# Predicting Freeway Travel Time Using Multiple- Source Heterogeneous Data Integration

^{1}

^{2}

^{3}

^{*}

## Abstract

**:**

## 1. Introduction

- Diverse influencing factors such as weather, holidays, traffic accidents, out of sample prediction, and mechanisms contributing to congestion. It is difficult to describe and predict the influence mechanism by using traditional conventional mathematical models.
- The complexity and incompleteness of basic data. Although many flow detectors and video detection equipment are on the freeway, captured data are incompatible, redundant, and include error or loss. To avoid these, techniques that use multi-source data to improve the accuracy of travel time prediction are extremely important.

#### 1.1. Overview of Prediction Method of Single Source Data

#### 1.2. Overview of Prediction Method of Multiple Source Data

- The method pays attention to machine learning algorithms and does not consider the characteristics of the traffic flow, resulting in uncoordinated and unsuitable correspondence between the data and the traffic flow.
- As big data updates continuously, it provides conditions for traffic travel time prediction; however, some advantages and characteristics of these data are not captured, and a great deal of useful data are not being used and mined.
- Some model parameter calibrations are too subjective, which largely depends on the researchers’ experiences.
- Some models are too specific examples and cannot be easily adapted to other situations.

## 2. Data Collection and Preprocessing

#### 2.1. Data Description

- Toll data of all toll stations along G5513 in February 2018 (vehicles entering and leaving toll station), with a total of 561,081 data items, including the name of the toll station, the time of vehicle entering and leaving the toll station, vehicle type and weight.
- Weather data of Meteorology monitoring stations, which was collected from the Chinese Weather Network in February 2018, with a total of 672 data items, including 24 h daily weather, temperature, relative humidity, precipitation, and wind direction.
- Freeway blockage record statistics, which was obtained from the freeway’s management department, a total of 260 freeway blockage information reports were collected in February, March, April, and May, including blockage location, reasons for the blockage, blockage start time, and blockage end time.
- Freeway traffic control measures report, which was obtained from the Traffic Police Department, with a total of seven data items collected on 5 April Qingming Traditional National Festival, May 1 International Labor Day, and other holiday control information.

#### 2.2. Data Preprocessing

## 3. Support Vector Machine Model

#### 3.1. Problem Descriptionof Freeway Travel Time Prediction

#### 3.2. Model Overview

#### 3.3. Model Construction

#### 3.4. Parameter Calibration and Optimization

**C**, which is also called Upper Bound, which denotes the upper bound function. However, existing studies mainly adopted the traditional grid search method, direct determination method, one-dimensional search method, and inverse ratio method to determine the insensitive loss function parameter ε and penalty parameter

**C**. However, there are many shortcomings associated with these methods, and the resulting errors will significantly influence the accuracy of the prediction results.

