Indoor positioning using wireless networks

Citation

Kan, Min Hao and Pang, Wai Leong and Lee, Chu Liang (2022) Indoor positioning using wireless networks. Periodic Research Publication, Faculty of Engineering. (Unpublished)

[img] Text
17_1171101437 KAN MIN HAO_WLPang_FYP POSTER.pdf
Restricted to Repository staff only

Download (603kB)

Abstract

In this research paper, a machine learning method is proposed for IPS using the WiFi. Received Signal Strength Indication ( RSSI) fingerprinting approach. A WEMOS D 1 Mini microcontroller with a built in ESP 8266 and a Liquid Crystal Display (LCD) were used to show the output of predicted locations. There are three different phases of experiments including Phase 1 (To identify the best machine learning algorithm and the number of APs to be used for IPS), Phase 2 (To determine the best number of datasets of each location for IPS) and Phase 3 (To determine the best AP’s locations and co channel for IPS) carried out for this study in order to obtain the best configuration for WiFi IPS. The result for Phase 1 gave a moderate average accuracy of 60% and Phase 2 gave an average accuracy of 73% for three test locations. However, the performance of the WiFi IPS is not decent in predicting the correct locations. Therefore, Phase 3 was carried out to improve the accuracy and the result shows an average accuracy of 94.33% improvement.

Item Type: Other
Subjects: Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75-76.95 Calculating machines
Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science > QA76.75-76.765 Computer software
Divisions: Faculty of Engineering (FOE)
Depositing User: Assoc. Dr Chee Pun Ooi
Date Deposited: 29 Nov 2022 01:06
Last Modified: 29 Nov 2022 01:06
URII: http://shdl.mmu.edu.my/id/eprint/10646

Downloads

Downloads per month over past year

View ItemEdit (login required)