...
首页> 外文期刊>IEEE Transactions on Vehicular Technology >Neural-net-based receiver structures for single- and multiamplitudebandlimited signals in CCI and ACI channels
【24h】

Neural-net-based receiver structures for single- and multiamplitudebandlimited signals in CCI and ACI channels

机译:基于神经网络的接收器结构,用于CCI和ACI通道中的单幅和多幅带宽受限信号

获取原文
获取原文并翻译 | 示例
           

摘要

This paper presents analysis and performance-evaluation resultsnfor several neural-network-based nondecision-feedback receivernstructures, which improve the performance of bandlimited single- andnmultiamplitude signals transmitted over additive interference channels,nsuch as cochannel interference (CCI) and adjacent channel interferencen(ACI). In particular, we propose, analyze, and evaluate a trainingnalgorithm for Nyquist-filtered single- and multiamplitude signals, basednupon a novel nonuniform signal-sampling technique. We also introduce annovel nonlinear activation function for multiamplitude signals andnevaluate its performance via computer simulation and in conjunction withnvarious bandlimited signaling formats, detection techniques, andnneural-network structures. Bit-error rate (BER) performance-evaluationnresults of the proposed neural-network receivers for coherent andnnoncoherent detection of Nyquist- and Butterworth-filtered single- andnmultiamplitude signals have shown performance improvements in thenpresence of CCI and ACI
机译:本文介绍了几种基于神经网络的非决策反馈接收器结构的分析和性能评估结果,这些结构提高了通过加性干扰信道(如同信道干扰(CCI)和邻信道干扰n(ACI))传输的带限单频和多频信号的性能。 。特别地,我们基于一种新颖的非均匀信号采样技术,提出,分析和评估针对奈奎斯特滤波的单幅和多幅信号的训练算法。我们还介绍了用于多振幅信号的新颖的非线性激活函数,并通过计算机仿真以及各种带宽受限的信号格式,检测技术和神经网络结构来评估其性能。拟议的神经网络接收机对Nyquist和Butterworth滤波的单幅和多幅幅度信号进行相干和非相干检测的误码率(BER)性能评估结果表明,在存在CCI和ACI的情况下,性能得到了改善

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号