Indoor Positioning Based on Wireless Local Area Network With Bayesian Algorithm

 




 

Koh, Soo Hong (2018) Indoor Positioning Based on Wireless Local Area Network With Bayesian Algorithm. Final Year Project (Bachelor), Tunku Abdul Rahman University College.

[img] Text
Koh Soo Hong.pdf
Restricted to Registered users only

Download (1MB)

Abstract

Global Positioning Service (GPS) provides us the outdoor location-based service but it does not work well in the indoor or the crayon area where there are obstacles that block the satellite signal. This caused the satellite signal attenuated and cannot provide accurate positioning. Hence, many indoor positioning techniques have been researched to meet the accurate indoor positioning demands. There are few indoor positioning system (IPS) such as Bluetooth IPS, Ultrasonic IPS but among them, Wi-Fi based IPS have grab a lot of attention due to its low cost, high accuracy and wide popularization. This IPS focus on the smartphone device application as most of the people own it but this rise up few problems especially when the object is on the move such as large positioning error, positioning jumps and etc. Many WLAN-based indoor positioning estimation algorithms have been proposed to tackle with these problem. These algorithms mostly take in the consideration of few factors such as Received Signal Strength (RSS), Time of Arrival (TOA), Time Difference of Arrival (TDOA) and location of Access Point (AP) as these are factors to approximate an object location. In this project, a WLAN based indoor positioning with Bayesian algorithms is proposed. In this work, we will be examining the robustness and reliability using Bayesian algorithm to estimate the user locations based on real life fingerprint data. The mathematical calculation of Bayesian will be investigated to understand its strengths and weaknesses. The robustness and reliability of the Bayesian algorithm are investigated by intentionally introducing changes in the online fingerprint data. The level of changes in fingerprint data will be categorized and hence could provide a guidance to the IPS designer.

Item Type: Final Year Project
Subjects: Technology > Electrical engineering. Electronics engineering
Faculties: Faculty of Engineering and Technology > Bachelor of Engineering (Honours) Electronic (Communication)
Depositing User: Library Staff
Date Deposited: 17 Oct 2018 08:36
Last Modified: 12 Apr 2022 08:51
URI: https://eprints.tarc.edu.my/id/eprint/366