Prediction of RFID tag detection for a stationary carton box

Passive RFID tag detection (or recognition) is one of the most important issues for the RFID systems to be successfully deployed in various applications. Passive RFID tag position greatly influences RFID tag detection by the RFID reader antenna. In this paper, we propose a method for a carton box object on a wooden pallet by an experimental approach based on tag signal strength, and propose a method for predicting detection directly related to the strength of tag signal using an intelligent machine learning technique called support vector machine. The proposed intelligent method is capable of saving time and costs by quick prediction of tag detection. Experiment shows that the proposed approach predicts tag recognition for a carton box object as accurately as around 95% for various reader heights and read field length values. The proposed approach is effective for determining the best tag detection influence factor condition on the target object by using the predicted detectability.