Smart Campus IoT Guidance System for Visitors Based on Bayesian Filters
In this work, we proposed an indoor location system that makes use of a Raspberry Pi embedded computer and WiFi signals to guide a person inside a region of the faculty of Electrical and Electronic at Universidad Nacional de Ingeniería, Peru. The main adv
- PDF / 855,581 Bytes
- 10 Pages / 439.37 x 666.142 pts Page_size
- 107 Downloads / 176 Views
bstract In this work, we proposed an indoor location system that makes use of a Raspberry Pi embedded computer and WiFi signals to guide a person inside a region of the faculty of Electrical and Electronic at Universidad Nacional de Ingeniería, Peru. The main advantage with similar indoor location systems like beacons or RFID technology is that the presented system does not require additional hardware since it makes use of the pre-installed WiFi routers. The experimental tests show promising results, achieving a location accuracy of 92.31%. Keywords Indoor location · WiFi · Bayes filter · Embedded computer
1 Introduction The existing navigation systems like Global Positioning System (GPS) offer a precise location in outside environments but an inaccurate location inside common buildings [1]. This problem of localization has attracted the interest of researchers and developers due to the high demand for such systems for indoor navigation, immersive experiences, asset tracking, augmented reality, and more. During the last decade, several approaches for indoor location systems [2] such as radio frequency identification (RFID), wireless local area networks (WLAN), and Bluetooth among others have been proposed [3]. In [4, 5], an indoor positioning A. Aspilcueta Narvaez · D. Núñez Fernández (B) · S. Gamarra Quispe · D. Lazo Ochoa Universidad Nacional de Ingeniería, Lima 15333, Peru e-mail: [email protected] A. Aspilcueta Narvaez e-mail: [email protected] S. Gamarra Quispe e-mail: [email protected] D. Lazo Ochoa e-mail: [email protected] © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021 Y. Iano et al. (eds.), Proceedings of the 5th Brazilian Technology Symposium, Smart Innovation, Systems and Technologies 202, https://doi.org/10.1007/978-3-030-57566-3_46
463
464
A. Aspilcueta Narvaez et al.
system for smart buildings was used to obtain relatively good results; however, the system makes use of RFID technology, which produces an additional cost for hardware implementation. Regarding indoor location using WiFi signals, [4] makes use of Monte Carlo (MC) filter for a precise WiFi-based indoor localization, but the system is intended for tracking objects with a high precision employing relative high computing processing, which is not suitable for real-time applications since it demands high computing resources and a small division of the regions. In recent work, [6, 7] proposes a novel, incremental approach that reduces the energy consumption of WiFi localization by scanning just a few selected channels. The results are remarkable and provide a way for the implementation of indoor location on embedded systems. In addition, Indoor Google [8] provides guidance; however, its accuracy is not enough (5–15 m). In this paper, we propose an indoor location system for a region of the faculty of Electrical and Electronic of Universidad Nacional de Ingeniería, Peru. Unlike the indoor location systems presented before, which rely on external devices like RFID hardw
Data Loading...
