Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Electrical and Electronic Engineering | en_US |
| dc.creator | Jin, Zihui | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/13906 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | en_US |
| dc.rights | All rights reserved | en_US |
| dc.title | Wireless sensing based passenger counting on public transport vehicles | en_US |
| dcterms.abstract | In recent years, a new type of person recognition system has gained popularity, and researchers are increasingly interested in conducting long-term studies to replace traditional image-based recognition systems. This innovative approach is known as Wireless Sensing-based Passenger Counting on Public Transport Vehicles. The objective of this article is to explore the potential of using Channel State Information (CSI) to achieve wireless sensor-based recognition of the number of people on board a vehicle. Compared to traditional image recognition, wireless sensing offers several advantages, such as enhanced privacy, lower power consumption, and broad applicability. | en_US |
| dcterms.abstract | The study involves four primary steps. The first step is collecting CSI data, which includes multidimensional information related to the propagation of wireless signals in space, such as signal strength and delay. This data is crucial for identifying the presence and movement of individuals within a specific area. The second step is to clean and filter the collected data, removing noise and irrelevant data points to ensure accuracy and usability. Once the data is preprocessed, the third step involves constructing models to analyze and learn from it. These models can include traditional machine learning algorithms, such as support vector machines and decision trees, as well as deep learning techniques, like convolutional neural networks. Model selection depends on the data characteristics and the recognition requirements, optimizing for best performance. | en_US |
| dcterms.abstract | Finally, the trained models are evaluated to determine their accuracy, robustness, and feasibility for real-world applications, followed by a summary of the model's performance under various conditions. Through these steps, this study aims to provide a reliable and efficient solution for passenger recognition using wireless sensing. Compared to image-based recognition, CSI-based recognition not only offers significant privacy benefits but can also operate effectively in challenging conditions, such as low-light or obstructed environments. This approach paves the way for improved automation and intelligence in public transport systems, offering a promising technological alternative. | en_US |
| dcterms.abstract | After a long period of exploration and optimization, we successfully improved the model's accuracy from an initial 15% to over 90%. | en_US |
| dcterms.extent | 1 volume (unpaged) : color illustrations | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2025 | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 8315.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 2.38 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/200/13906