一种双信标机制下的指纹库构建方法

doi:10.19665/j.issn1001-2400.2022.03.0013

西安电子科技大学学报 ›› 2022, Vol. 49 ›› Issue (3): 111-119.doi: 10.19665/j.issn1001-2400.2022.03.0013

一种双信标机制下的指纹库构建方法

秦宁宁^1,²(),吴忆松¹(),孙顺远¹()

1.江南大学轻工过程先进控制教育部重点实验室,江苏无锡 214122
2.南京航空航天大学电磁频谱空间认知动态系统工信部重点实验室,江苏南京 211106

收稿日期:2021-01-31 修回日期:2021-12-16 出版日期:2022-06-20 发布日期:2022-07-04
通讯作者: 孙顺远
作者简介:秦宁宁(1980—),女,教授,博士, E-mail: ningning801108@163.com|吴忆松(1995—),男,江南大学硕士研究生,E-mail: wuyisong0919@163.com
基金资助:
国家自然科学基金(61702228);国家自然科学基金(61803183);江苏省自然基金(BK20170198);江苏省自然基金(BK20180591);电磁频谱空间认知动态系统工信部重点实验室开放研究基金(KF20202104)

Algorithm for fingerprint database construction under the dual beacon mechanism

QIN Ningning^1,²(),WU Yisong¹(),SUN Shunyuan¹()

1. Key Laboratory of Advanced Process Control for Light Industry of Ministry of Education,Jiangnan University,Wuxi 214122,China
2. Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space,Ministry of Industry and Information Technology,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,China

Received:2021-01-31 Revised:2021-12-16 Online:2022-06-20 Published:2022-07-04
Contact: Shunyuan SUN

摘要/Abstract

摘要：

针对室内定位研究中指纹库构建需要耗费大量人力及时间进行信号采集的问题,提出了一种基于双信标机制和径向基神经网络的指纹库扩展算法。基于双信标机制和径向基神经网络的指纹库扩展算法能够根据场景需求灵活调整信标点采样比例,兼顾随机性与均匀性的基础上,调控各维度抽样区间内均能获取一个样本值,在保证预测准确度的前提下,取得最低采样开销;采用径向基神经网络挖掘信标点位置与信号之间的深层联系,以场景特征扩充小尺度指纹库,预测待估计位置信号强度,达到扩张指纹库的目的。通过主次信标的协同,选择具备平衡指纹精度和扩张效率的最优信标点,减少采样信标数量的同时,确保定位精度。经实测场景测试,在保障预测准确率的前提下,基于双信标机制和径向基神经网络的指纹库扩展算法受益于消除信标集合的偶然性的能力,能将指纹库扩展至140%,在差值误差控制在3.1%左右的情况下,平均预测误差较现有算法降低12%以上。

关键词: 室内定位, 指纹定位, 指纹库构建, 双信标

Abstract:

Considering the problem that the construction of fingerprint database in indoor positioning research requires a lot of manpower and time for signal acquisition,this paper proposes an algorithm for fingerprint database expansion based on the dual beacon mechanism and radial basis neural network.This algorithm can flexibly adjust the sampling ratio of beacon points according to the needs of the scene,and obtain the lowest sampling overhead under the premise of ensuring the accuracy of prediction.The algorithm uses the radial basis neural network to mine the deep connection between the position of the beacon and the signal to predict the signal strength of the position to be estimated,and achieve the purpose of expanding the fingerprint database.Tested by the actual scene,on the premise of ensuring the accuracy of prediction,the proposed algorithm expands the fingerprint database by 140%.Through experimental verification,the average prediction error is reduced by more than 12% compared with the existing algorithms.

Key words: indoor positioning, fingerprint positioning, fingerprint database construction, dual beacon

中图分类号:

TN96

秦宁宁,吴忆松,孙顺远. 一种双信标机制下的指纹库构建方法[J]. 西安电子科技大学学报, 2022, 49(3): 111-119.

