期刊
IEEE TRANSACTIONS ON SIGNAL PROCESSING
卷 69, 期 -, 页码 2316-2329出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TSP.2021.3070186
关键词
Semantics; Task analysis; Feature extraction; Training; Modulation; Deep learning; Image reconstruction; Zero-shot learning; signal recognition; CNN; autoencoder; deep learning
资金
- National Key Research and Development Project [2017YFE0119300]
- NSFC [61731018, U1709219]
This paper proposes a ZSL framework called SR2CNN for signal recognition and reconstruction, addressing the issue of lacking training data for signal recognition tasks. By introducing appropriate losses and distance metrics, SR2CNN learns the representation of signal semantic feature space, enabling signal recognition even without training data.
Signal recognition is one of the significant and challenging tasks in the signal processing and communications field. It is often a common situation that there's no training data accessible for some signal classes to perform a recognition task. Hence, as widely-used in image processing field, zero-shot learning (ZSL) is also very important for signal recognition. Unfortunately, ZSL regarding this field has hardly been studied due to inexplicable signal semantics. This paper proposes a ZSL framework, signal recognition and reconstruction convolutional neural networks (SR2CNN), to address relevant problems in this situation. The key idea behind SR2CNN is to learn the representation of signal semantic feature space by introducing a proper combination of cross entropy loss, center loss and reconstruction loss, as well as adopting a suitable distance metric space such that semantic features have greater minimal inter-class distance than maximal intra-class distance. The proposed SR2CNN can discriminate signals even if no training data is available for some signal class. Moreover, SR2CNN can gradually improve itself in the aid of signal detection, because of constantly refined class center vectors in semantic feature space. These merits are all verified by extensive experiments with ablation studies.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据