计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (6A): 240900124-7.doi: 10.11896/jsjkx.240900124

• 网络&通信 • 上一篇    下一篇

基于改进随机森林算法的RFID室内定位方法

蒋蔚1, 郭成波1, 寇家华1, 张若宛1, 郭艳玲2   

  1. 1 东北林业大学土木与交通学院 哈尔滨 150040
    2 东北林业大学机电工程学院 哈尔滨 150040
  • 出版日期:2025-06-16 发布日期:2025-06-12
  • 通讯作者: 郭成波(chengbo.guo@nefu.edu.cn)
  • 作者简介:(2023122232@nefu.edu.cn)
  • 基金资助:
    国家自然科学基金(52075090)

RFID Indoor Positioning Method Based on Improved Random Forest Algorithm

JIANG Wei1, GUO Chengbo1, KOU Jiahua1, ZHANG Ruowan1, GUO Yanling2   

  1. 1 College of Civil Engineering & Transportation,Northeast Forestry University,Harbin 150040,China
    2 College of Mechanical and Electrical Engineering,Northeast Forestry University,Harbin 150040,China
  • Online:2025-06-16 Published:2025-06-12
  • About author:JIANG Wei,born in 1999,postgra-duate. Her main research interests include radio frequencyidentification and indoor positioning system.
    GUO Chengbo,born in 1987,Ph.D,lecturer. His main research interests include Internet of Things technology and intelligent logistics equipment.
  • Supported by:
    National Natural Science Foundation of China(52075090).

PDF (PC)

42

摘要： 为解决现有射频识别技术在物流仓储型高精度定位需求领域应用率低且定位精度差的问题,提出了一种基于改进随机森林模型的射频识别技术定位方法。首先,搭建了多天线同时读取参考标签接收信号强度的环境,并在读取过程中采用迭代平均值过滤算法采集接收信号强度数值,采用滑动窗口从已有的接收信号强度数值中推导出新的属性,扩大机器学习的数据集。其次,引入随机森林分类模型,构建以接收信号强度及其新属性为输入,以X轴和Y轴坐标为输出的随机森林模型基础,并通过参数分析确定相关参数值,改进随机森林模型在室内定位方面的使用效果。最后,采用随机森林分类模型预测目标标签的所属区域,再利用相应区域随机森林回归模型预测目标标签的精确坐标,实现了基于射频识别技术接收信号强度的室内精确定位。在室内环境下,通过所搭建的射频识别技术室内定位方法可测得的平均定位误差为4.89 cm,与其他算法相比平均定位精度提高80%以上,能够满足物流高密度仓储场景下的物品定位需求。

关键词: 室内定位, 射频识别技术, 接收信号强度, 随机森林

Abstract: In order to solve the problem of low application rate and poor positioning accuracy of the existing RFID technology in the field of logistics and warehousing high-precision positioning,a positioning method of RFID technology based on improved random forest model is proposed. Firstly,an environment is built in which multiple antennas read the received signal strength of the reference tag at the same time,and the iterative average filtering algorithm is used to collect the received signal strength values during the reading process,new properties are deduced from the existing received signal strength values by using a sliding window to expand the machine learning data set. Secondly,the random forest classification model is introduced to construct the basis of the random forest model,which takes the received signal strength and its new attributes as input and the X-axis and Y-axis coordinates as output. The relevant parameter values are determined through parameter analysis to improve the use effect of the random forest model in indoor positioning. Finally,the random forest classification model is used to predict the region to which the target label belongs,and then the random forest regression model of the corresponding region is used to predict the exact coordinates of the target label,so as to realize the indoor accurate positioning based on the received signal strength of radio frequency identification technology. In the indoor environment,the average positioning error that can be measured by the indoor positioning method of the radio frequency identification technology is 4.98 cm. Compared with other algorithms,the average positioning accuracy is improved by more than 80%,which can meet the positioning needs of items in high-density logistics storage scenarios.

