Neural Network Detectors for Molecular Communication Systems
Neural Network Detectors for Molecular Communication Systems
复制标题
用于分子通信系统的神经网络探测器
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
A. Goldsmith
中科院分区：
文献类型：
--
作者：
N. Farsad;A. Goldsmith
我们考虑了分子通信系统，并表明可以在不了解底层通道模型的情况下训练探测器。特别是，我们证明了我们之前开发的一种称为滑动双向循环神经网络（SBRNN）的技术，当使用包含各种通道条件下的许多样本传输的数据集进行训练时，它在各种通道状态下都表现良好。我们还证明了所提出的 SBRNN 检测器的误码率 (BER) 性能优于具有不完善信道状态信息 (CSI) 的维特比检测器 (VD)，并且计算效率高。
We consider molecular communication systems and show it is possible to train detectors without any knowledge of the underlying channel models. In particular, we demonstrate that a technique we previously developed, which is called sliding bidirectional recurrent neural network (SBRNN), performs well for a wide range of channel states when it is trained using a dataset that contains many sample transmissions under various channel conditions. We also demonstrate that the bit error rate (BER) performance of the proposed SBRNN detector is better than that of a Viterbi detector (VD) with imperfect channel state information (CSI) and it is computationally efficient.