## 4. Case Study

#### 4.1. Data Selection

#### 4.2. Results and Comparative Analysis

#### 4.3. Analysis of Influencing Factors of Travel Time

#### 4.3.1. Effect of Traffic Accidents on Travel Time

#### 4.3.2. Effect of Holidays on Travel Time

## 5. Conclusions

## Author Contributions

## Funding

## Acknowledgments

## Conflicts of Interest

## References

- Gipps, P.G. The Estimation of a Measure of Vehicle Delay from Detector Output; Newcastle-Upon-Tyne University: Northumberland, UK, 1977; pp. 1–18. [Google Scholar]
- Yildirimoglu, M.; Geroliminis, N. Experienced travel time prediction for congested freeways. Transp. Res. Part B Method
**2013**, 53, 45–63. [Google Scholar] [CrossRef] [Green Version] - Shen, L.; Hadi, M. Practical approach for travel time estimation from point traffic detector data. J. Adv. Transp.
**2013**, 47, 526–535. [Google Scholar] [CrossRef] - Hyun, K.; Tok, A.; Ritchie, S.G. Long distance truck tracking from advanced point detectors using a selective weighted Bayesian model. Transp. Res. Part C Emerg. Technol.
**2016**, 82, 24–42. [Google Scholar] [CrossRef] - Hyun, K.K.; Jeong, K. Assessing crash risk considering vehicle interactions with trucks using point detector data. Accid. Anal. Prev.
**2018**. [Google Scholar] [CrossRef] [PubMed] - Ramezani, M.; Geroliminis, N. On the estimation of arterial route travel time distribution with Markov chains. Transp. Res. Part B
**2012**, 46, 1576–1590. [Google Scholar] [CrossRef] [Green Version] - Zhang, J.T.; Zhou, J. An Arterial Travel Time Estimation Model Based on Discrete Time Markov Chains. Syst. Eng.
**2014**, 5, 98–104. [Google Scholar] [CrossRef] - Zhang, J.T.; Zhou, J. Travel time estimation model based on spatial Markov chains. Syst. Eng.
**2015**, 12, 72–77. [Google Scholar] - Woodard, D.; Nogin, G. Predicting travel time reliability using mobile phone GPS data. Transp. Res. Part C Emerg. Technol.
**2017**, 75, 30–44. [Google Scholar] [CrossRef] - Bahuleyan, H.; Vanajakshi, L.D. Arterial path-level travel-time estimation using machine-learning techniques. J. Comput. Civ. Eng.
**2016**, 31, 04016070. [Google Scholar] [CrossRef] - Zhou, X.; Liu, Z.; Zhao, X.X.; Guo, J.H. Framework for dynamic od matrix estimation based on multi-source traffic data fusion. Appl. Mech. Mater.
**2014**, 505–506, 1153–1156. [Google Scholar] [CrossRef] - Chu, D.; Sheets, D.A.; Zhao, Y.; Wu, Y.; Zheng, M.; Chen, G.; Yang, J. Visualizing hidden themes of Taxi Movement with semantic transformation. In Proceedings of the 2014 IEEE Pacific Visualization Symposium, Yokohama, Kanagawa, Japan, 4–7 March 2014; IEEE Computer Society Press: Los Alamitos, CA, USA, 2014; pp. 137–144. [Google Scholar]
- Al-Dohuki, S.; Wu, Y.; Kamw, F. Semantic Traj: A new approach to interacting with massive taxi trajectories. IEEE Trans. Vis. Comput. Gr.
**2017**, 23, 11–20. [Google Scholar] [CrossRef] [PubMed] - Lécué, F.; Tallevi-Diotallevi, S.; Hayes, J.; Tucker, R.; Bicer, V.; Sbodio, M.; Tommasi, P. Smart traffic analytics in the semantic web with STAR-CITY: Scenarios, system and lessons learned in Dublin City. J. Web Semant.
**2014**, 27–28, 26–33. [Google Scholar] [CrossRef] - vanLint, J.W.C. Incremental and online learning through extended kalman filtering with constraint weights for freeway travel time prediction. In Proceedings of the 2006 IEEE Intelligent Transportation Systems Conference, Toronto, ON, Canada, 17–20 September 2006; pp. 1041–1046. [Google Scholar]
- Zhou, J.; Zhang, C.B. Travel Time Prediction Model for Urban Road Network based on Multi-source Data. Procedia Soc. Behav. Sci.
