可解释性
卷积神经网络
计算机科学
卷积(计算机科学)
一般化
可分离空间
人工智能
调制(音乐)
任务(项目管理)
模式识别(心理学)
特征提取
特征(语言学)
算法
人工神经网络
机器学习
工程类
数学
数学分析
哲学
系统工程
美学
语言学
作者
Chunyan Xiao,Shuyuan Yang,Zhixi Feng
出处
期刊:IEEE Transactions on Instrumentation and Measurement
[Institute of Electrical and Electronics Engineers]
日期:2023-01-01
卷期号:72: 1-10
被引量:2
标识
DOI:10.1109/tim.2023.3298657
摘要
Automatic Modulation Classification (AMC) is a critical task in industrial cognitive communication systems. Existing state-of-the-art methods, typified by real-valued convolutional neural networks, have introduced innovative solutions for AMC. However, such models viewed the two constituent components of complex-valued modulated signals as discrete real-valued inputs, causing structural phase damage to original signals and reduced interpretability of the model. In this article, a novel end-to-end AMC model called a complex-valued depth-wise separable convolutional neural network (CDSCNN) is proposed, which adopts complex-valued operation units to enable automatic complex-valued feature learning specifically tailored for AMC. Considering the limited hardware resources available in industrial scenarios, complex-valued depth-wise separable convolution (CDSC) is designed to strike a balance between classification accuracy and model complexity. With an overall accuracy of 62.63% on the RadioML2016.10a dataset, CDSCNN outperforms its counterparts by 1% to 11%. After fine-tuning on the RadioML2016.10b dataset, the overall accuracy reaches 63.15%, demonstrating the robust recognition and generalization capability of CDSCNN. Moreover, the CDSCNN exhibits lower model complexity compared to other methods.
科研通智能强力驱动
Strongly Powered by AbleSci AI