Research on prediction of traffic flow based on GEBF-OSFNN
Efficient transport and communication systems lay the groundwork for Singapore’s urban development. However, growing population, economic and commercial progress, and high number of vehicle ownership licenses have resulted in overcrowding and congestions. Hence, it is imperative to use intelligent s...
Saved in:
| 主要作者: | |
|---|---|
| 其他作者: | |
| 格式: | Final Year Project |
| 語言: | English |
| 出版: |
2019
|
| 主題: | |
| 在線閱讀: | http://hdl.handle.net/10356/78251 |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 機構: | Nanyang Technological University |
| 語言: | English |
| 總結: | Efficient transport and communication systems lay the groundwork for Singapore’s urban development. However, growing population, economic and commercial progress, and high number of vehicle ownership licenses have resulted in overcrowding and congestions. Hence, it is imperative to use intelligent systems to analyse, predict and control traffic, saving resources. Intelligent transport system (ITS) was invented that monitors and collects traffic data using surveillance devices and processes that data to help curb congestion and avoid accidents. As the backbone of ITS, traffic guidance systems rely heavily on accurate prediction of traffic flow. Hence, traffic flow prediction has been an important research subject. In this project, chaos theory, and Generalised Ellipsoidal Basis Function Based Online Self-Constructing Fuzzy Neural Network (GEBF-OSFNN) is adopted to predict short-term traffic flow. The proposed technique will facilitate traffic analysis and prediction capabilities as well as provide a comprehensive platform for traffic management solutions. |
|---|