CAJ | 학술논문

针对现有射频指纹匹配定位算法存在训练开销过大、环境信号动态改变自适应能力较差以及系统扩展性不足等问题,该文提出了一个基于线性插值和射频指纹动态补偿的分布式定位算法.该算法利用同一信标发射无线信号局部物理空间的相关性,提出了射频指纹的线性插值方法,减少了训练数据的采集工作量.此外,为自适应环境无线信号的动态变化,该算法使用少量均匀部署在定位区域内的参考节点实时监测环境信号变化,对移动节点测量的RSSI进行动态补偿,从而提高定位精度.实验结果表明,所提定位算法不仅有效减少了指纹数据库的创建工作量,而且能够较好地自适应环境变化,具有较高的定位精度.
침대현유사빈지문필배정위산법존재훈련개소과대、배경신호동태개변자괄응능력교차이급계통확전성불족등문제,해문제출료일개기우선성삽치화사빈지문동태보상적분포식정위산법.해산법이용동일신표발사무선신호국부물리공간적상관성,제출료사빈지문적선성삽치방법,감소료훈련수거적채집공작량.차외,위자괄응배경무선신호적동태변화,해산법사용소량균균부서재정위구역내적삼고절점실시감측배경신호변화,대이동절점측량적RSSI진행동태보상,종이제고정위정도.실험결과표명,소제정위산법불부유효감소료지문수거고적창건공작량,이차능구교호지자괄응배경변화,구유교고적정위정도.
In order to reduce the training cost and improve the robustness to environmental change for the radio-fingerprinting-based positioning systems, this paper presents a distributed localization algorithm based on linear interpolation and dynamic fingerprinting correction. It utilizes the spatial correlation of measurements sampled at adjacent reference points to obtain new fingerprints by linear interpolation and deploys a few reference nodes to dynamically compensate mobile node's RSSI. Extensive experiments show that the proposed algorithm not only achieve high localization accuracy, but also save training time and is able to adapt to the environmental change.