基于信息区分度的AP有效集构建方法  

An Approach for Generating Effective AP Set Based on Information Discrimination

作　　者：严维轩 朱立才 季衍辉 李永 杨浩 YAN Weixuan;ZHU Licai;JI Yanhui;LI Yong;YANG Hao(College of Computer and Info.Eng.,Nanjing Technol.Univ.,Nanjing 211816,China;School of Info.Eng.,Yancheng Teachers Univ.,Yancheng 224001,China;Suzhou Inst.of Higher Education,Univ.of Sci.and Technol.of China,Suzhou 215123,China)

机构地区：[1]南京工业大学计算机科学与技术学院,江苏南京211816 [2]盐城师范学院信息工程学院,江苏盐城224001 [3]中国科学技术大学苏州高等研究院,江苏苏州215123

出　　处：《工程科学与技术》2024年第1期110-116,共7页Advanced Engineering Sciences

基　　金：国家自然科学基金项目(61772448);江苏省高等学校基础科学(自然科学)研究重大项目(23KJA520014);中国博士后基金项目(2019M660132);江苏省博士后科研资助计划项目(2019K123);盐城市重点研发计划(社会发展)(YCBE202310);盐城工业职业技术学院开放基金课题(YGKF202204);网络与数据安全四川省重点实验室开放课题资助项目(NDS2023-2)。

摘　　要：随着无线网络的广泛应用,面向接受信号强度(RSS)指纹定位的接入点(AP)日益增多,导致一些AP的作用是冗余的,甚至对定位产生不利影响,同时也增加了定位计算的开销。通过对AP进行适当筛选可以一定程度上去除冗余AP,但定位效果会随着AP数量发生较大变化,甚至会增大误差。本文提出一种基于信息区分度的AP有效集构建方法(EID),充分利用指纹信号在不同空间的差异,实现了准确的位置估计。首先,用信息区分度评估AP的定位能力,有效反映出每个AP在不同采样点的区别,展示AP对空间位置的分辨程度。然后,基于AP信息区分度设计更加符合现实环境的增量聚类算法,能根据AP的定位能力得到不同类别的集合并具有较好的鲁棒性。最后,利用点集距离最大原则提出AP有效集选择策略,根据聚类结果和选择要求,选择出合适的AP集合。本文在真实场景下进行实验验证,并与现有的AP选择方法,即基于组判别(GDB)算法、基于软件定义网络(SDN)算法和基于非均匀量化RSS熵(NQRE)算法对比,在减少不低于40%AP数量的情形下,EID将定位精度分别提升了18.7%、11.2%和14.6%。与此同时,本文方法具有更好的稳定性,在95%的情形下定位误差低于1.2 m。The widespread adoption of wireless networks has led to a significant increase in the deployment of Access Points(APs)for Received Signal Strength(RSS)fingerprint localization.This surge has introduced redundancy,negatively impacting localization and increasing computational costs.While traditional AP filtering mitigates redundancy to some extent,an Effective Access Point Set Construction method(EID)based on information distinctiveness was proposed in this paper.Firstly,EID was utilized to evaluate APs by assessing their spatial resolution through information distinctiveness.Moreover,an incremental clustering algorithm was designed,which was able to form sets of different categories according to localization abilities of APs.Finally,an AP effective set selection strategy based on the maximum point set distance principle was proposed in the paper,resulting in suitable AP sets.Extensive experiments validated the performance of the proposed EID in real-world scenarios.EID was also compared with existing AP selection methods including the Group Discrimination-Based(GDB)algorithm,Software Defined Network(SDN)algorithm,and Nonuniform Quantization RSSI Entropy(NQRE)algorithm.Experimental results showed that EID demonstrates a significant improvement in localization accuracy by 18.7%,11.2%,and 14.6%with enhanced stability,achieving a localization error below 1.2 m in 95%of cases,even with a 40%reduction in AP quantity.

关 键 词：AP选择 信息区分度 有效集 室内定位 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]