**2014**, 138, 811–818. [Google Scholar] - Chang, T.H.; Chen, A.Y.; Hsu, Y.T.; Yang, C.L. Freeway Travel Time Prediction Based on Seamless Spatio-temporal Data Fusion: Case Study of the Freeway in Taiwan. Transp. Res. Procedia
**2016**, 17, 452–459. [Google Scholar] [CrossRef] - Fei, X.; Lu, C.C. A Bayesian dynamic linear model approach for real-time short-term freeway travel time prediction. Transp. Res. Part C
**2011**, 19, 1306–1318. [Google Scholar] [CrossRef] - Zhan, X.; Ukkusuri, S.V. A Bayesian mixture model for short-term average link travel time estimation using large-scale limited information trip-based data. Autom. Constr.
**2016**, 72, 237–246. [Google Scholar] [CrossRef] - Wosyka, J.; Pribyl, P. Real-time travel time estimation on highways using loop detector data and license plate recognition. In Proceedings of the 2012 Elektro, Žilina-Rajecké Teplice, Slovakia, 21–22 May 2012; pp. 391–394. [Google Scholar]
- Innamaa, S. Short-Term Prediction of Travel Time using Neural Networks on an Interurban Highway. Transportation
**2005**, 32, 649–669. [Google Scholar] [CrossRef] - vanLint, J.W.C.; Hoogendoorn, S.P. Accurate freeway travel time prediction with state-space neural networks under missing data. Transp. Res. Part C
**2005**, 13, 347–369. [Google Scholar] [CrossRef] - Ben-Akiva, M.; Bierlaire, M.; Burton, D.; Koutsopoulos, H.N.; Mishalani, R. Network State Estimation and Prediction for Real-Time Traffic Management. Netw. Spat. Econ.
**2001**, 1, 293–318. [Google Scholar] [CrossRef] - Mahmassani, H.S. Dynamic Network Traffic Assignment and Simulation Methodology for Advanced System Management Applications. Netw. Spat. Econ.
**2001**, 1, 267–292. [Google Scholar] [CrossRef] - Chilà, G.; Musolino, G.; Polimeni, A.; Rindone, C.; Russo, F.; Vitetta, A. Transport models and intelligent transportation system to support urban evacuation planning process. IETIntell. Transp. Syst.
**2016**, 10, 279–286. [Google Scholar] - Alonso, B.; Pòrtilla, Á.I.; Musolino, G.; Rindone, C.; Vitetta, A. Network Fundamental Diagram (NFD) and traffic signal control: First empirical evidences from the city of Santander. Transp. Res. Procedia
**2017**, 27, 27–34. [Google Scholar] [CrossRef] - Wu, C.H.; Ho, J.M. Travel-time prediction with support vector regression. IEEE Trans. Intell. Transp. Syst.
**2004**, 5, 276–281. [Google Scholar] [CrossRef] - Vanajakshi, L.; Rilett, L.R. Support Vector Machine Technique for the Short-Term Prediction of Travel Time. In Proceedings of the 2007 IEEE Intelligent Vehicles Symposium, Istanbul, Turkey, 13–15 June 2007; pp. 600–605. [Google Scholar]
- Mendes-Moreira, J.; Jorge, A.M.; de Sousa, J.F.; Soares, C. Comparing state-of-the-art regression methods for long term travel time prediction. Intell. Data Anal.
**2012**, 16, 427–449. [Google Scholar] [CrossRef] - Wang, X.; Chen, X.H.; Yang, X.M. Short term prediction of expressway travel time based on k nearest neighbor algorithm. Chin. J. Highw. Transp.
**2015**, 28, 102–111. [Google Scholar] - Li, S.; Yuan, Z.C.; Wang, C. Optimization of support vector machine parameters based on group intelligence algorithm. CAAI TIS
**2018**, 13, 70–84. [Google Scholar] - Wang, Q.; Liu, Z.; Peng, Z. A PSO-SVM Model for short-term travel time prediction based on Bluetooth Technology. J. Harbin Inst. Technol.
**2015**, 22, 7–14. [Google Scholar] - Yang, Z.S. Study on the Synthetic Link Travel Time Prediction Model of Key Theory of ITS. J. Traffic Transp. Eng.
**2001**, 1, 65–67. [Google Scholar]

