Contaminated Multiband Signal Identification Via Deep Learning
Contaminated Multiband Signal Identification Via Deep Learning
复制标题
DOI：
10.1109/ssp49050.2021.9513845
复制
发表时间：
2021-07
期刊：
影响因子：
--
通讯作者：
Youye Xie;M. Wakin;Gongguo Tang
中科院分区：
文献类型：
--
作者：
Youye Xie;M. Wakin;Gongguo Tang
多波段信号，其有效频率处于连续间隔内，在雷达成像等广泛应用中出现。在本文中，我们提出了一种新的深度网络来估计带的数量并定位带的中心，给出了受污染的多带信号的有限和变长时域样本。结合长短期记忆（LSTM）和卷积神经网络的多频带信号表示模型，将不同长度的观测样本映射到频谱表示中。然后，计数模型根据估计的频谱计算频带数。结合谱表示和估计频带数，可以有效、自动地恢复频带中心。数值实验表明，该方法是非常有效的，并且可以利用扩展样本获得更好的性能。此外，它在不同噪声水平下的线谱估计优于其他深度架构，并且比基于原子范数的方法快得多。
Multiband signals, whose active frequencies lie within continuous intervals, arise in a wide range of applications like radar imaging. In this paper, given limited and varying-length time-domain samples of a contaminated multiband signal, we propose novel deep networks to estimate the number of bands and locate the bands’ centers. A multiband signal representation model, which combines the long short-term memory (LSTM) and convolutional neural network, is trained to map varying-length observed samples to a frequency spectrum representation. A counting model then counts the number of bands based on the estimated spectrum. Combining the spectrum representation and estimated number of bands, the bands’ centers can be recovered efficiently and automatically. Numerical experiments demonstrate that the proposed method is very effective and can leverage extended samples for better performance. Moreover, it outperforms other deep architectures for line spectral estimation at different noise levels and is much faster than an atomic norm-based method.