引入卡尔曼滤波的RFID数据清洗方法

Cleaning Method of RFID Data Stream Based on Kalman Filter

RFID技术现已广泛应用在供应链、制药监管等领域,然而数据的不准确性制约了RFID技术的进一步发展.为提供高质量的RFID数据给高层应用,对RFID原始数据进行清洗十分必要.本文提出一种基于卡尔曼滤波过滤的数据清洗方法KAL-RFID,有效地解决了单个阅读器的消极读和积极读问题以及动态标签跃迁产生的延迟问题.实验结果表明KAL-RFID方法提高了清洗效率,并且得到更准确的清洗结果.

RFID technology is now widely used in many fields, such as supply chain,pharmacy monitoring. Whereas the unreliable data restricts the RFID technology from being farther developed. For effectively and efficiently supporting high-level RFID business logic processing, it is necessary to provide high-quality RFID data. For that case, it is critical to clean the original data. This paper proposed a cleaning method KAL-RFID based on Kalman Filter, to solve false negative and false positive reading from individual readers, and the transition time respond delay problem of mobile tags. In the end, as experiments shows that the KAL-RFID method improves the efficiency of data cleaning and produces more accurate data.