Abstract
Indoor fingerprinting localization approaches estimate the location of a mobile object by matching observations of received signal strengths (RSS) from access points (APs) with fingerprint records. In real WLAN environments, there are more and more APs available, with interference between them, which increases the localization difficulty and computational consumption. To cope with this, a novel AP selection method, LocalReliefF-C( a novel method based on ReliefF and correlation coefficient), is proposed. Firstly, on each reference location, the positioning capability of APs is ranked by calculating classification weights. Then, redundant APs are removed via computing the correlations between APs. Finally, the set of best-discriminating APs of each reference location is obtained, which will be used as the input features when the location is estimated. Furthermore, an effective clustering method is adopted to group locations into clusters according to the common subsets of the best-discriminating APs of these locations. In the online stage, firstly, the sequence of RSS observations is collected to calculate the set of the best-discriminating APs on the given location, which is subsequently used to compare with cluster keys in order to determine the target cluster. Then, hidden naive Bayes (HNB) is introduced to estimate the target location, which depicts the real WLAN environment more accurately and takes into account the mutual interaction of the APs. The experiments are conducted in the School of Environmental Science and Spatial Informatics at the China University of Mining and Technology. The results validate the effectiveness of the proposed methods on improving localization accuracy and reducing the computational consumption.
Highlights
With the popularity of smart phones and the development of mobile Internet, a great deal of location-based services (LBS) emerges, such as e-advertisements for customers walking in shopping malls and for cars locating services in underground parking lots
Fingerprinting localization, the second category of indoor positioning methods, is recognized as a main research direction owing to the following advantages: it is flexible and easy to realize; there is no need to know exactly the physical location of the access points (APs); and it does not rely on additional hardware
We have proposed a novel AP selection method, LocalReliefF-C, which can obtain the set of the best-discriminating APs for each reference location via removing useless and redundant APs
Summary
With the popularity of smart phones and the development of mobile Internet, a great deal of location-based services (LBS) emerges, such as e-advertisements for customers walking in shopping malls and for cars locating services in underground parking lots. Fingerprinting localization, the second category of indoor positioning methods, is recognized as a main research direction owing to the following advantages: it is flexible and easy to realize; there is no need to know exactly the physical location of the APs; and it does not rely on additional hardware. It is urgently needed to find a good strategy of finding the set of the most useful APs while effectively exploiting the interaction between APs. We have proposed a novel AP selection method, LocalReliefF-C (a novel method based on ReliefF and correlation coefficient), which can obtain the set of the best-discriminating APs for each reference location via removing useless and redundant APs. The process of AP selection reduces the dimension of the input vector used for positioning and, brings lower computational complexity. The rest of this paper is organized as follows: Section 2 introduces related work on AP selection and depicts the proposed AP selection method, LocalReliefF-C, in detail; Section 3 shows the fast clustering process of fingerprint records based on the sets of best-discriminating APs; Section 4 describes the location estimation method based on the hidden naive Bayes model; Section 5 gives the experimental design and results analysis; and Section 6 concludes the paper and gives suggestions for future research
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
