Reducing Search Area in Indoor Localization Applications
- PDF / 2,182,431 Bytes
- 16 Pages / 439.37 x 666.142 pts Page_size
- 49 Downloads / 218 Views
Reducing Search Area in Indoor Localization Applications Hossein Ghaffarian1 Accepted: 29 October 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract In this paper, we propose vertical and horizontal methods to reduce size of search area in indoor localization applications. Although, larger fingerprints means better accuracy, mostly indoor localization applications are running in mobile devices with limited battery, memory, and even processing power. In the proposed approaches, we reduce the size of fingerprints using reducing Access Points (APs) information (vertical reduction) and reducing fingerprint records (horizontal reduction). In vertical reduction, we focus on the importance of APs based on their appearance in fingerprint records. In horizontal reduction, we use regression and decision tree classifiers for primary location estimation. Then, only records in a predefined neighbourhood radius are selected for final localizations. Our studies show that the results of the vertical reduction approaches have a better performance against the results of the horizontal reduction approaches during the indoor localization phase. Also, these findings show that the best way to reduce the size of the fingerprints file is by removing the most common APs from the list. Keywords Search area · Fingerprint · Indoor localization · Vertical reduction · Horizontal reduction
1 Introduction Nowadays, localization becomes an interesting research topic. Although satellite-based localization systems prove their abilities, they are not applicable in indoor environments. Therefore, indoor localization has worth considering. Such technology is applicable in safety, security, and energy-saving applications. Due to the proliferation of Wireless Local Area Networks (WLAN), it gives priority to the technology used in this field. Readers can find several useful surveys in this area, e.g. [1–7]. WiFi-based indoor localization systems involve two steps: an offline phase and an online phase. In the offline phase, a fingerprints file of Received Signal Strength (RSS) of concerned APs in different locations of a building is created. The online phase involves finding the location of a user based on comparing received RSSs in his current location with stored fingerprints. In some WiFi-based localization applications, instead of direct * Hossein Ghaffarian h‑[email protected] 1
Computer Engineering Department, Faculty of Engineering, Arak University, Arak, Iran
13
Vol.:(0123456789)
H. Ghaffarian
use of the fingerprints file, it has been used to create a statistical model, e.g. [8–10]. Then this model is used for localization. However, due to the fully dynamic nature of signals of WLANs inside a building, this approach is not considered globally. Although the accuracy of localization has a direct relation with the quality of stored fingerprints file, the size of fingerprints can make processing overheads, especially in large buildings. Portable and mobile devices have limited memory and processing capa
Data Loading...
