# XGBoost-DNN Mixed Model for Predicting Driver’s Estimation on the Relative Motion States during Lane-Changing Decisions: A Real Driving Study on the Highway

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Description of Algorithms

#### 2.1. Description of XGBoost Algorithm

#### 2.2. Description of DNN Model

#### 2.3. XGBoost-DNN Mixed Algorithm Model

## 3. Study Implementation

#### 3.1. Participants

#### 3.2. Apparatus and Experimental Route

#### 3.3. Experimental Design and Procedure

#### 3.4. Variables Definition

## 4. Statistical Analysis Results

#### 4.1. Analysis of Relative Distance Estimation Error

#### 4.1.1. General Analysis

#### 4.1.2. Ridge Regression Analysis

#### 4.2. Analysis of Target Vehicle Speed Estimation Error

#### 4.2.1. General Analysis

#### 4.2.2. Ridge Regression Analysis

## 5. Modeling of Relative Distance and Velocity Estimation

#### 5.1. Model Construction

#### 5.1.1. Model Label Settings

#### 5.1.2. Model Parameter Settings

#### 5.2. Model Evaluation

#### 5.2.1. Model Evaluation Methods

#### 5.2.2. Model Evaluation Results

## 6. Discussion

## 7. Conclusions and Future Work

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Data Availability Statement

## Conflicts of Interest

## References

- Liu, X.; Jin, G.; Wang, Y.; Yin, C. A Deep Learning-based Approach to Line Crossing Prediction for Lane Change Maneuver of Adjacent Target Vehicles. In Proceedings of the 2021 IEEE International Conference on Mechatronics (ICM), Kashiwa, Japan, 7–9 March 2021; pp. 1–6. [Google Scholar]
- Sun, D.; Elefteriadou, L. Lane-Changing Behavior on Urban Streets: An “In-Vehicle” Field Experiment-Based Study. Comput.-Aided Civ. Infrastruct. Eng.
**2012**, 27, 525–542. [Google Scholar] [CrossRef] - Wang, J.R.K. IVHS/Crash Avoidance Countermeasure Targe. In Proceedings of the Safety & Human Factors Session of 1993 IVHS America Annual Meeting, Santa Monica, CA, USA, 14–17 April 1993. [Google Scholar]
- Risto, M.; Martens, M.H. Driver headway choice: A comparison between driving simulator and real-road driving. Transp. Res. Part F Traffic Psychol. Behav.
**2014**, 25, 1–9. [Google Scholar] [CrossRef] - Eberhard, C.D.; Luebkemann, K.M.; Moffa, P.J.; Young, S.K.; Allen, R.W.; Harwin, E.A.; Keating, J.; Mason, R. Development Of Performance Specifications for Collision Avoidance Systems for Lane Change, Merging and Backing, Task 1—Interim Report: Crash Problem Analysis; National Highway Traffic Safety Administration: Washington, DC, USA, 1995.
- Shawky, M. Factors affecting lane change crashes. IATSS Res.
**2020**, 44, 155–161. [Google Scholar] [CrossRef] - Peng, J.; Guo, Y.; Fu, R.; Yuan, W.; Wang, C. Multi-parameter prediction of drivers’ lane-changing behaviour with neural network model. Appl. Ergon.
**2015**, 50, 207–217. [Google Scholar] [CrossRef] - Yan, F.; Eilers, M.; Baumann, M.; Luedtke, A. Development of a Lane Change Assistance System Adapting to Driver’s Uncertainty During Decision-Making. In Proceedings of the Adjunct 8th International Conference on Automotive User Interfaces and Interactive Vehicular Applications, Ann Arbor, MI, USA, 24–26 October 2016; pp. 93–98. [Google Scholar]
- Milanés, V.; Alonso, J.; Bouraoui, L.; Ploeg, J. Cooperative Maneuvering in Close Environments Among Cybercars and Dual-Mode Cars. IEEE Trans. Intell. Transp. Syst.
