arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.13273cs.ITcs.LGeess.SPmath.IT
收藏

用于源数检测的模型辅助深度神经网络

Model-aided Deep Neural Network for Source Number Detection

Tsinghua University(清华大学);University of Virginia(弗吉尼亚大学);Xidian University(西安电子科技大学)

Yuwen Yang, Feifei Gao, Cheng Qian, Guisheng Liao

摘要:

信源个数检测是阵列信号处理中的一个关键问题。传统的模型驱动方法,例如,Akaikes信息准则(AIC)和最小描述长度(MDL)在快拍数较少或信噪比较低时,性能会严重下降。在本文中,我们利用基于模型辅助的深度神经网络(DNN)来估计源数量。具体地说,我们首先提出了基于特征值的回归网络(ERNet)和分类网络(ECNet)来估计非相干源的数量,其中接收信号协方差矩阵的特征值和源数量分别作为网络的输入和监督标签。然后,我们扩展的ERNet和ECNet的相干源的数量估计,其中的前向-后向空间平滑(FBSS)计划,以提高ERNet和ECNet的性能。数值实验结果表明,ERNet和ECNet算法优于传统的AIC和MDL算法,具有良好的泛化能力,具有很大的实际应用潜力。

英文摘要:

Source number detection is a critical problem in array signal processing. Conventional model-driven methods e.g., Akaikes information criterion (AIC) and minimum description length (MDL), suffer from severe performance degradation when the number of snapshots is small or the signal-to-noise ratio (SNR) is low. In this paper, we exploit the model-aided based deep neural network (DNN) to estimate the source number. Specifically, we first propose the eigenvalue based regression network (ERNet) and classification network (ECNet) to estimate the number of non-coherent sources, where the eigenvalues of the received signal covariance matrix and the source number are used as the input and the supervise label of the networks, respectively. Then, we extend the ERNet and ECNet for estimating the number of coherent sources, where the forward-backward spatial smoothing (FBSS) scheme is adopted to improve the performance of ERNet and ECNet. Numerical results demonstrate the outstanding performance of ERNet and ECNet over the conventional AIC and MDL methods as well as their excellent generalization capability, which also shows their great potentials for practical applications.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