Prediction Method | Author | Data Source |
---|---|---|

Kalman filter | VanLint, J.W.C., 2006 [15] | Travel time data |

Zhou, J., 2014 [16] | Floating vehicle and fixed detector data | |

Chang, T.H., 2016 [17] | Electronic Toll Collection (ETC) and traditional Vehicle Detector data | |

Bayesian estimation | Fei, X., 2011 [18] | The real loop detector data of an I-66 segment in Northern Virginia |

Zhan, X., 2016 [19] | A large-scale taxi trip dataset from New York City | |

Statistical decision theory | Wosyka, J., 2012 [20] | Two detectors data in Prague and also in the Czech Republic. |

Neural network | Innamaa, S., 2005 [21] | Travel time data |

VanLint, J.W.C., 2005 [22] | Travel data and Some missing or corrupt travel data | |

Consolidated behaviormodels | Ben-Akiva, M., 2001 [23] | Origin-Destination flow data |

Mahmassani, H.C., 2001 [24] | O rigin-Destination trip information | |

Chilà, G., 2016 [25] | The flow and the user’s behavior | |

Alonso, B., 2017 [26] | Traffic loops and the signal control plans in Santander urban area |

Toll Station | Start Point | End Point | Distance (km) |
---|---|---|---|

1 | Changsha West | Guanshan | 10.6 |

2 | Changsha West | Ningxiang | 23.2 |

Variable Category | Variable Name | Variable Type | Variable Value | Variable Meaning |
---|---|---|---|---|

Meteorological | Weather status | Discrete | Clear; Cloudy; Fog; Overcast; Light rain; mod rain; hvy rain | Clear; Cloudy; Fog; Overcast; Light rain; mod rain; hvy rain |

Time | Holiday | Discrete | 0 | N |

1 | Y | |||

Weekday | Discrete | 1 … 7 | Monday … Sunday | |

Accident | Traffic accidents | Discrete | 0 | N |

1 | Y |

Section | Penalty Parameter, C | Nuclear Parameter, σ | Insensitive Loss Function Parameter, ε |
---|---|---|---|

Changsha West–Guanshan | 6.8755 | 0.0064 | 0.3461 |

Changsha West–Ningxiang | 8.6485 | 0.0034 | 0.6991 |

Method | Changsha West–Guanshan Station | Changsha West–Ningxiang Station | |||||||
---|---|---|---|---|---|---|---|---|---|

RMSE | L-RMSE | MAPE | CP | RMSE | L-RMSE | MAPE | CP | ||

Weekday | BPNN | 7.6544 | 9.3541 | 5.0873 | 0.5489 | 10.5124 | 11.9621 | 5.5104 | 0.5809 |

SVM | 6.3405 | 8.3952 | 4.8225 | 0.5810 | 9.0375 | 11.6215 | 4.5422 | 0.6930 | |

OSVM | 6.0369 | 8.0369 | 4.6536 | 0.5952 | 8.3069 | 10.6541 | 4.4524 | 0.6404 | |

Weekend | BPNN | 11.6308 | 13.6169 | 9.1023 | 0.5990 | 16.0845 | 16.9551 | 9.6148 | 0.6454 |

SVM | 11.5152 | 13.1510 | 7.8645 | 0.6460 | 13.3215 | 14.4151 | 8.1153 | 0.6905 | |

OSVM | 9.6218 | 11.7411 | 6.2451 | 0.7621 | 12.2548 | 15.0215 | 7.8651 | 0.7245 |

© 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Long, K.; Yao, W.; Gu, J.; Wu, W.; Han, L.D.
Predicting Freeway Travel Time Using Multiple- Source Heterogeneous Data Integration. *Appl. Sci.* **2019**, *9*, 104.
https://doi.org/10.3390/app9010104

**AMA Style**

Long K, Yao W, Gu J, Wu W, Han LD.
Predicting Freeway Travel Time Using Multiple- Source Heterogeneous Data Integration. *Applied Sciences*. 2019; 9(1):104.
https://doi.org/10.3390/app9010104

**Chicago/Turabian Style**

Long, Kejun, Wukai Yao, Jian Gu, Wei Wu, and Lee D. Han.
2019. "Predicting Freeway Travel Time Using Multiple- Source Heterogeneous Data Integration" *Applied Sciences* 9, no. 1: 104.
https://doi.org/10.3390/app9010104