Research on Temperature Control Algorithm Based on Outlier Mining in RFID

Using data mining approach to handle real-time RFID temperature data can effectively achieve automatic real time monitoring of temperature. The FAM algorithm proposed by the paper which uses the two properties of global approximation outlier degrees and local approximate outliers to realize the pruning of the RFID temperature data sets. The experimental results demonstrate that when handling the cold chain temperature data, the algorithm can reduce user dependence, decrease the complexity of the algorithm and improve the accuracy. It is an effective solution to the problem of processing massive data by the use of RFID technology.