| Author: | Yang, Fan |
| Title: | Consumer behavior analysis based on smartphone sensory data using mobile augmented reality framework |
| Advisors: | Chan, C. C. Keith (COMP) |
| Degree: | Eng.D. |
| Year: | 2020 |
| Subject: | Consumer behavior Smartphones -- Social aspects Retail trade -- Management Hong Kong Polytechnic University -- Dissertations |
| Department: | Faculty of Engineering Department of Computing |
| Pages: | xiv, 119 pages : color illustrations |
| Language: | English |
| Abstract: | Consumer behavior analysis (CBA) is concerned with understanding how consumer cognitive processes influence consumer decision making, choices, and behavior which plays an important role in intelligent retail system (IRS). The complexity of off-line CBA arises from many challenges such as insufficient features of consumer personas. In today's "new retail" economy, innovative solutions of smart technologies in retail settings has started catching the attention of scholars and practitioners. In particular, the usage of smartphone sensory data within augmented reality (AR) technology allows retailers to provide superior consumers' experiences and achieve increased business profitability. Aims to infer consumer preference in retailing, we study on sensing retail context and present a context-aware model called UTLIP to execute the CBA process. Base on the CBA engine, we develop an innovative system named "Easy Buy" by combining the latest mobile technologies with AR framework to capture personas labels in real-time and use the system to analyze consumer behavior in retail environments. To achieve the precise personalized recommendation goal on "Easy Buy", three key technologies are implemented: indoor positioning, mobile AR implementing and consumer behavior modeling. Preliminary evaluation indicates that the precision of indoor localization of our approach is less than 0.2 meter on average in corridor environments. Test results also indicate that the proposed scene mapping RP matching rates is over 80% and average error distances for pose estimation is within 1 meter in our mobile AR framework. Finally, we have successfully achieved the accurate personalized recommendation result via UTLIP model with a recognition accuracy rate of 91.5%. |
| Rights: | All rights reserved |
| Access: | restricted access |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 5111.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 4.62 MB | Adobe PDF | View/Open |
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/200/10673