• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Cloud Computing and Security >Chaos Prediction of Fast Fading Channel of Multi-rates Digital Modulation Using Support Vector Machines
【24h】

Chaos Prediction of Fast Fading Channel of Multi-rates Digital Modulation Using Support Vector Machines

机译：支持向量机的多速率数字调制快速衰落信道的混沌预测

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

According to the support vector domain properties, the paper establishes vector domain predictive models of chaos channel as well as chaos phase trace of non-linear map, the chaotic fading channel model was established based on Takens phase space delay reconstructing theory. Self-learning makes error least upper bound of generalization model to be minimum. The non-linear higher dimension map was realized by the squares support vector domain. The future fading channel data was predicted from training data set. The predictive error changes with the increase of embed dimension to a constant. The experiment result indicates that the support vector domain needs little support vector with fast convergence rate. With the small sample and unknown probability density, the multi-path predictive series consisted with true value series in Doppler fast fading channel. Under the conditions of small sample, the predicted series is in concordance with the channel true value.
机译：根据支持向量域的性质，建立了混沌信道的向量域预测模型以及非线性映射的混沌相位轨迹，基于Takens相空间时延重构理论建立了混沌衰落信道模型。自学习使误差最小化泛化模型的上限最小。非线性高维图是通过平方支持向量域实现的。从训练数据集中预测了未来的衰落信道数据。预测误差随嵌入尺寸的增加而变化为常数。实验结果表明，支持向量域几乎不需要支持向量，收敛速度快。由于样本量少且概率密度未知，因此多径快速衰落信道中的多径预测序列由真值序列组成。在小样本条件下，预测序列与信道真实值一致。

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