基于随机森林模型的城市非法营运车辆识别

doi:10.16180/j.cnki.issn1007-7820.2024.01.010

摘要/Abstract

摘要：

区域经济社会的快速发展与交通出行的需求发展不匹配,在一定程度上为非法营运车辆提供了市场契机。城市高速公路的ETC(Electronic Toll Collection)数据可有效稽查高速公路的非法营运车辆,从而优化运行秩序并提升管理水平。文中提取ETC数据的有效字段,采用随机森林算法建立非法营运车辆识别分类器,加入CART(Classification and Regression Tree)分类树模型分类器和二元逻辑回归模型分类器与之对比,并以西南某市高速公路自2022年2月6日~2022年3月8日的ETC指标数据进行实证分析。结果表明,随机森林模型分类器比CART分类树模型分类器和二元逻辑回归模型分类器预测效果更好,其准确性高达98.75%。

关键词: 非法营运车辆, 随机森林模型, CART分类树模型, 二元逻辑回归模型, 分类算法, 机器学习, 深度学习, 识别算法

Abstract:

The rapid development of regional economy and society does not match the development of traffic demand, which provides market opportunities for illegal taxi operation. ETC(Electronic Toll Collection) data of urban expressways can effectively check illegal taxi operation on expressways, so as to optimize operation order and improve management level. This study extracts the effective fields of ETC data, uses the random forest algorithm to establish the illegal taxi operation recognition classifier, adds the classifiers of the CART(Classification and Regression Tree) classification tree model and the binary logistic regression model to conduct performance comparison, and makes an empirical analysis with the ETC index data of a highway in a southwest city from February 6, 2022 to March 8, 2022. The results show that performance the random forest model classifier is better than that of the CART classification tree model classifier and the binary logistic regression model classifier, and its accuracy score of the proposed model is 98.75%.

Key words: illegal taxi operation, random forest model, CART classification tree model, binary logistic regression model, classification algorithm, machine learning, deep learning, recognition algorithm

中图分类号:

TP183

黄子璇,李桥兴. 基于随机森林模型的城市非法营运车辆识别[J]. 电子科技, 2024, 37(1): 66-71.

HUANG Zixuan,LI Qiaoxing. Research on Identification of Urban Illegal Vehicles Based on Random Forest Model[J]. Electronic Science and Technology, 2024, 37(1): 66-71.

图/表 8

表1

图1

表2

ETC数据有效字段"

字段	字段名称	定义与说明
OBU_LICENSE	OBU车牌	OBU设备登记绑定的车牌号,用于了解车牌省籍等信息,识别车辆
VEHICLE_CLASS	OBU车辆类型	OBU设备登记绑定车辆的类型,可了解车辆类型,三大主类(客车、货车、专项作业车)、16个亚类
VEHICLE_USER_ TYPE	OBU车辆用户类型	OBU设备登记绑定车辆的用户类型,了解用户类型或身份,如普通、公务车、军警车等,可用于嫌疑车辆排除
EN_TIME	入口时间	车辆通过入口站的时间,可了解车辆入口信息,与出口信息一起了解车辆高速公路上行驶时间等信息,同时嫌疑车辆如若经常从一个站点进入或出站也会增加嫌疑
EN_STATION	入口站	入口收费站的编码,与入口路段一起识别车辆的入口站点,与出口站一起可了解车辆高速公路上的通行里程等
EX_TIME	出口时间	车辆通过出口站的时间,可了解车辆出口信息,与入口信息一起了解车辆高速公路上行驶时间等信息,同时嫌疑车辆如若经常从一个站点进入或出站也会增加嫌疑
EX_STATION	出口站	出口收费站的编码,与出口路段一起识别车辆的出口站点,与入口站一起可了解车辆高速公路上的通行里程等
TRADE_TIME	交易时间	车辆进出口收费站的交易时间,用于了解车辆通行交通量的高峰时段等,也可与入口时间一起判断异常数据
SHIFT_DATE	交易工班日期	车辆进出口收费站的交易日期,可用于了解每天车辆通行的交通量,了解高峰日期与天数等
TRADE_RESULT	交易结果	车辆进出口收费站的交易结果(0.未知;1.交易成功;2.逻辑失败,如无 CPU 卡、挂失、非法拆卸等逻辑原因交易失败;3.物理失败,正常执行写卡等操作但是最终交易失败; 4.无标签(或漏读);5.闯关车),可用于数据清洗时去掉交易失败等数据,便于数据分析更精准;同时可用于了解交易失败的原因,优化收费站点或车道管理

