Calibration Procedures for Indoor Location Using Fingerprinting
Fingerprinting is a location technique, based on the use of wireless networks, where data stored during the offline phase is compared with data collected by the mobile node during the online phase. When this location technique is used in a real-life scena
- PDF / 342,956 Bytes
- 15 Pages / 439.37 x 666.142 pts Page_size
- 30 Downloads / 250 Views
Abstract Fingerprinting is a location technique, based on the use of wireless networks, where data stored during the offline phase is compared with data collected by the mobile node during the online phase. When this location technique is used in a real-life scenario there is a high probability that the mobile node used throughout the offline phase is different from the mobile nodes that will be used during the online phase. This means that there might be very significant differences between the Received Signal Strength values acquired by the mobile node being located and the ones previously stored in the Fingerprinting Map. As a consequence, this difference between RSS values might contribute to increase the location estimation error. One possible solution to minimize these differences is to adapt the RSS values, acquired during the online phase, before sending them to the Location Estimation Algorithm. Also the internal parameters of the Location Estimation Algorithms, for example the weights of the Weighted k-Nearest Neighbour, might need to be tuned for every type of terminal. This paper focuses both approaches, using Direct Search optimization P. Mestre (B) · C. Serodio CITAB-UTAD, Algoritmi-UM, Vila Real, Portugal e-mail: [email protected] C. Serodio e-mail: [email protected] L. Reigoto · L. Coutinho UTAD, Vila Real, Portugal e-mail: [email protected] L. Coutinho e-mail: [email protected] A. Correia CM-UTAD, ESTGF-IPP, Felgueiras, Portugal e-mail: [email protected] J. Matias CM-UTAD,Vila Real, Portugal e-mail: [email protected] G.-C. Yang et al. (eds.), IAENG Transactions on Engineering Technologies, Lecture Notes in Electrical Engineering 229, DOI: 10.1007/978-94-007-6190-2_27, © Springer Science+Business Media Dordrecht 2013
349
350
P. Mestre et al.
methods to adapt the Received Signal Strength and to tune the Location Estimation Algorithm parameters. As a result it was possible to decrease the location estimation error originally obtained without any calibration procedure. Keywords Direct search optimization methods · Fingerprinting Indoor location · LEA adaptation · RSS adaptation
· IEEE802.11 ·
1 Introduction Fingerprinting location estimation is a wireless network based technique on which the values of a given property of the wireless signals, received by a mobile device, are compared with a set previously stored values, called the Fingerprinting Map (FM). This location estimation technique comprises two distinct phases: one on which data to generate the Fingerprinting Map is collected and stored in a database, called the offline phase; and a second phase, called the online phase, on which the estimation of the node location is made by comparing the collected data with the data stored in the Fingerprinting Map [1, 14]. Although any property of the wireless signal can be used, typically the Received Signal Strength (RSS) is used. During the offline phase, for each point of the spatial domain that will be mapped on the Fingerprinting Map, are collected RSS values from the wireless
Data Loading...
