Exploiting proximity readers for statistical cleaning of unreliable RFID data

Standard RFID data cleaning provides a smoothing filter that interpolate for lost readings and aggregate data via a sliding-window. Existing cleaning techniques work well under various conditions, but they mainly focus an individual reader and have disregarded the very high cost of cleaning in a real application that have thousands of readers and millions of tags. Given the enormous volume of information, diverse sources of error, and rapid response requirements, setting the window size is still a challenging task. In this paper, we propose to use proximity readers, common in real RFID applications, to enhance adaptive cleaning of massive RFID data sets. Considering the need for effective cleaning with minimum costs, we extend the multi-tag cleaning mechanism of the SMURF. Experiments are also carried out to verify the effectiveness of our algorithm. The promising experimental results reveal that the new adaptive cleaning mechanism is effective for lost readings and redundant RFID data.