| Floating Car Data Based Nonparametric Regression Model for Short-Term Travel Speed Prediction |
| |
| 引用本文： | 翁剑成 扈中伟 于泉 任福田. Floating Car Data Based Nonparametric Regression Model for Short-Term Travel Speed Prediction[J]. 西南交通大学学报(英文版), 2007, 15(3): 223-230 |
| |
| 作者姓名： | 翁剑成 扈中伟 于泉 任福田 |
| |
| 作者单位： | Beijing Key Lab of Traffic Engineering Beijing University of Technology，Beijing Key Lab of Traffic Engineering，Beijing University of Technology，Beijing Key Lab of Traffic Engineering，Beijing University of Technology，Beijing Key Lab of Traffic Engineering，Beijing University of Technology，Beijing 100022，China，Beijing 100022，China，Beijing 100022，China，Beijing 100022，China |
| |
| 基金项目： | Foundation items The Project of Research on Technology and Devices for Traffic Guidance （ Vehicle Navigation） System of Beijing Municipal Commission of Science and Technology （No. H030630340320 ） and the Project of Research on the Intelligence Traffic Information Platform of Beijing Education Committee |
| |
| 摘 要： | A K-nearest neighbor (K-NN) based nonparametric regression model was proposed to predict travel speed for Beijing expressway. By using the historical traffic data collected from the detectors in Beijing expressways, a specically designed database was developed via the processes including data filtering, wavelet analysis and clustering. The relativity based weighted Euclidean distance was used as the distance metric to identify the K groups of nearest data series. Then, a K-NN nonparametric regression model was built to predict the average travel speeds up to 6 min into the future. Several randomly selected travel speed data series, collected from the floating car data (FCD) system, were used to validate the model. The results indicate that using the FCD, the model can predict average travel speeds with an accuracy of above 90%, and hence is feasible and effective.
|
| 关 键 词： | 悬浮汽车 智能运输系统 非参数衰退 近邻 |
| 文章编号： | 1005-2429（2007）03-0223-08 |
| 修稿时间： | 2006-12-29 |
Floating Car Data Based Nonparametric Regression Model for Short-Term Travel Speed Prediction |
| |
| WENG Jian-cheng,HU Zhong-wei,YU Quan,REN Fu-tian. Floating Car Data Based Nonparametric Regression Model for Short-Term Travel Speed Prediction[J]. Journal of Southwest Jiaotong University, 2007, 15(3): 223-230 |
| |
| Authors: | WENG Jian-cheng HU Zhong-wei YU Quan REN Fu-tian |
| |
| Affiliation: | Beijing Key Lab of Traffic Engineering, Beijing University of Technology, Beijing 100022, China |
| |
| Abstract: | A K-nearest neighbor (K-NN) based nonparametric regression model was proposed to predict travel speed for Beijing expressway. By using the historical traffic data collected from the detectors in Beijing expressways, a specically designed database was developed via the processes including data filtering, wavelet analysis and clustering. The relativity based weighted Euclidean distance was used as the distance metric to identify the K groups of nearest data series. Then, a K-NN nonparametric regression model was built to predict the average travel speeds up to 6 min into the future. Several randomly selected travel speed data series, collected from the floating car data (FCD) system, were used to validate the model. The results indicate that using the FCD, the model can predict average travel speeds with an accuracy of above 90%, and hence is feasible and effective. |
| |
| Keywords: | K-Nearest neighbor Short-term prediction Travel speed Nonparametric regression Intelligence transportation system (ITS) Floating car data (FCD) |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
