Publication:
Improving accuracy and simplifying training in fingerprinting-based indoor location algorithms at room level

Loading...
Thumbnail Image
Identifiers
Publication date
2016-01-01
Defense date
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
Hindawi
Impact
Google Scholar
Export
Research Projects
Organizational Units
Journal Issue
Abstract
Fingerprinting-based algorithms are popular in indoor location systems based on mobile devices. Comparing the RSSI (Received Signal Strength Indicator) from different radio wave transmitters, such asWi-Fi access points, with prerecorded fingerprints from located points (using different artificial intelligence algorithms), fingerprinting-based systems can locate unknown points with a fewmeters resolution.However, training the system with already located fingerprints tends to be an expensive task both in time and in resources, especially if large areas are to be considered. Moreover, the decision algorithms tend to be of high memory and CPU consuming in such cases and so does the required time for obtaining the estimated location for a new fingerprint. In this paper, we study, propose, and validate a way to select the locations for the training fingerprints which reduces the amount of required points while improving the accuracy of the algorithms when locating points at room level resolution.We present a comparison of different artificial intelligence decision algorithms and select those with better results. We do a comparison with other systems in the literature and draw conclusions about the improvements obtained in our proposal.Moreover, some techniques such as filtering nonstable access points for improving accuracy are introduced, studied, and validated.
Description
Keywords
Indoor location systems, Fingerprinting-based algorithms, Mobile devices, Artificial intelligence
Bibliographic citation
Mobile Information Systems, 2016 (2682869), pp. 16