X.H. Chen
Beijing University of Posts and Telecommunications, 100876, Beijing, China
L. Niu
Beijing University of Posts and Telecommunications, 100876, Beijing, China
Y.J. Zhou
Beijing University of Posts and Telecommunications, 100876, Beijing, China
Z. Bi
Beijing University of Posts and Telecommunications, 100876, Beijing, China
G. Ding
Beijing University of Posts and Telecommunications, 100876, Beijing, China
D. Liang
Beijing University of Posts and Telecommunications, 100876, Beijing, China
ABSTRACT
Affinity propagation is an algorithm which is proposed in recent years. It is an algorithm of broad application and high accuracy. From the perspective of statistic, the clustering error falls into two major categories. One results from environmental distraction, which belongs to a random error. Another part is system error resulting from the shortcoming of the fingerprint-based location technique. We refine this shortcoming as aliasing. Aliasing means that there are several distinct locations but having the same RSS vector. When there are clusters having the same vector as a certain input RSS vector, fingerprint-based technique is not able to indicate which cluster is the correct one. So, how to avoid aliasing error has become a crucial problem to solve. In this study, we proposed an innovative approach inspired by Affinity Propagation and based upon the log-normal shadowing model. The experimental results demonstrate that this approach not only achieves lower location error and quicker coverage speed, but also avoid great error to some extent.
PDF References Citation
How to cite this article
X.H. Chen, L. Niu, Y.J. Zhou, Z. Bi, G. Ding and D. Liang, 2013. Rss-based Affinity Propagation Algorithm Accuracy Improvement Considering
Physical Location. Information Technology Journal, 12: 4544-4548.
DOI: 10.3923/itj.2013.4544.4548
URL: https://scialert.net/abstract/?doi=itj.2013.4544.4548
DOI: 10.3923/itj.2013.4544.4548
URL: https://scialert.net/abstract/?doi=itj.2013.4544.4548
REFERENCES
- Miluzzo, E., N.D. Lane, K. Fodor, R. Peterson and H. Lu et al., 2008. Sensing meets mobile social networks: the design, implementation and evaluation of the CenceMe application. Proceedings of the International Conference on Embedded Networked Sensor Systems, June 2008, New York, USA., pp: 337-350.
Direct Link - Shravan, G., J. Li, R.R. Choudhury, L. Cox and A. Schmidt, 2008. Micro-blog: Sharing and querying content through mobile phones and social participation. Proceedings of the 6th International Conference on Mobile Systems, Applications and Services, June 2008, Breckenridge, CO., pp: 174-186.
CrossRef - Varshavsky, A., A. LaMarca, J. Hightower and E. de Lara, 2007. The skyloc floor localization system. Proceedings of the 5th Annual IEEE International Conference on Pervasive Computing and Communications, March 19-23, 2007, White Plains, NY., pp: 125-134.
CrossRef - You, Z., O. Baala and A. Caminada, 2010. Optimization model for an indoor WLAN-based positioning system. Proceedings of the International Conference on Indoor Positioning and Indoor Navigation, September 15-17, 2010, Zurich, Switzerland, pp: 1-7.
CrossRef