基于改进卡尔曼滤波的RFID数据清洗方法研究

计算机科学 ›› 2014, Vol. 41 ›› Issue (3): 202-204.

基于改进卡尔曼滤波的RFID数据清洗方法研究

陈静云,周良,丁秋林

南京航空航天大学计算机科学与技术学院南京210016;南京航空航天大学计算机科学与技术学院南京210016;南京航空航天大学计算机科学与技术学院南京210016

出版日期:2018-11-14 发布日期:2018-11-14
基金资助:
本文受国防基础科研计划项目资助

Cleaning Method Research of RFID Data Stream Based on Improved Kalman Filter

CHEN Jing-yun,ZHOU Liang and DING Qiu-lin

Online:2018-11-14 Published:2018-11-14

摘要/Abstract

摘要： 采用RFID(radio frequency identification)技术在阅读器和动态电子标签之间进行通信,采集到的数据通常存在大量的脏数据。为更好支持高层应用,必须对原始数据进行清洗。针对标签频繁移动这一特点,将滑动窗口技术引入卡尔曼滤波模型,给出了一种改进的卡尔曼滤波模型,进而提出了一种基于改进卡尔曼滤波的RFID数据清洗方法。该方法在保证数据清洗准确率的基础上能有效解决标签动态跃迁带来的时间延迟问题,从而更加适用于标签频繁移动的场景。实验结果表明,该算法提高了清洗效率及准确率。

关键词: 卡尔曼滤波,RFID,数据清洗,滑动窗口,动态标签中图法分类号TP311文献标识码A

Abstract: RFID (radio frequency identification) technology has been widely applied to the communication between RFID readers and dynamic electronic labels,but the data captured by RFID readers often tends to be noisy．In order to provide a better support for high-level RFID’s applications,it is necessary to clean the collected data．Considering the characteristic of frequent movement of labels,this paper put forward an improved Kalman filter model by combining the sliding window technique with Kalman filter model and then proposed a method of RFID data cleaning based on an improved Kalman filter．The method can not only guarantee the accuracy of data cleaning but also effectively solve the problem of time delay caused by dynamic electronic tags．Thus this method is more adaptable to the situation where labels are moved frequently．The experiment’s result shows this approach can improve the efficiency and accuracy of the data cleaning．

Key words: Kalman filter,RFID,Data cleaning,Slide window,Dynamic label

陈静云,周良,丁秋林. 基于改进卡尔曼滤波的RFID数据清洗方法研究[J]. 计算机科学, 2014, 41(3): 202-204. https://doi.org/

CHEN Jing-yun,ZHOU Liang and DING Qiu-lin. Cleaning Method Research of RFID Data Stream Based on Improved Kalman Filter[J]. Computer Science, 2014, 41(3): 202-204. https://doi.org/

参考文献

[1] 王霞,玄丽娟,夏秀峰.基于时序关系的RFID不确定数据清洗算法[J]．辽宁大学学报,2012,9(2):174-178
[2] 马岩,张延园,尹方鸣．基于滑动窗口的RFID数据流多标签清洗算法[J]．科学技术与工程,2009,9(5):1165-1171
[3] 李晓静,谷峪,吕燕飞,等.基于动态事件概率模型的高效RFID数据清洗算法[J]．计算机研究与发展,2008,5(Suppl.):8-12
[4] 杨梦宁,赵鹏,张小洪,等.一种基于总线模型的数据清洗方法[J].计算机科学,2010,7(4):224-226
[5] Jeffrey R,Alonso G,Franklin M,et al．A pipelined framework for on line cleaning of sensor data streams[C]∥Proc of ICDE,2006.Washington:IEEE Computer Society,2006:773-778
[6] Bai Yi-jian,Wang Fu-sheng,Lin Pei-ya．Efficiently FilteringRFID data streams[C]∥Proceedings of the 1st International VLDB Workshop on Clean Database,2006．Seoul:Morgan Kaufmann Publishers,2006:50-57
[7] Jeffery S R,Garofalakis M,Franklin M J．Adaptive cleaning forRFID data streams[C]∥Proceedings of the 32nd International Conference on Very Large Data Bases,2006．Seoul:ACM,2006:163-174
[8] Li Xing,Fu Wen-xiu.Efficient RFID Data Cleaning Method[J]．TELKOMNIKA,2013,1(3):1707-1713
[9] Meng Ling-yong,Yu Feng-qi．RFID Data Cleaning Based on Adaptive Window[C]∥Proc of the 2nd International Conference on Future Computer and Communication,2010．Wuhan,China,IEEE,2010:746-749
[10] Wang Yan,Song Bao-yan．Cleaning Method of RFID DataStream Based on Kalman Filter[J]．Journal of Chinese Compu-ter Systems,2011,32(9):1794-1799
[11] Wang Fu-sheng,Liu Shao-rong,Liu Pei-ya．Complex RFID Event Processing[J]．VLDB Journal,2009,8:913-931

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed