计算机与现代化

• 算法设计与分析 • 上一篇    下一篇

基于滑动窗口的RFID自适应数据清洗算法

  

  1. (南京航空航天大学计算机科学与技术学院,江苏南京210016)
  • 收稿日期:2014-10-11 出版日期:2015-01-19 发布日期:2015-01-21
  • 作者简介:封慧英(1990-),女,河北石家庄人,南京航空航天大学计算机科学与技术学院硕士研究生,研究方向:信息系统及集成,物联网系统; 周良(1966-),男,副教授,硕士生导师,博士,研究方向:信息系统,知识工程。
  • 基金资助:
    江苏省产学研联合创新资金资助项目(SBY201320423)

Adaptive RFID Data Cleaning Algorithm Based on Sliding-window

  1. (College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China)
  • Received:2014-10-11 Online:2015-01-19 Published:2015-01-21

摘要: RFID(射频识别)标签阅读器对操作环境的敏感性很高,导致其产生的RFID数据流不可靠,并含有大量的漏读,因此必须要对原始数据进行清洗。设计基于滑动窗口的自适应数据清洗算法,算法使用滑动窗口技术和二项分布模型计算合适的窗口大小,通过窗口子区间的监测结果和标签的状态来动态调整窗口大小。结果显示,在移动环境下本算法比SMURF算法产生的平均错误数少,性能更加优越,准确率和稳定性都有明显提高。

关键词: RFID, 滑动窗口, 二项分布模型, 数据清洗

Abstract: RFID (radio frequency identification devices) tag reader is very sensitive to the operating environment, which causes the produced RFID data flow unreliable, containing a large amount of missing words in reading, therefore, it’s necessary to cleanse the original data. An adaptive data cleansing algorithm based on sliding window is designed, which employs the sliding window technology and binomial distribution model to calculate the appropriate size of windows and dynamically adjusts the size of the window through the monitoring results of the subinterval windows and the states of the tags. Results show that this algorithm produces fewer errors on average than SMURF algorithm, that its performances are more superior and that its accuracy and stability are obviously improved.

Key words: RFID, slidingwindow, binomial model, data cleaning

中图分类号: