Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Computing | en_US |
| dc.contributor.advisor | Chan, C. B. Henry (COMP) | en_US |
| dc.creator | Ho, Yik Him | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/11503 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | en_US |
| dc.rights | All rights reserved | en_US |
| dc.title | Mobile positioning methods using bluetooth low energy technologies | en_US |
| dcterms.abstract | There are over 3 billion smartphones in the world with an annual growth rate of about 10 percent in recent years. With the advent of smartphones, mobile positioning is an important research topic. Compared to other wireless/mobile technologies, Bluetooth Low Energy (BLE) is particularly suitable for supporting mobile positioning because it is lightweight, energy efficient, and available on most smartphones. The aim of this thesis is to investigate mobile positioning methods using BLE technologies. The major contributions are summarized as follows. First, a new positioning algorithm, namely Blueprint with NUFO detection is proposed. It aims to improve the accuracy by discretizing the measured signal strength to four values using a simple fingerprint-like method. Positions are estimated based on a rule-based algorithm. Experimental results show that it can perform better than other methods in terms of positioning accuracy and ease of implementation. Second, as nearly all existing positioning techniques require training (e.g., training of the parameters of a signal propagation model or building a fingerprint database), they are not easy to implement especially for large-scale implementation. To address this problem, a decentralized and collaborative positioning protocol is proposed by modifying the BLE broadcasting packets. The benefit is that it does not require training before deployment and on-the-fly training can be done by the anchor nodes. Experiments show that the collaborative protocol can achieve good accuracy, and more importantly, it is adaptive to environmental changes. | en_US |
| dcterms.abstract | Third, to develop system/software prototypes for testing indoor positioning algorithms, time consuming development efforts are often required. In fact, positioning algorithms can be decomposed into small sub-components and many of them have common components. Therefore, a component-based positioning development framework is proposed to provide an effective way to share these components to minimize the development efforts. With the prototype built using MIT App Inventor, components are shareable and reusable. This allows others to focus on implementing their core algorithms. This approach facilitates the comparison of different algorithms as they are developed under a common framework, and also testing each component by mixing-and-matching with other components to assess the effectiveness. Fourth, there have been considerable interests in studying social distancing-related research and applications (e.g., in relation to COVID-19) in recent years. To contribute to this important development, BLE-based distancing/- positioning methods with machine learning have been investigated. While previous work on BLE typically used mean RSSI over aggregated channels, an innovative method of using clustered RSSI data as well as other RSSI-related parameters is proposed for data training purposes. Using these RSSI-based features/parameters for data training, machine learning models are used for distance classification and estimation purposes. Last but not least, a new distancing/positioning paradigm called Mobile Ad-hoc Distancing (MAD) / Positioning (MAP) is proposed and investigated using machine learning. Apart from evaluating various machine learning models, a MAD use case and a MAP use case have also been studied. In particular, an iterative algorithm is proposed to tackle a new collaborative positioning problem. Experimental/simulation results show that machine learning can provide effective and promising methods for supporting MAD/MAP. | en_US |
| dcterms.extent | xix, 174 pages : color illustrations | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2021 | en_US |
| dcterms.educationalLevel | Ph.D. | en_US |
| dcterms.educationalLevel | All Doctorate | en_US |
| dcterms.LCSH | Location-based services | en_US |
| dcterms.LCSH | Wireless localization | en_US |
| dcterms.LCSH | Mobile geographic information systems | en_US |
| dcterms.LCSH | Bluetooth technology | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.accessRights | open access | en_US |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/11503