表2

图2

图3

图4

图5

图6

参考文献 23

[1]	梁鹏毅. 建立车脸识别系统查打“遁牌黑车”犯罪研究[J]. 辽宁警察学院学报, 2021, 23(1):9-13.
	Liang Pengyi. Research on fighting the crime of “conceal vehicle license plate” by the car-face recognition management system[J]. Journal of Liaoning Police College, 2021, 23(1):9-13.
[2]	赵光辉. 交通运输行业超限超载与黑车治理困境及突围—来自赏金猎人制度的借鉴[J]. 中国流通经济, 2020, 34(1):112-121.
	Zhao Guanghui. Dilemmas and breakthrough of overload and the “black car” governance system in Chain's transportation industry-the experience from bounty hunters[J]. China Business and Market, 2020, 34(1):112-121.
[3]	刘善清, 朱祎伟. “堵”“疏”结合治理非法营运[J]. 黑龙江人力资源和社会保障, 2022(16):53-55.
	Liu Shanqing, Zhu Yiwei. "Blocking" and "sparing" combined to cure illegal operation[J]. Human Resources and Social Security, 2022(16):53-55.
[4]	杨贺雅, 邢纹硕, 陈聪, 等. 基于随机森林二分类器的模块化多电平换流器子模块开路故障检测方法[J]. 中国电机工程学报, 2023, 43(10):3916-3928.
	Yang Heya, Xing Wenshuo, Chen Cong, et al. A fault d-etection and location strategy for sub-module open-circuit fault in modular multilevel converters based onrandom forest binary classifier[J]. Proceeding of the CSEE, 2023, 43(10):3916-3928.
[5]	魏山森, 梁建芳, 雷钦渊. 基于CART决策树算法的服装可持续消费者画像构建[J]. 丝绸, 2022, 59(9):71-79.
	Wei Shansen, Liang Jianfang, Lei Qinyuan. Portrait construction of sustainable clothing consumers based on CART algorithm[J]. Journal of Silk, 2022, 59(9):71-79.
[6]	杨越佳, 华蓓, 钟志威, 等. 基于同态加密的隐私保护逻辑回归协同计算[J]. 计算机工程, 2023, 49(4):23-31. doi: 10.19678/j.issn.1000-3428.0064391
	Yang Yuejia, Hua Bei, Zhong Zhiwei, et al. Collaborative computing of privacy-preserving logistic regression based on homomorphic encryption[J]. Computer Engineering, 2023, 49(4):23-31. doi: 10.19678/j.issn.1000-3428.0064391
[7]	孙悦, 袁健. 基于Spark的改进随机森林算法[J]. 电子科技, 2019, 32(4):60-63,67.
	Sun Yue, Yuan Jian. Improved random forest algorithm based on Spark[J]. Electronic Science and Technology, 2019, 32(4):60-63,67.
[8]	石玉琳, 刘嘉懿, 胡晓娟, 等. 基于舌脉象数据的决策树算法的非小细胞肺癌证候分类方法[J]. 世界科学技术-中医药现代化, 2022, 24(7):2766-2775.
	Shi Yulin, Liu Jiayi, Hu Xiaojuan, et al. Classification of syndromes of non-small cell lung cancer based on decision tree algorithm based on tongue data and pulse data[J]. Modernization of Traditional Chinese Medicine and Materia Medica-World Science and Technology, 2022, 24(7):2766-2775.
[9]	郑博文, 赵逢禹. 基于决策树分类算法异构数据的索引优化[J]. 电子科技, 2018, 31(3):48-52,60.
	Zheng Bowen, Zhao Fengyu. Optimization for heterogeneous data index based on decision tree classification[J]. Electronic Science and Technology, 2018, 31(3):48-52,60.
[10]	范天程, 贾云飞, 李云飞, 等. 基于遥感影像与逻辑回归模型的延河流域沟壑分布概率预测[J]. 水土保持研究, 2022, 29(4):316-321.
	Fan Tiancheng, Jia Yunfei, Li Yunfei, et al. Prediction of gully distribution probabilit in Yanhe basin based on remote sensin image and logistic regression model[J]. Research of Soil and Water Conservation, 2022, 29(4):316-321.
[11]	Dou Q, Coelho de Castro D, Kamnitsas K, et al. Domain generalization via model-agnostic learning of semantic features[C]. Curran: Advances in Neural Information Processing Systems, 2019:697-705.
[12]	胡雪梅, 蒋慧凤. 具有技术指标的逻辑回归模型预测谷歌股票的涨跌趋势[J]. 系统科学与数学, 2021, 41(3):802-823.
	Hu Xuemei, Jiang Huifeng. Logistic regression model with technical indicators predicts ups and downs for Google stock prices[J]. Journal of Systems Science and Mathematical Sciences, 2021, 41(3):802-823.
