• DocumentCode
    1501974
  • Title

    Intelligent RFID tag detection using support vector machine

  • Author

    Jo, Minho ; Youn, Hee Yong ; Chen, Hsiao-Hwa

  • Author_Institution
    Grad. Sch. of Inf. Manage. & Security, Korea Univ., Seoul, South Korea
  • Volume
    8
  • Issue
    10
  • fYear
    2009
  • fDate
    10/1/2009 12:00:00 AM
  • Firstpage
    5050
  • Lastpage
    5059
  • Abstract
    RFID Tag detection/recognition is one of the most critical issues for successful deployment of RFID systems in diverse applications. The main factors influencing tag detection by RFID reader antenna include tag position, relative position of reader, read field length, etc. In this paper, we analyze the characteristics of tag detection for a carton box object on a wooden pallet by an experimental approach based on tag signal strength, and we propose a method for predicting detection related directly to the strength of tag signal using an intelligent machine learning technique called support vector machine (SVM). The use of the proposed method is able to save time and cost by quick prediction of tag detection. Extensive experiments showed that the proposed approach can predict tag recognition for a carton box object with an accuracy at 95% for various reader heights and read field lengths. The proposed approach is effective for determining the best tag detection influencing factor conditioned on the target object with the help of detectability prediction.
  • Keywords
    radiofrequency identification; signal detection; support vector machines; RFID reader antenna; RFID tag detection; carton box object; radiofrequency identification; signal detection; support vector machines; tag position; Data mining; Learning systems; Machine intelligence; Middleware; Object detection; RFID tags; Radio frequency; Radiofrequency identification; Signal analysis; Support vector machines; RFID, SVM, intelligent prediction of tag detection influencing factor;
  • fLanguage
    English
  • Journal_Title
    Wireless Communications, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    1536-1276
  • Type

    jour

  • DOI
    10.1109/TWC.2009.071198
  • Filename
    5288941