Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
Artificial Intelligence: A Guide to Intelligent Systems
Artificial Intelligence: A Guide to Intelligent Systems
Wireless Communications: Principles and Practice
Wireless Communications: Principles and Practice
Ecolocation: a sequence based technique for RF localization in wireless sensor networks
IPSN '05 Proceedings of the 4th international symposium on Information processing in sensor networks
A practical evaluation of radio signal strength for ranging-based localization
ACM SIGMOBILE Mobile Computing and Communications Review
Wireless Sensors Self-Location in an Indoor WLAN Environment
SENSORCOMM '07 Proceedings of the 2007 International Conference on Sensor Technologies and Applications
Architectural Solutions for Mobile RFID Services for the Internet of Things
SERVICES '08 Proceedings of the 2008 IEEE Congress on Services - Part I
Genetic Algorithm Based Wireless Sensor Network Localization
ICNC '08 Proceedings of the 2008 Fourth International Conference on Natural Computation - Volume 01
Propagation measurements and models for wireless communications channels
IEEE Communications Magazine
Hi-index | 0.00 |
In the current (Internet of Things) trend, the identification capability of RFID is integrated for the identification and applications of all objects, and this trend reveals the future demand for RFID wireless communication and localization. Therefore, this paper investigates the influences of RSSI and the distance to RFID and analyzes the common indoor localization algorithms, including range-based algorithms and range-free algorithms. However, there are too many interference factors in the indoor environment that easily lead to localization inaccuracy. To improve the RF-mapping technique in RFID that requires much time for initiation and lots of calculations, this paper proposes a GA-based (Genetic Algorithms, GA) localization algorithm to estimate the locations of unknown nodes and avoid the influence of environmental factors by pre-establishing the pattern. The designed scenarios and reference nodes in this paper are used to train our proposed algorithm and obtain the patents of the scenarios, which are adopted for RFID nodes to further compare and decrease errors. Therefore, as long as the algorithm is trained in advance with the scenarios and then include the patents in the new environment, the errors and the training time can be greatly reduced. Moreover, our proposed algorithm needs only little information about reference nodes to pre-establish the pattern.