• 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 >Spatiotemporal Radio Tomographic Imaging with Bayesian Compressive Sensing for RSS-Based Indoor Target Localization
【24h】

Spatiotemporal Radio Tomographic Imaging with Bayesian Compressive Sensing for RSS-Based Indoor Target Localization

机译：基于贝叶斯压缩感知的时空无线电层析成像，用于基于RSS的室内目标定位

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

摘要

Wireless sensor network based device-free localization (DFL) is now widely used in security and monitoring systems for indoor and outdoor areas. Multipath fading induced noises often degrade the performance of the DFL security system. To address this problem, the paper firstly presents a spatiotemporal radio tomographic imaging (RTI) approach for the enhancement of localization. Specifically, the task of RTI can be formulated into a sparse Bayesian learning problem. In addition, two robust sparse Byesian learning algorithms are developed to handle with the low signal-to-noise-ratio (SNR) with heterogeneous noise. The proposed spatiotemporal RTI approach performs much better than traditional RTI with lower average errors in our four diverse cluttered indoor scenes. The localization results also highlight advantages of applying proposed robust sparse Bayesian learning algorithms in addressing missing estimations and outlier errors, and finally improving indoor target DFL performance.
机译：基于无线传感器网络的无设备定位（DFL）现在已广泛用于室内和室外区域的安全和监视系统。多径衰落引起的噪声通常会降低DFL安全系统的性能。为了解决这个问题，本文首先提出了一种时空无线电层析成像（RTI）方法来增强定位。具体而言，RTI的任务可以表述为稀疏的贝叶斯学习问题。此外，还开发了两种鲁棒的稀疏Byesian学习算法来处理异构噪声低的信噪比（SNR）。在四个杂乱的室内场景中，建议的时空RTI方法的性能要比传统RTI好得多，且平均误差较低。定位结果还突出了在解决遗漏的估计和离群误差以及最终改善室内目标DFL性能方面应用所提出的鲁棒的稀疏贝叶斯学习算法的优势。

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