受经济利益驱动，中国高速公路逃费行为频繁发生。为此，该文选取了2020年某研究区域的脱敏通行数据，通过数据挖掘分析逃费车辆的行为特征，提出一种基于递归特征消除算法和OPTUNA优化框架的极限梯度提升树（recursive feature elimination-OPTINA-extreme gradient boosting,RFE-OPTUNA-XGBoost）的逃费模式识别模型，该识别模型准确率达到了0.945，各逃费方式的平均接受者操作特性曲线下面积值（area under curve,AUC）分别为：大车小标0.997、U/J型0.980、假绿通0.969、冲岗0.924。结果证明，基于RFE-OPTUNA-XGBoost的模型对于逃费模式识别的准确程度及各逃费模式的AUC值都更高。综上所述，提出的基于RFE-OPTUNA-XGBoost的高速公路逃费车辆逃费的识别模型能精准识别逃费模式。在实际应用中，对于高速公路管理部门展开稽查工作具有重大现实意义。
Driven by economic benefits, highway toll evasion behavior occurs frequently in China. This study utilizes anonymized toll data from a specific region in 2020 to address this issue. Through data mining to analyze the behavior characteristics of the evading vehicles, we propose a toll evasion pattern recognition model based on RFE-OPTUNA-XGBoost. The accuracy of this recognition model reaches 0.945, with average AUC values for different evasion methods as follows: large vehicle misclassification at 0.997, U/J-turn evasion at 0.980, fake green pass at 0.969, and gate crashing at 0.924. The results demonstrate that the RFE-OPTUNA-XGBoost model achieves higher accuracy in toll evasion pattern recognition and higher AUC values for each evasion method. In summary, the proposed model can accurately identify toll evasion patterns, offering significant practical value for highway management departments in conducting inspections and preventing toll evasion.
[1] 王添碧. 基于历史通行数据的假冒绿通车行为预测与治理措施研究[D]. 成都: 西南交通大学, 2020.
[2] 陈浩泰. 基于Logistic回归的高速公路绿通车稽查研究[D]. 西安: 长安大学, 2017.
[3] 李松江, 周舟, 李岩芳, 等. 基于IGA-IBP算法的高速公路逃费预测[J]. 计算机工程与设计, 2018, 39(12): 3840-3845. Li S J, Zhou Z, Li Y F, et al. Prediction of highway escape cost based on IGA-IBP algorithm [J]. Computer Engineering and Design, 2018, 39(12): 3840-3845. (in Chinese)
[4] 向红艳, 杨朋涛, 伊佳佳. 基于RF-LR的高速公路逃费车辆状态预测模型[J]. 重庆师范大学学报(自然科学版), 2020, 37(1): 75-80. Xiang H Y, Yang P T, Yi J J. State prediction model of expressway escaping vehicles based on RF-LR [J]. Journal of Chongqing Normal University (Natural Science), 2020, 37(1): 75-80. (in Chinese)
[5] 刘昱岗, 郑帅, 徐旭东, 等. 基于历史通行数据的假冒绿通车逃费行为预测[J]. 公路交通科技, 2021, 38(4): 92-102, 141. Liu Y G, Zheng S, Xu X D, et al. Prediction of fraudulent green traffic fare evasion behavior based on historical traffic data [J]. Journal of Highway and Transportation Science and Technology, 2021, 38(4): 92-102, 141. (in Chinese)
[6] 任文龙. 基于神经网络的联网高速公路收费稽查研究[D]. 西安: 长安大学, 2010.
[7] Zhao Y H, Shi H F, Ren X C, et al. A toll evasion recognition method based on Gaussian mixture clustering [J]. Communications in Statistics-Simulation and Computation, 2022, 51(7): 3901-3911.
[8] Wang J S, Zhu R, Li T, et al. ETC-oriented efficient and secure blockchain: credit-based mechanism and evidence framework for vehicle management [J]. IEEE Transactions on Vehicular Technology, 2021, 70(11): 11324-11337.
[9] Yang Y, Wang K, Yuan Z Z, et al. Predicting freeway traffic crash severity using XGBoostBayesian network model with consideration of features interaction [J]. Journal of Advanced Transportation, 2022: 4257865.
[10] 翁小雄, 吕攀龙. 基于GBDT算法的地铁IC卡通勤人群识别[J]. 重庆交通大学学报（自然科学版）, 2019, 38(5): 8-12. Weng X X, Lyu P L. Subway IC card commuter crowd identification based on GBDT algorithm [J]. Journal of Chongqing Jiaotong University (Natural Science), 2019, 38(5): 8-12. (in Chinese)
[11] 何红艳, 黄国言, 张炳, 等. 基于极限树特征递归消除和LightGBM的异常检测模型[J]. 信息网络安全, 2022, 22(1): 64-71. He H Y, Huang G Y, Zhang B, et al. Intrusion detection model based on extra trees-recursive feature elimination and LightGBM [J]. Netinfo Security, 2022, 22(1): 64-71. (in Chinese)
[12] 杨洋, 贺昆, 王云鹏, 等. 面向动态交通流的高速公路事故风险模型空间移植研究[J]. 交通运输系统工程与信息, 2023, 23(3): 174-186. Yang Y, He K, Wang Y P, et al. Spatial transplantation for modeling of freeway traffic crash risk based on dynamic traffic flow [J]. Journal of Transportation Systems Engineering and Information Technology, 2023, 23(3): 174-186. (in Chinese)
[13] 万明, 梁莹, 周涂强, 等. 考虑动态交通信息的异质出行行为分析[J]. 华东交通大学学报, 2022, 39(5): 61-69. Wan M, Liang Y, Zhou T Q, et al. Heterogeneous travel behavior analysis considering dynamic traffic information [J]. Journal of East China Jiaotong University, 2022, 39(5): 61-69. (in Chinese)
[14] 万平, 吴超仲, 马晓凤. 基于ROC曲线和驾驶行为特征的驾驶愤怒强度判别阈值[J]. 吉林大学学报(工学版), 2020, 50(1): 121-131. Wan P, Wu C Z, Ma X F. Discriminating threshold of driving anger intensity based on driving behavior features by ROC curve analysis [J]. Journal of Jilin University (Engineering and Technology Edition), 2020, 50(1): 121-131. (in Chinese)
[15] Biau G. Analysis of a random forests model [J]. Journal of Machine Learning Research, 2014, 13(1): 1063-1095.
