...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>WSEAS Transactions on Signal Processing >Performance evaluation of MLP based detectors in Gaussian Clutter using Importance Sampling Techniques
【24h】

Performance evaluation of MLP based detectors in Gaussian Clutter using Importance Sampling Techniques

机译：基于重要性采样技术的高斯杂波中基于MLP的检测器性能评估

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

A neural network based coherent detector is proposed for detecting gaussian targets in gaussian clutter. Target and clutter ACF are supposed gaussian with different powers and one lag correlation coefficients. The influence of target mean Doppler frequency is also considered. The neural detector performance is compared to the Neyman-Pearson one. For evaluating it, Montecarlo Simulation and Importance Sampling Techniques are used. An exhaustive study of the importance sampling parameter is made in order to obtain the minimum value of probability of false alarm for a given relative error and a number of patterns. Results show that a low complexity neural network can implement very good approximations of the Neyamn-Pearson detector. In the presented cases, the MLP performance tends to decrease when the TSIR (Training Signal to Interference Ratio) decreases to very low values, but it is more robust when the correlation characteristics of target and clutter are varied.
机译：提出了一种基于神经网络的相干检测器来检测高斯杂波中的高斯目标。目标ACF和杂波ACF被认为是具有不同功效和一个滞后相关系数的高斯。还应考虑目标平均多普勒频率的影响。将神经检测器的性能与Neyman-Pearson的性能进行了比较。为了对其进行评估，使用了蒙特卡洛模拟和重要性采样技术。为了获得给定的相对误差和许多模式的虚警概率的最小值，对重要性采样参数进行了详尽的研究。结果表明，低复杂度的神经网络可以很好地逼近Neyamn-Pearson检测器。在提出的情况下，当TSIR（训练信噪比）降低到非常低的值时，MLP性能趋于降低，但是当目标和杂波的相关特性发生变化时，MLP性能会更强健。

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