**2011**, 12, 15–24. [Google Scholar] [CrossRef] [Green Version] - Wang, C.; Sun, Q.; Guo, Y.; Fu, R.; Yuan, W. Improving the User Acceptability of Advanced Driver Assistance Systems Based on Different Driving Styles: A Case Study of Lane Change Warning Systems. IEEE Trans. Intell. Transp. Syst.
**2020**, 21, 4196–4208. [Google Scholar] [CrossRef] - Chen, C.; Lü, N.; Liu, L.; Pei, Q.-Q.; Li, X.-J. Critical safe distance design to improve driving safety based on vehicle-to-vehicle communications. J. Cent. South Univ.
**2013**, 20, 3334–3344. [Google Scholar] [CrossRef] - Hidas, P. Modelling lane changing and merging in microscopic traffic simulation. Transp. Res. Part C Emerg. Technol.
**2002**, 10, 351–371. [Google Scholar] [CrossRef] - Qiu, T. Research on Learning Based Lane Keeping and Lane Changing Behaviors of Intelligent Vehicle. Master’s Thesis, Beijing University of Technology, Beijing, China, 2019. [Google Scholar]
- Xu, B.; Liu, X.; Wang, Z.; Liu, F.; Liang, J. Fusion decision model for vehicle lane change with Fusion decision model for vehicle lane change with. J. Zhejiang Univ.
**2019**, 53, 1171–1181. [Google Scholar] [CrossRef] - Shi, C. Analysis of Driving Suitability of Novice Drivers. China Saf. Sci. J.
**2013**, 23, 20–26. [Google Scholar] [CrossRef] - Shi, C.; Ou, J.; Cao, J. Analysis of psychological and physiological characteristics of people with bad driving behavior. Chin. J. Ergon.
**2013**, 19, 56–59. [Google Scholar] [CrossRef] - Snowden, R.J.; Stimpson, N.; Ruddle, R.A. Speed perception fogs up as visibility drops. Nature
**1998**, 392, 450. [Google Scholar] [CrossRef] [PubMed] - Sokolov, A.N.; Ehrenstein, W.H.; Pavlova, M.A.; Cavonius, C.R. Motion Extrapolation and Velocity Transposition. Perception
**1997**, 26, 875–889. [Google Scholar] [CrossRef] [PubMed] - DeLucia, P.R. Effects of Size on Collision Perception and Implications for Perceptual Theory and Transportation Safety. Curr. Dir. Psychol. Sci.
**2013**, 22, 199–204. [Google Scholar] [CrossRef] - Wu, C.; Yu, D.; Doherty, A.; Zhang, T.; Kust, L.; Luo, G. An investigation of perceived vehicle speed from a driver’s perspective. PLoS ONE
**2017**, 12, e0185347. [Google Scholar] [CrossRef] [PubMed] [Green Version] - Sun, R.; Zhuang, X.; Wu, C.; Zhao, G.; Zhang, K. The estimation of vehicle speed and stopping distance by pedestrians crossing streets in a naturalistic traffic environment. Transp. Res. Part F Traffic Psychol. Behav.
**2015**, 30, 97–106. [Google Scholar] [CrossRef] - Yan, B.; Chen, H.; Wei, J. Influence of Drivers’ Perceptual Features on Traffic Safety in Tunnel Group. China Saf. Sci. J.
**2011**, 21, 16–21. [Google Scholar] [CrossRef] - Peng, J. Drivers Lane Change Intent Identification Based on Visual Characteristics and Vehicles’ Relative Movements. Ph.D. Thesis, Changan University, Xian, China, 2012. [Google Scholar]
- Haglund, M.; Åberg, L. Speed choice in relation to speed limit and influences from other drivers. Transp. Res. Part F Traffic Psychol. Behav.
**2000**, 3, 39–51. [Google Scholar] [CrossRef] - Michaels, R.M. Perceptual Factors in Car-Following. In Proceedings of the 2nd International Symposium on the Theory of Road Traffic Flow, London, UK, 25–27 June 1963; pp. 44–59. [Google Scholar]
- Kang, G. The Study of Driver’s Space Distance Judgment on Ground Dynamic Environment. Master’s Thesis, Changan University, Xian, China, 2005. [Google Scholar]
- Wei, J.; Zhao, W.; Baolin, X. Effects of different factors on visual cognition distance of drivers at night. China Saf. Sci. J.
**2013**, 23, 21–27. [Google Scholar] [CrossRef] - Chen, T.; Guestrin, C. XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 13–17 August 2016; pp. 785–794. [Google Scholar]
- Xu, Y.; Zhao, X.; Chen, Y.; Yang, Z. Research on a Mixed Gas Classification Algorithm Based on Extreme Random Tree. Appl. Sci.
**2019**, 9, 1728. [Google Scholar] [CrossRef] [Green Version] - Wang, K.; Xue, Q.; Xing, Y.; Li, C. Improve Aggressive Driver Recognition Using Collision Surrogate Measurement and Imbalanced Class Boosting. J. Environ. Res. Public Health
**2020**, 17, 2375. [Google Scholar] [CrossRef] [PubMed] [Green Version] - Wang, X.; Wang, L.; Wang, S.; Chen, J.-F.; Wu, C. An XGBoost-enhanced fast constructive algorithm for food delivery route planning problem. Comput. Ind. Eng.
**2021**, 152, 107029. [Google Scholar] [CrossRef] - Krizhevsky, A.; Sutskever, I.; Hinton, G.E. ImageNet classification with deep convolutional neural networks. In Proceedings of the 25th International Conference on Neural Information Processing Systems, Lake Tahoe, NV, USA, 3–6 December 2012; Volume 1, pp. 1097–1105. [Google Scholar]
- Song, K.; Yan, F.; Ding, T.; Gao, L.; Lu, S. A steel property optimization model based on the XGBoost algorithm and improved PSO. Comput. Mater. Sci.
