| 摘要: |
| 分析了一种面向智能物联的双路径机器学习调制模式识别方法.以元学习网络为基础，将模糊分类和精确分类相结合，在低信噪比环境下，能扩增识别信号类型，同时保持较高的识别精度，有效地降低了恶劣环境对信号带来的影响.用理论分析和仿真结果证明了该方法的有效性. |
| 关键词: 智能物联 自适应网络 元学习 双路径 |
| DOI：10.3969/J.ISSN.1000-5137.2022.02.012 |
| 分类号:TP311 |
| 基金项目:浦东新区科技发展基金产学研专项(PKX2020-D6) |
|
| A dual path machine learning modulation pattern recognition method for intelligent Internet of Things |
|
XIU Sirui, ZHOU Xiaolin, WANG Baorui, DU Gang
|
|
School of Information Science and Technology, Fudan University, Shanghai 200433, China
|
| Abstract: |
| In this paper a dual path machine learning modulation pattern recognition method was analyzed for intelligent Internet of Things. Based on meta-learning network and the combination of fuzzy classification and precise classification, the types of identification signals were increased, and high identification accuracy was maintained in the low signal-to-noise ratio environment at the same time which could effectively reduced the impacts of harsh environment to the signal. The theoretical analysis and simulation results demonstrated the effectiveness of the proposed method. |
| Key words: intelligent Internet of Things adaptive network meta-learning dual path |
