.7% when the signal-to-noise ratio is 14 dB, which outperforms state-of-the-art automatic modulation classifiers.
- 14 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 25 (4) , 1206-1210
A Data Preprocessing Method for Automatic Modulation Classification Based on CNN
As a backbone of deep learning models, convolutional neural networks (CNNs) are widely used in the field of automatic modulation classification. Nevertheless, we speculate that the forms of signal samples make them inefficient for direct use as a CNN input. In this letter, a novel data preprocessing method is proposed to markedly improve CNN-based automatic modulation classification. The benchmark dataset used in this research is the well-known RadioML2016.10a dataset. The experimental results show that using the proposed method gains approximately 10% accuracy improvement in a simple CNN. Furthermore, according to the form of the preprocessed data, we designed a CNN with residual blocks to reach a maximum accuracy of 93.7% when the signal-to-noise ratio is 14 dB, which outperforms state-of-the-art automatic modulation classifiers.