**2020**, 174, 109472. [Google Scholar] [CrossRef] - Toshev, A.; Szegedy, C. DeepPose: Human Pose Estimation via Deep Neural Networks. In Proceedings of the 27th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA, 23–28 June 2014; pp. 1653–1660. [Google Scholar]
- Wang, S.H.; Mo, B.C.; Zhao, J.H. Deep neural networks for choice analysis: Architecture design with alternative-specific utility functions. Transp. Res. Part C-Emerg. Technol.
**2020**, 112, 234–251. [Google Scholar] [CrossRef] - Hoerl, A.E.; Kennard, R.W. Ridge regression: Biased estimation for nonorthogonal problems. Technometrics
**2000**, 42, 80–86. [Google Scholar] [CrossRef] - Whittaker, J.C.; Thompson, R.; Denham, M.C. Marker-assisted selection using ridge regression. Genet. Res.
**2000**, 75, 249–252. [Google Scholar] [CrossRef] - Zhang, R.; McDonald, G.C. Characterization of ridge trace behavior. Commun. Stat.-Theory Methods
**2005**, 34, 1487–1501. [Google Scholar] [CrossRef] - Fawcett, T. An introduction to ROC analysis. Pattern Recognit. Lett.
**2006**, 27, 861–874. [Google Scholar] [CrossRef] - Stehman, S.V. Selecting and interpreting measures of thematic classification accuracy. Remote Sens. Environ.
**1997**, 62, 77–89. [Google Scholar] [CrossRef] - Tharwat, A. Classification assessment methods. Appl. Comput. Inform.
**2021**, 17, 168–192. [Google Scholar] [CrossRef] - Zhang, H.; Guo, Y.; Wang, C.; Fu, R. Stacking-based ensemble learning method for the recognition of the preceding vehicle lane-changing manoeuvre: A naturalistic driving study on the highway. IET Intell. Transp. Syst.
**2022**, 16, 489–503. [Google Scholar] [CrossRef] - Nwadiuto, J.C.; Yoshino, S.; Okuda, H.; Suzuki, T. Variable Selection and Modeling of Drivers’ Decision in Overtaking Behavior Based on Logistic Regression Model With Gazing Information. IEEE Access
**2021**, 9, 127672–127684. [Google Scholar] [CrossRef] - Ding, J.; Bar-Joseph, Z. MethRaFo: MeDIP-seq methylation estimate using a Random Forest Regressor. Bioinformatics
**2017**, 33, 3477–3479. [Google Scholar] [CrossRef] [PubMed] - Yang, X.; Yu, Q.; He, L.; Guo, T. The one-against-all partition based binary tree support vector machine algorithms for multi-class classification. Neurocomputing
**2013**, 113, 1–7. [Google Scholar] [CrossRef] - Madzarov, G.; Gjorgjevikj, D.; Chorbev, I. A Multi-class SVM Classifier Utilizing Binary Decision Tree. Informatica
**2009**, 33, 225–233. [Google Scholar] [CrossRef] - Zhou, R.S.; Wang, Z.J. A Review of a Text Classification Technique: K-Nearest Neighbor. In Proceedings of the International Conference on Computer Information Systems and Industrial Applications (CISIA), Bangkok, Thailand, 28–29 June 2015; pp. 453–455. [Google Scholar]
- Ma, X.L.; Ding, C.; Luan, S.; Wang, Y.; Wang, Y.P. Prioritizing Influential Factors for Freeway Incident Clearance Time Prediction Using the Gradient Boosting Decision Trees Method. IEEE Trans. Intell. Transp. Syst.
**2017**, 18, 2303–2310. [Google Scholar] [CrossRef] - Zheng, H.T.; Yuan, J.B.; Chen, L. Short-Term Load Forecasting Using EMD-LSTM Neural Networks with a Xgboost Algorithm for Feature Importance Evaluation. Energies
**2017**, 10, 1168. [Google Scholar] [CrossRef] [Green Version] - Wang, C.; Fu, R.; Zhang, Q. Speed estimation model during lane-changing decision. J. Traffic Transp. Eng.
**2015**, 16, 83–91. [Google Scholar] [CrossRef]

