Please use this identifier to cite or link to this item:
Title: Indoor Positioning for RFID using Machine Learning
Authors: KONG, MAN LONG(龔文龍)
Department: Department of Electrical and Computer Engineering
Faculty: Faculty of Science and Technology
Issue Date: 2020
Citation: Kong, M. L., Ho, C. H., Ieong, I. N. (2020). Indoor Positioning for RFID using Machine Learning (Outstanding Academic Papers by Students (OAPS)). Retrieved from University of Macau, Outstanding Academic Papers by Students Repository.
Abstract: Nowadays, with the rapid development of wireless technology, people cannot live without wireless communication technology. Among many wireless communication technologies, wireless positioning technology plays an important role in people's life and travel, etc. In recent years, in addition to the well-known GPS positioning, wireless positioning technology also includes many positioning technologies. This paper mainly focuses on indoor positioning. Because GPS positioning technology is generally only applicable to outdoor positioning, this paper will introduce other commonly used indoor positioning technology, and then focus on our theme: RFID indoor positioning and positioning methods. In here, some positioning methods or techniques can be applied in RFID indoor positioning. The project team will choose to use the Received Signal Strength Indication (RSSI) positioning and the positioning algorithm (LANDMARC) as our main positioning method and applied it to RFID indoor positioning for experimental research. The main purpose of this project is to try to use some more accurate methods for positioning in the process of learning RFID and collect some data in several positioning-related experiments to plan the positioning method. As well as to build up the positioning programs as our basic program (input is RSSI reading, output is possible to position), and finally try to use LANDMARC algorithm and machine learning to make positioning results more accurate.
Instructor: Dr. Wai Wa Choi
Programme: Bachelor of Science in Electrical and Computer Engineering
Appears in Collections:FST OAPS 2020

Files in This Item:
File Description SizeFormat 
OAPS_2020_FST_005.pdf97.87 MBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.