	崔静静, 胡泽文, 任萍. 基于决策树和逻辑回归模型的人工智能领域潜在“精品”论文识别研究[J]. 情报科学, 2022, 40(5):90-96.
	Cui Jingjing, Hu Zewen, Ren Ping. Identification of "hidden treasures" among massive literature from artificial intelligence field based on decision tree and logistic regression[J]. Information Science, 2020, 40(5):90-96.
[13]	田晓, 陈锦欢. 治理网约车非法营运乱象的路径探析[J]. 西部交通科技, 2020(5):178-180.
	Tian Xiao, Chen Jinhuan. Analysis on the path to cure the disorder of illegal operation of online car hailing[J]. Western China Communications Science & Technology, 2020(5):178-180.
[14]	雷丽彩, 高尚, 蒋艳. 网约车新政下网约车平台与网约车司机的演化博弈分析[J]. 管理工程学报, 2020, 34(1):55-62.
	Lei Licai, Gao Shang, Jiang Yan. Evolutionary game analysis of car-hailing industry between platforms and drivers based on new policy of car-hailing[J]. Journal of Industrial Engineering and Engineering Management, 2020, 34(1):55-62.
[15]	高宁波, 许文波, 徐兰花. 基于大数据的两客一危全过程安全监管模型及平台[J]. 软件, 2022, 43(1):38-40.
	Gao Ningbo, Xu Wenbo, Xu Lanhua. Safety supervision model and platform for the whole process based on big data[J]. Software, 2022, 43(1):38-40.
[16]	王玉臻. 网约车行政纠纷案件中非法营运的识别与运用[J]. 山西省政法管理干部学院学报, 2020, 33(2):27-29.
	Wang Yuzhen. Identification and application of illegal operation in administrative dispute cases of online car- hailing[J]. Journal of Shanxi Politics and Law Institute for Administrators, 2020, 33(2):27-29.
[17]	陈斌, 叶敬元. 阻断“黑车”黑色经济链[J]. 中国公路, 2021(4):52-54.
	Chen Bin, Ye Jingyuan. Blocking the black economic chain of "black car"[J]. China Highway, 2021(4):52-54.
[18]	Fox V, Poulikakos D. Travel arrangements in hemodialysis patients during the COVID-19 pandemic including London-style "black cabs" for transfer to a designated isolation unit[J]. Hemodialysis International, 2021, 25(4): 563-564. doi: 10.1111/hdi.v25.4
[19]	Katie C, Janet S. Shape of black cab fares badly on route to registration[J]. European Intellectual Property Review, 2018, 40(3):195-199.
[20]	Sacks T. All-electric black cab developer aims to make cities greener[J]. Drives & Controls, 2021(7):37-45.
[21]	马仕玉, 孙承东, 朱家利. SOM神经网络在非法营运车辆识别中的应用[J]. 信息与电脑(理论版), 2017(8):83-85.
	Ma Shiyu, Sun Chengdong, Zhu Jiali. Application of SOM neural network in the identification of illegal operating vehicles[J]. Information & Computer(Theoretical Version), 2017(8):83-85.
[22]	王娜, 段鹏飞, 武林林. 基于卷积神经网络的非法营运车辆识别[J]. 计算机应用, 2016, 36(S2):193-196.
	Wang Na, Duan Pengfei, Wu Linlin. Research of illegal operation vehicle identification based on convolutional neural network[J]. Journal of Computer Applications, 2016, 36(S2):193-196.
[23]	帅丹, 蓝章礼, 李益才. 基于k-mediods及其改进算法的非法营运车辆识别[J]. 计算机应用与软件, 2016, 33(5):154-157,211.
	Shuai Dan, Lan Zhangli, Li Yicai. Recognition illegal operation vehicles based on k-mediods and its improved algorithm[J]. Computer Applications and Software, 2016, 33(5):154-157,211.

特征指标	数据意义	赋值
累计通行天数/天	由ETC通行数据计算某时间段通行总天数
累计通行次数/次	由ETC通行数据计算某时间段通行总次数
单次平均通行时间/min	为每次通行时间总数与累计通行次数之比
是否同城	根据高速公路出入口站所属地判断是否为同城通行	同城为1,非同城为0
是否周末通行	根据通行车辆形式日期判断是否为周末通行	周末通行为1,非周末通行为0
通行时间段	根据通行车辆驶入入口站时间判断其通行时间段	通行时间段在早高峰时间段7∶00~9∶00赋值为0,在晚高峰时间段17∶00~20∶00赋值为1,在平峰时间段9∶00~17∶00赋值为2, 其他时间段20∶00~7∶00赋值为3