• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>International journal of RF and microwave computer-aided engineering >Outdoor positioning based on deep learning and wireless network fingerprint technology
【24h】

Outdoor positioning based on deep learning and wireless network fingerprint technology

机译：基于深度学习和无线网络指纹技术的户外定位

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

Localization has attracted considerable attention in recent years because of thegrowth in location-based services and computer-aided technology. In particular,wireless fingerprint-based positioning techniques have received considerableattention due to their satisfactory positioning performance withsmartphones. In this work, a two-level hierarchical structure positioning systemis proposed to achieve satisfactory positioning accuracy. First, long-timeevolution(LTE) mobile networks are used to provide positioning information,and the collected measurements of LTE signals are converted into grayscalefingerprint images to construct the fingerprint database. To overcome theinstability of LTE signals, several data enhancement methods are leveraged toincrease the diversity of the fingerprint database. Second, a modified deepresidual network (MResNet) coarse localizer is used to learn reliable featuresfrom the fingerprint image database. Then, inspired by the ideas of featurefusion and transfer learning, a multilayer perceptron (MLP)-based finelocalizer is used to further learn the features of the fingerprint images andachieve a better positioning performance. Our experimental results convincinglyreveal that the proposed positioning system can achieve satisfactory positioningperformance in a variety of outdoor environments.
机译：近年来，本地化引起了相当大的关注基于位置的服务和计算机辅助技术的增长。特别是，基于无线指纹的定位技术已接受相当大的由于他们满意的定位性能而引起的注意力智能手机。在这项工作中，两级层次结构定位系统建议实现令人满意的定位精度。首先，长时间（LTE）移动网络用于提供定位信息，并且LTE信号的收集测量被转换为灰度指纹图像构建指纹数据库。克服这一点LTE信号的不稳定性，若干数据增强方法可以利用增加指纹数据库的多样性。二，深入修改剩余网络（MRESNet）粗定型器用于学习可靠的功能从指纹图像数据库。然后，受到特色的启发融合和转移学习，一个多层的感知者（MLP） - 基于罚款Localizer用于进一步了解指纹图像的特征和实现更好的定位性能。我们的实验结果非常令人信服揭示所提出的定位系统可以实现令人满意的定位各种户外环境中的性能。

著录项

  • 来源
  • 作者

    Da Li; Yingke Lei; Haichuan Zhang; Xin Li;

  • 作者单位

    Science and Technology on Communication Information Security Control Laboratory Jiaxing China College of Electronic Engineering National University of Defense Technology Hefei China;

    Science and Technology on Communication Information Security Control Laboratory Jiaxing China College of Electronic Engineering National University of Defense Technology Hefei China;

    Science and Technology on Communication Information Security Control Laboratory Jiaxing China;

    Science and Technology on Communication Information Security Control Laboratory Jiaxing China;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    deep learning; fingerprint positioning; MResNet; transfer learning; wireless networks;

    机译：深度学习;指纹定位;MRESNET;转移学习;无线网络;

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