基于滑动窗口的RFID数据流多标签清洗算法  

Multi-tag Cleaning Algorithm of RFID Data Stream Based on Sliding Window

作　　者：马岩[1] 张延园[1] 尹方鸣[1] 

机构地区：[1]西北工业大学计算机学院,西安710129

出　　处：《科学技术与工程》2009年第5期1165-1171,共7页Science Technology and Engineering

基　　金：国家自然科学基金项目(60720106001)资助

摘　　要：RFID数据流清洗技术主要关注的是数据的实时性、完整性和动态性。传统的适应性清洗机制针对的只是单标签的情况,且在调整窗口以保证动态性的情况下丧失了完整性。为此,首先在二项分布模型的基础上提出了一种新的单标签清洗算法,改进和完善了传统的单标签清洗算法;之后提出了基于防碰撞模型的多标签清洗算法,从而形成了一套完整的数据流清洗算法。此外,进行了大量实验,验证了算法的有效性。RFID data stream cleaning technology is mainly concerned for real-time, integrity and dynamic nature of data. The traditional adaptive cleaning mechanism is only used for single tag scenario, and losing its integrity when adjusting the window in order to ensure the dynamic nature. To this end, firstly proposes a new single tag cleaning algorithm which improves and refines the traditional single tag cleaning mechanism based on the binomial distribution model, and then proposes a muhiple tag cleaning algorithm based on the anti-collision model so that we form a complete set of data stream cleansing algorithm. In addition, a lot of correlative experiments to verify the effectiveness of our algorithm.

关 键 词：完整性 动态性 二项分布模型 防碰撞模型 

分 类 号：TP391.07[自动化与计算机技术—计算机应用技术]