**Figure 6.**The experiment of relative distance and speed estimation by the participant driving subject vehicle S to the target vehicle T at the rear of the target lane.

**Figure 7.**Distribution of target vehicle motion and position parameters during relative distance estimation task.

**Figure 9.**The weights of the effects of each analytical variable on the error of distance estimation.

**Figure 10.**Distribution of target vehicle motion and position parameters during relative speed estimation task.

**Figure 13.**Evaluation results of different algorithms in two-classifications. (

**a**) Speed estimation prediction model; (

**b**) distance estimation prediction model.

**Figure 14.**ROC curves of the prediction models. (

**a**) Speed estimation prediction model; (

**b**) distance estimation prediction model.

**Figure 15.**Evaluation results of different algorithms in three-classifications. (

**a**) Speed estimation prediction model; (

**b**) distance estimation prediction model.

Participant ID | Gender | Age | Driving Experience |
---|---|---|---|

01 | male | 29 | 4 |

02 | male | 29 | 4 |

03 | male | 28 | 3 |

04 | male | 27 | 3 |

05 | male | 28 | 4 |

06 | male | 48 | 21 |

07 | male | 34 | 7 |

08 | male | 36 | 10 |

09 | female | 42 | 15 |

10 | male | 38 | 8 |

11 | male | 36 | 7 |

12 | male | 48 | 23 |

13 | female | 31 | 4 |

14 | male | 32 | 5 |

Class | Hyperparameter | Search Range | Model | Optimal Value | |
---|---|---|---|---|---|

2-class | XGBoost | Learning rate | [0.01, 0.5] | Speed | 0.08 |

Distance | 0.07 | ||||

Max tree depth | [2, 10] | Speed | 5 | ||

Distance | 4 | ||||

Minimum loss reduction | [0, 5] | Speed | 0 | ||

Distance | 0 | ||||

Number of estimators | [20, 150] | Speed | 55 | ||

Distance | 64 | ||||

DNN | Hidden layer sizes | Speed | (100,) | ||

Distance | (100) | ||||

Learning rate | [0.001, 0.1] | Speed | 0.001 | ||

Distance | 0.001 | ||||

Activation | Relu, tanh, Logistic | Speed | Relu | ||

Distance | Relu | ||||

Solver | SGD, Adam | Speed | SGD | ||

Distance | SGD | ||||

Number of iterations | Speed | 200 | |||

Distance | 200 | ||||

Batchsize | Speed | Auto | |||

Distance | Auto | ||||

3-class | XGBoost | Learning rate | [0.01, 0.5] | Speed | 0.05 |

Distance | 0.05 | ||||

Max tree depth | [2, 10] | Speed | 6 | ||

Distance | 6 | ||||

Minimum loss reduction | [0, 5] | Speed | 0 | ||

Distance | 0 | ||||

Number of estimator | [20, 150] | Speed | 67 | ||

Distance | 73 | ||||

DNN | Hidden layer sizes | Speed | (100) | ||

Distance | (100) | ||||

Learning rate | [0.001, 0.1] | Speed | 0.001 | ||

Distance | 0.001 | ||||

Activation | Relu, tanh, Logistic | Speed | Relu | ||

Distance | Relu | ||||

Solver | SGD, Adam | Speed | SGD | ||

Distance | SGD | ||||

Number of iterations | Speed | 200 | |||

Distance | 200 | ||||

Batchsize | Speed | Auto | |||

Distance | Auto |

Confusion matrix | Predicted values (Model prediction outcome) | ||

Overestimation (Positive) | Underestimation (Negative) | ||

True values (Driver’s estimation outcome) | Overestimation (Positive) | True Positive (TP) | False Negative (FN) |

