HiQ: A Hierarchical Q-Learning Algorithm to Solve the Reader Collision Problem
SAINT-W '06 Proceedings of the International Symposium on Applications on Internet Workshops
Bio-inspired and gradient-based algorithms to train MLPs: The influence of diversity
Information Sciences: an International Journal
Review Article: Recent Advances in Artificial Immune Systems: Models and Applications
Applied Soft Computing
Probabilistic DCS: An RFID reader-to-reader anti-collision protocol
Journal of Network and Computer Applications
RFID Dense Reader Network Anti-collision PSO Model and Solving
IHMSC '11 Proceedings of the 2011 Third International Conference on Intelligent Human-Machine Systems and Cybernetics - Volume 01
Hi-index | 12.05 |
In a radio-frequency identification (RFID) system, if a group of readers transmit and/or receive signals at the same time, they will probably interfere with each other, so that the resulting reader collision problems (e.g., reader-to-reader collision, reader-to-tag collision) will happen. Generally, the reader-to-reader collision can be mitigated by maximizing the tag identification capability, which is related to frequencies and time slots, so it can be transferred as a resource scheduling problem by optimizing the tag identification capability. Artificial immune system is an emerging heuristic evolutionary method which is widely applied to scientific researches and engineering problems. This paper formulates a reader-to-reader anti-collision model from the viewpoint of resource scheduling and proposes an adaptive hierarchical artificial immune system (RA-AHAIS) to solve this optimization problem. A series of simulation experiments are arranged to analyzing the effects of time slots and frequency. Further simulation experiments are made to compare such performance indices as number of identified tags between the proposed RA-AHIAS and the other existing algorithms. The numerical simulation results indicate that this proposed RA-AHAIS is an effective reader-to-reader anti-collision method, and performs better in tag identification capability and computational efficiency than the other methods, such as genetic algorithm (RA-GA), particle swarm optimization (RA-PSO) and artificial immune system for resource allocation (RA-AIS).