arXiv 1907.073212019-07-15eess.SPcs.LGstat.ML

用于频谱感知的神经网络结构比较

Comparison of Neural Network Architectures for Spectrum Sensing

UC San Diego（加州大学圣地亚哥分校）；Massey University（梅西大学）；UESTC（电子科技大学）

Ziyu Ye, Andrew Gilman, Qihang Peng, Kelly Levick, Pamela Cosman, Larry Milstein

备注：: 6 pages, 4 figures

摘要：

不同的神经网络（NN）结构具有不同的优点。卷积神经网络（CNN）在计算机视觉领域取得了巨大的成功，而递归神经网络（RNN）在语音识别领域也得到了广泛的应用。目前还不知道哪种类型的神经网络结构是最适合的通信信号的分类。在这项工作中，我们比较了全连接NN（FC），CNN，RNN和双向RNN（BiRNN）在频谱感知任务中的行为。四个神经网络结构进行了比较，他们的检测性能，训练数据的要求，计算复杂度和内存需求。给定丰富的训练数据以及计算和内存资源，CNN，RNN和BiRNN显示出类似的性能。除了计算复杂度受到严格限制的情况外，FC的性能比其他三种类型的性能差。

英文摘要：

Different neural network (NN) architectures have different advantages. Convolutional neural networks (CNNs) achieved enormous success in computer vision, while recurrent neural networks (RNNs) gained popularity in speech recognition. It is not known which type of NN architecture is the best fit for classification of communication signals. In this work, we compare the behavior of fully-connected NN (FC), CNN, RNN, and bi-directional RNN (BiRNN) in a spectrum sensing task. The four NN architectures are compared on their detection performance, requirement of training data, computational complexity, and memory requirement. Given abundant training data and computational and memory resources, CNN, RNN, and BiRNN are shown to achieve similar performance. The performance of FC is worse than that of the other three types, except in the case where computational complexity is stringently limited.

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。

摘要：

英文摘要：

相关论文