QIN Ningning,WU Yisong,SUN Shunyuan. Algorithm for fingerprint database construction under the dual beacon mechanism[J]. Journal of Xidian University, 2022, 49(3): 111-119.

图/表 11

图1

图2

图3

图4

表1

图5

图6

图7

图8

图9

图10

参考文献 15

[1]	GUO R, QIN D, ZHAO M, et al. Indoor Radio Map Construction Based on Position Adjustment and Equipment Calibration[J]. Sensors, 2020, 20(10):2818. doi: 10.3390/s20102818
[2]	NI Y, CHAI J, WANG Y, et al. A Fast Radio Map Construction Method Merging Self-Adaptive Local Linear Embedding (LLE) and Graph-Based Label Propagation in WLAN Fingerprint Localization Systems[J]. Sensors, 2020, 20(3):767. doi: 10.3390/s20030767
[3]	ZHOU B, LI Q, MAO Q, et al. A Robust Crowdsourcing-Based Indoor Localization System[J]. Sensors, 2017, 17(4):864-880. doi: 10.3390/s17040864
[4]	李世宝, 王升志, 刘建航, 等. 基于接收信号强度非齐性分布特征的半监督学习室内定位指纹库构建[J]. 电子与信息学报, 2019, 41(10):2302-2309.
	LI Shibao, WANG Shengzhi, LIU Jianhang, et al. Semi-Supervised Indoor Fingerprint Database Construction Method Based on the Nonhomogeneous Distribution Characteristic of Received Signal Strength[J]. Journal of Electronics & Information Technology, 2019, 41(10):2302-2309.
[5]	刘志建, 关维国, 华海亮, 等. 基于克里金空间插值的位置指纹数据库建立算法[J]. 计算机应用研究, 2016, 33(10):3139-3142.
	LIU Zhijian, GUAN Weiguo, HUA Hailiang, et al. LocationFingerprint Database Construction Algorithm Based on Kriging Spatial Interpolation[J]. Application Research of Computers, 2016, 33(10):3139-3142.
[6]	杨刚, 柴雅文. 基于矩阵填充和压缩感知的蓝牙室内定位方法[J]. 光通信研究, 2019, 5:58-63.
	YANG Gang, CHAI Yawen. Bluetooth Indoor Location Method Based on Matrix Completion and Compressed Sensing[J]. Study on Optical Communications, 2019, 5:58-63.
[7]	OKTAVIA E, WIDYAWAN, MUSTIKA I. Inverse Distance Weighting and Kriging Spatial Interpolation for Datacenter Thermal Monitoring[C]// Proceedings of 2016 1st International Conference on Information Technology,Information Systems and Electrical Engineering.Piscataway:IEEE, 2016:69-74.
[8]	乐燕芬, 张贺娜, 施伟斌. 基于泛克里金插值的 WSN 位置指纹预处理[J]. 传感技术学报, 2019, 32(12):1889-1894.
	LE Yanfen, ZHANG Hena, SHI Weibin. Pre-Processing of Fingerprints Based on Universal Kriging Interpolation for WSN Positioning Systems[J]. Chinese Journal of Sensors and Actuators, 2019, 32(12):1889-1894.
[9]	ISMAIL A H, MIZUSHI R, TASAKI R, et al. A Novel Automated Construction Method of Signal Fingerprint Database for Mobile Robot Wireless Positioning System[J]. International Journal of Automation Technology, 2017, 11(3):459-471. doi: 10.20965/ijat.2017.p0459
[10]	李文浩, 李丽娜, 徐攀峰, 等. 基于矩阵填充的室内定位位置指纹库构建[J]. 辽宁大学学报(自然科学版), 2015, 42(4):325-329.
	LI Wenhao, LI Lina, XU Panfeng, et al. Construction of Indoor Location Fingerprint Database Based on Matrix Completion[J]. Journal of Liaoning University(Natrual Sciences Edition), 2015, 42(4):325-329.
[11]	NIKITAKI S, TSAGKATAKIS G, TSAKALIDES P. Efficient Training for Fingerprint Based Positioning Using Matrix Completion[C]/ / Proceedings of the 20th European Signal Processing Conference (EUSIPCO).Piscataway:IEEE, 2012:195-199.
[12]	张兴国, 刘晓磊, 李靖, 等. BP神经网络下的限速交通标志实时检测识别[J]. 西安电子科技大学学报, 2018, 45(5):136-142.
	ZHANG Xingguo, LIU Xiaolei, LI Jing, et al. Real-Time Detection and Identification of Speed Limit Traffic Signs under the BP Neural Network[J]. Journal of Xidian University, 2018, 45(5):136-142.
[13]	贾丽杰, 李文静, 乔俊飞. 基于神经元特性的径向基函数神经网络自组织设计方法[J]. 控制理论与应用, 2020, 37(12):2618-2626.
	JIA Lijie, LI Wenjing, QIAO Junfei. Self-Orgnizing Design of Radial Basis Function Neural Network Based on Neuron Characteristics[J]. Control Theory & Application, 2020, 37(12):2618-2626.
[14]	余修武, 余昊, 刘永, 等. 基于加权混合滤波和重心法的APIT定位算法[J]. 北京邮电大学学报, 2019, 42(4):32-37. doi: 10.13190/j.jbupt.2018-313
	YU Xiuwu, YU Hao, LIU Yong, et al. APIT Location Algorithm Based on Weighted Hybrid Filtering and Center of Gravity Method[J]. Journal of Beijing University of Posts and Telecommunications, 2019, 42(4):32-37. doi: 10.13190/j.jbupt.2018-313
[15]	刘夏, 莫树培. 改进克里金插值算法的井下无线定位指纹库构建方法[J]. 传感技术学报, 2019, 32(7):1100-1106.
	LIU Xia, MO Shupei. Construction of Underground Wireless Position Fingerprint Database Based on Improved Kriging Interpolation Algorithms[J]. Chinese Journal of Sensors and Actuators, 2019, 32(7):1100-1106.

