Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Multi-disciplinary Studies | en_US |
| dc.creator | Tsang, King-man | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/4965 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | - |
| dc.rights | All rights reserved | en_US |
| dc.title | A road opening impact assessment system based on artificial neural network | en_US |
| dcterms.abstract | Traffic congestion arising from road openings costs road users millions of dollars every year. Both the Government and the public are keen to derive actions to reduce the incidence of road openings and their duration, and to ameliorate their effects. Starting from 1 January 1995, the Government requires Utility companies to submit traffic impact assessments prior to carrying out road openings at certain busy roads. The aim of the exercise is to assess the degree of disruption of the works to the traffic and to recommend remedial measures if necessary. The traditional way of conducting traffic impact assessment is very complicated and requires a lot of professional knowledge. In view of the large number of road openings happening every day in Hong Kong, it is certainly impractical to conduct such assessment for every single case unless the process can be much simplified. A Road Opening Impact Assessment system based on artificial neural network is proposed to predict the traffic conditions as a result of the road opening. We have constructed and successful trained a 3-layer backpropagation network that could be used to give a broad brushed traffic impact assessment due to road openings. For the purpose of training and testing, two sets of data were generating using the traditional traffic forecast method with the study area restricted to North Point area. The proposed System will simplify the traffic impact assessment procedures. It only requires users to input very simple data and produce fast estimate of the traffic conditions as a result of the road opening. The System use a backpropagation neural network to do the prediction and is implemented on the personal computer platform. The System was applied to a problem domain restricted to the North Point area. Fifty-six training pairs each comprising of one road opening were simulated to train the system and the trained network were tested against ten single road opening pairs and ten multiple road opening pairs. The results are generally acceptable although slight discrepancy was observed for case with multiple road openings which are located close together. The results prove that a Road Opening Impact Assessment System based on artificial road opening can be developed to provide a simple broad brushed tool for assessing the traffic impacts resulting from road openings. The system is fast, easy to use and reasonably accurate, and it does not require professional knowledge to operate. After proper training, the System can be further enhanced and applied to a larger area or another area. | en_US |
| dcterms.extent | iv, 120 leaves : ill., Map ; 30 cm | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 1996 | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.LCSH | Roads -- Maintenance and repair -- Data processing | en_US |
| dcterms.LCSH | Neural networks (Computer science) | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b12249282.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 3.02 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/200/4965