RFID数据清洗技术研究进展

Research Progress of RFID Data Cleaning Technology

无线射频识别(RFID)技术是一种自动识别方法,它依赖于称为RFID标签的无线电转发器快速存储和检索数据。由于RFID标签与读写器通信时无需直接接触,这样为短时间内采集大量的数据提供了可能。但是,采集到的数据也产生了诸如漏读、多读、冗余、乱序等问题,如何在短时间内高效地清洗产生的大规模RFID数据成为数据库领域的重要研究课题。对现有的RFID数据清洗技术进行了综述。首先,给出了RFID系统与RFID数据清洗问题的有关定义与描述,列出了典型的数据集与评价标准,从相关技术的分类、子类、基本思想、优势、局限、适用场景等方面详细比较和总结了现有的RFID数据清洗工作,同时对相关应用系统进行比较分析。然后,针对漏读数据清洗、多读数据清洗、冗余数据清洗、乱序数据处理等关键问题,对已有的研究进行了详细的比较和总结。最后,从RFID原始数据与基准数据集构建、加密与隐私保护数据的清洗策略、数据采集准确率、清洗结果的时效性、场景自学习等方面提出了RFID数据清洗领域未来五个值得关注的研究方向。

Radio frequency identification(RFID)technology is an automatic identification method,which relies on the use of radio repeaters called RFID tags to quickly store and retrieve data.Because RFID tags do not need linear contact when communicating with readers,it is possible to collect a large amount of data in a short time.However,the collected data also produce problems such as false negative readings,false positive readings,duplicated readings,out-of-order readings and so on.In this case,how to efficiently clean the large-scale RFID data in short time has become an important research topic in the field of database.This paper mainly summarizes the existing RFID data cleaning technology.Firstly,the relevant definitions and descriptions of RFID system and RFID data cleaning problem are given,and typical datasets and evaluation criteria are listed.Then the existing RFID data cleaning work is compared and summarized in detail from the classification,subcategory,basic idea,advantages,limitations,application scenarios and other aspects of related technologies.At the same time,the relevant application systems are compared and analyzed.Then,for the key problems of the false negative reading,false positive reading,duplicated reading and out-of-order reading,the existing studies are compared and summarized in detail.Finally,this paper proposes next five research directions worthy of paying attention to in the field of RFID data cleaning,such as the construction of RFID original data and benchmark dataset,the cleaning strategy of encryption and privacy protection data,the accuracy of data collection,the timeliness of cleaning results,and scene self-learning.