Underestimation (Negative) | False Positive (FP) | True Negative (TN) |

Algorithm | Speed Estimation | Distance Estimation | ||||||
---|---|---|---|---|---|---|---|---|

Acc (%) | P | R | F1 | Acc (%) | P | R | F1 | |

RF | 75.32 | 75.38 | 74.90 | 75.01 | 78.83 | 81.32 | 78.44 | 78.23 |

SVM | 69.23 | 69.07 | 68.94 | 68.98 | 68.37 | 69.08 | 68.07 | 67.83 |

LR | 73.08 | 72.96 | 73.03 | 72.99 | 68.37 | 68.34 | 68.32 | 68.32 |

KNN | 76.92 | 76.89 | 76.62 | 76.71 | 73.23 | 73.78 | 73.01 | 72.94 |

DNN | 75.96 | 76.85 | 76.55 | 75.94 | 72.26 | 72.42 | 72.36 | 72.25 |

GDBT | 85.58 | 85.64 | 85.35 | 85.45 | 86.62 | 86.64 | 86.58 | 86.60 |

XGBoost | 88.78 | 88.83 | 88.61 | 88.70 | 90.51 | 90.54 | 90.47 | 90.50 |

XGBoost-DNN | 91.03 | 91.02 | 90.94 | 90.72 | 92.46 | 92.45 | 92.48 | 92.46 |

Algorithm | Speed Estimation | Distance Estimation | ||||||
---|---|---|---|---|---|---|---|---|

Acc (%) | P | R | F1 | Acc (%) | P | R | F1 | |

RF | 68.27 | 75.33 | 57.08 | 59.94 | 65.21 | 74.56 | 58.83 | 56.55 |

SVM | 63.78 | 68.26 | 51.32 | 53.21 | 51.82 | 36.42 | 41.88 | 36.64 |

LR | 63.46 | 62.31 | 56.32 | 58.24 | 55.72 | 60.28 | 49.08 | 47.89 |

KNN | 63.46 | 62.51 | 56.87 | 58.61 | 62.77 | 65.02 | 57.09 | 57.66 |

DNN | 65.06 | 67.40 | 55.93 | 58.85 | 61.31 | 64.51 | 57.49 | 56.62 |

GDBT | 80.13 | 79.72 | 78.00 | 78.78 | 78.10 | 80.10 | 75.49 | 76.97 |

XGBoost | 85.25 | 84.66 | 84.42 | 84.44 | 86.62 | 87.76 | 85.07 | 86.03 |

XGBoost-DNN | 87.18 | 88.05 | 85.05 | 86.39 | 87.59 | 87.85 | 87.00 | 87.38 |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2022 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 (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Zhao, C.; Zhao, X.; Li, Z.; Zhang, Q.
XGBoost-DNN Mixed Model for Predicting Driver’s Estimation on the Relative Motion States during Lane-Changing Decisions: A Real Driving Study on the Highway. *Sustainability* **2022**, *14*, 6829.
https://doi.org/10.3390/su14116829

**AMA Style**

Zhao C, Zhao X, Li Z, Zhang Q.
XGBoost-DNN Mixed Model for Predicting Driver’s Estimation on the Relative Motion States during Lane-Changing Decisions: A Real Driving Study on the Highway. *Sustainability*. 2022; 14(11):6829.
https://doi.org/10.3390/su14116829

**Chicago/Turabian Style**

Zhao, Chen, Xia Zhao, Zhao Li, and Qiong Zhang.
2022. "XGBoost-DNN Mixed Model for Predicting Driver’s Estimation on the Relative Motion States during Lane-Changing Decisions: A Real Driving Study on the Highway" *Sustainability* 14, no. 11: 6829.
https://doi.org/10.3390/su14116829