Key words: Indoor positioning system, Radio frequency identification, Received signal strength, Random forest

中图分类号: 

  • TP391.44
[1]NIKOLA G,SCHULZ K,IVANOCHKO I. Use of RFID Technology in Retail Supply Chain[J]. Developments in Information &Knowledge Management for Business Applications,2021,1:555-587.
[2]GOSWAMI S. Indoor location technologies[M]. Springer Science & Business Media,2012.
[3]LI N,BECERIK-GERBER B. Performance-based evaluation of RFID-based indoor location sensing solutions for the built environment[J]. Advanced Engineering Informatics,2011,25(3):535-546.
[4]GOMES E L,FONSECA M,LAZZARETTI A E,et al. Clustering and hierarchical classification for high-precision RFID indoor location systems[J]. IEEE Sensors Journal,2021,22(6):5141-5149.
[5]HE Y,GUO Z X,GUI L Q,et al. RFID Multi-tag Relative Location Method Based on RSSI Sequence Features[J]. Computer Science,2023,50(11):296-305.
[6]LAN Q Q,XIAO B X,Grid-based density peak clustering algorithm for RFID positioning [J]. Journal of Electronic Measurement and Instru-mentation,2018,32(10):73-78.
[7]MIAO Z H,CHEN A G,ZHU L J,et al. Im-proved LANDMARC Downhole Positioning Algorithm Based on Adaptive CKF[J]. Metal Mine,2024(1):158-164.
[8]JIAO X L,GUO A B,ZHANG J Y,et al. Novel optimization algorithm for cable RFID positioning technology[J]. China SafetyScience Journal,2023,33(S2):182-187.
[9]CAVUR M,DEMIR E. RSSI-based hybrid algorithm for real-time tracking in underground mining by using RFID technology[J]. Physical Communication,2022,55:101863.
[10]XUE H,LI L,WEN P,et al. A machine learning-based positioning method for poultry in cage environments[J]. Computers and Electronics in Agriculture,2023,208:107764.
[11]WANG Z,LIANG X,CHU Y,et al. 3D Localization of RFID Tags Using SA Single-Antenna Based on Time Series Regression Model[J]. IEEE Internet of Things Journal,2024,11(23):38755-38766.
[12]AFUOSI M B,ZOGHI M R. Indoor positioning based on improved weighted KNN for energy management in smart buil-dings[J]. Energy and Buildings,2020,212:109754.
[13]KHAN S I,RAY B R,KARMAKAR N C. Rfid localization in construction with iot and security integration[J]. Automation in Construction,2024,159:105249.
[14]LI L,ZHENG J L,LUO W C,et al. RFID Indoor Positioning Algorithm Based on Proximal Policy Opyimization[J]. Computer Science,2021,48(04):274-281.
[15]XU W,TU J,XU N,et al. Predicting daily heating energy consumption in residential build-ings through integration of random forest model and meta-heuristic algorithms[J]. Energy,2024,301:131726.
[16]WU Z,WANG Y,FU J. A hybrid RSSI and AoA indoor positioning approach with adapted confidence evaluator[J]. Ad Hoc Networks,2024,154:103375.
[17]XIE L B,LI Y Y,WANG Y,et al. Indoor RFID localization algorithm based on adaptive bat algorithm[J]. Journal Communications,2022,43(8):90-99.
[18]ZHANG X,SHEN H,HUANG T,et al. Improved random fo-rest algorithms for increasing the accuracy of forest above ground biomass estimation using Sentinel-2 imagery[J]. Ecological Indicators,2024,159:111752.
[19]XU H,WU M X,LI P. RFID Indoor Relative Position Positioning Algorithm Based on ARIMA Model[J]. Computer Scien-ce,2020,47(9):252-257.
[20]LIU G B,ZHU Z,FANG T,et al. Design of Mine Air Quality Evaluation System Based on Improved Random Forests[J]. Mental Mine,2024(11):210-218.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发