A constructive Steiner graph matching for Radio frequency identification device tag detection in wireless and internet of things environment

Abstract

SummaryRadio frequency identification device (RFID) has emerged as one of the most potential building blocks for future IoT‐enabled technologies. Various applications like logistic monitoring use the RFID system to deal with the tagged objects. RFID‐based tracking approach is extremely solicited for appropriate logistic distribution because of the frequent tagged‐objects rearrangements. Nevertheless, with an RFID system, one of the most significant issues is resolving collisions between tags as they transfer data to the reader at the same time. This work investigates the core issue of locating all lost tags in RFID systems. The most significant factor in missing tag recognition is to reduce the time required for execution. A problem needs to be formulated to differentiate the tagged objects' motion state, that is, static or dynamic, to handle this issue. It tracks the moving objects with various existing localization approaches. Finally, a tag detection known as constructive Steiner graph matching (CSGM) detection is proposed to achieve time efficiency by utilizing RFID collision signals. Specifically, the physical‐layer features are considered for differentiating the positions. Experimental outcomes demonstrate that the anticipated model can attain better prediction accuracy by reducing inventory time compared to other approaches. Simulation findings show that the suggested approach performs exceptionally well in giving a significant performance boost in an RFID system. It minimizes the complexity of tracking the objects. The simulation outcomes illustrate that the algorithm's identification speed is substantially enhanced and ensuring high system efficiency. The simulation results of the proposed algorithm have been improved in terms of system efficiency (9.5%), success rate (6.3%), and identification speed (4%) compared to the conventional algorithm. The suggested CSGM technique's average waiting time is decreased by more than 45.372%, and its detection speed is increased by at least 38.219% compared to other existing algorithms.