抽样方法	/m	e_min/m	e_max/m	方差
LHS	1.76	1.60	1.98	8.5×10³
随机抽样	2.10	1.65	3.21	26.7×10³

一种双信标机制下的指纹库构建方法

Algorithm for fingerprint database construction under the dual beacon mechanism

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 15

相关文章 8

Metrics

本文评价

推荐阅读 10

[1]	孙顺远,朱红洲,秦宁宁. 一种动态校正的信号双尺度近邻定位方法[J]. 西安电子科技大学学报, 2022, 49(3): 93-100.
[2]	秦宁宁,吴忆松,杨乐. 动态模糊匹配下的多元相似度定位算法[J]. 西安电子科技大学学报, 2021, 48(4): 27-35.
[3]	秦宁宁,王超. 时序测量信息触发的递归贝叶斯定位算法[J]. 西安电子科技大学学报, 2020, 47(4): 10-17.
[4]	王博远,刘学林,蔚保国,贾瑞才,甘兴利,黄璐. WiFi指纹定位中改进的加权k近邻算法[J]. 西安电子科技大学学报, 2019, 46(5): 41-47.
[5]	鲁航;崔维嘉;巴斌;逯志宇. 多观测值约束的可见光定位算法[J]. 西安电子科技大学学报, 2017, 44(4): 156-161.
[6]	贺磊南;卢虎;姬正洲. WiFi/PDR室内分层三维定位技术[J]. 西安电子科技大学学报, 2017, 44(4): 167-173+166.
[7]	赵响;林基明. 室内可见光成像传感器定位系统的理论极限[J]. 西安电子科技大学学报, 2016, 43(4): 63-68.
[8]	王跃;巴斌;崔维嘉;逯志宇. 马尔可夫蒙特卡罗的室内定位算法[J]. 西安电子科技大学学报, 2016, 43(2): 145-149.