Date Added: Feb 2013
The data stream produced by RFID reader is sometimes inaccurate. As a result there is a big load of unreliable data which is useless for higher level processing. Therefore the authors need to clean this unreliable data which they sometimes call dirty data. Dirty data appears in three reading errors form: false positive, false negative and duplicate readings. In this paper, an assumed data set is generated and applied this data set on data mining tools to make comparison on both the tools i.e. Tanagra and weka to check the result.