基于深度特征聚类的高排放移动污染源自动识别

交通运输系统工程与信息 ›› 2021, Vol. 21 ›› Issue (6): 298-309.

• “碳达峰、碳中和”下的交通运输业发展 • 上一篇下一篇

基于深度特征聚类的高排放移动污染源自动识别

许镇义^{* 1}，王仁军^1，2，张聪³，王瑞宾^1，2，夏秀山⁴

1. 合肥综合性国家科学中心人工智能研究院，合肥 230088；2. 安徽大学，计算机科学与技术学院，合肥 230601； 3. 合肥市生态环境局，合肥 230601；4.中国科学技术大学，先进技术研究院，合肥 230088

收稿日期:2021-07-09 修回日期:2021-08-31 接受日期:2021-09-08 出版日期:2021-12-25 发布日期:2021-12-24
作者简介:许镇义(1993- )，男，江苏宿迁人，副研究员。
基金资助:
国家自然科学基金

Automatic Identification of High-emitting Vehicle Based on Deep Feature Clustering

XU Zhen-yi^{* 1} , WANG Ren-jun^{1, 2} , ZHANG Cong³ , WANG Rui-bin^{1, 2} , XIA Xiu-shan⁴

1. Hefei Comprehensive National Science Center Artificial Intelligence Research Institute, Hefei 230088, China; 2. School of Computer Science and Technology, Anhui University, Hefei 230601, China; 3. Hefei Municipal Environmental Protection Bureau, Hefei 230601, China; 4. Institute of Advanced Technology, University of Science and Technology of China, Hefei 230088, China

Received:2021-07-09 Revised:2021-08-31 Accepted:2021-09-08 Online:2021-12-25 Published:2021-12-24
Supported by:
National Natural Science Foundation of China(62103124)

摘要/Abstract

摘要： 传统的高排放移动源识别方式是将采集的尾气数据与预先设定的排放阈值进行比较判定，但是，排放阈值的设定很大程度上取决于人为标准，并且忽视了外部因素对尾气排放的影响，无法真正反映移动源排放水平。针对此问题，本文结合机器学习算法，提出一种基于深度特征聚类的高排放移动源识别方法。首先，利用随机森林算法筛选出不同污染物(CO、HC、NO)排放的主要影响特征；其次，对多维影响特征进行聚类分析，获取高排放类别标签；最后，训练得到基于深度森林的移动污染源分类模型，自动识别高排放目标源。通过对比实验，在合肥市机动车污染遥测数据集上验证了所提方法的有效性。

关键词: 信息技术, 高排放识别, 特征聚类, 深度森林

Abstract: The traditional approach of identifying high emission mobile sources is to compare the collected tailpipe data with pre-defined emission thresholds. However, the setting of emission thresholds depends mainly on human standards, and this method ignores the influence of external factors on tailpipe emissions, which cannot exactly reflect the emission level of mobile sources. To address this problem, this paper combines different machine learning algorithms and proposes a method for identifying high emission mobile sources based on deep feature clustering. The random forest algorithm is first used to filter out the main impact features of different pollutant (CO/HC/NO) emissions. Then, the multidimensional impact features are clustered to obtain the high emission category labels. A deep forest-based mobile source classification model is trained to automatically identify the high emission target sources. The experiment results on the telemetry dataset of mobile source pollution in Hefei verify the effectiveness of this method.

Key words: information technology, high-emitter identification, feature clustering, deep forest

中图分类号:

U495

许镇义, 王仁军, 张聪, 王瑞宾, 夏秀山. 基于深度特征聚类的高排放移动污染源自动识别[J]. 交通运输系统工程与信息, 2021, 21(6): 298-309.

XU Zhen-yi, WANG Ren-jun , ZHANG Cong , WANG Rui-bin , XIA Xiu-shan. Automatic Identification of High-emitting Vehicle Based on Deep Feature Clustering[J]. Journal of Transportation Systems Engineering and Information Technology, 2021, 21(6): 298-309.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/abstract/abstract30361.shtml

http://www.tseit.org.cn/CN/Y2021/V21/I6/298

参考文献

[1] FRANCO V, KOUSOULIDOU M, MUNTEAN M, et al. Road vehicle emission factors development: A review[J]. Atmospheric Environment, 2013, 70: 84-97.

[2] MCCLINTOCK P M. 2007 high emitter remote sensing project[J]. 2007.

[3] PUJADAS M, DOMÍNGUEZ- SÁEZ A, DE LA FUENTE J. Real-driving emissions of circulating spanish car fleet in 2015 using RSD technology[J]. Science of The Total Environment, 2017, 576: 193-209.

[4] ROPKINS K, DEFRIES T H, POPE F, et al. Evaluation of EDAR vehicle emissions remote sensing technology[J]. Science of the Total Environment, 2017, 609: 1464- 1474.

[5] GUO H, ZENG J, HU Y. Neural network modeling of vehicle gross emitter prediction based on remote sensing data[C]. 2006 IEEE International Conference on Networking, Sensing and Control, Fort Lauderdale, Florida, IEEE, 2006: 943-946.

[6] JUN Z, HUAFANG G, YUEMING H. A PKGV- ANN model for vehicle high emitters identification based on remote sensing data[C]. 2008 27th Chinese Control Conference, Kunming, China, IEEE, 2008: 171-175.

[7] XIE H, ZHANG Y, HE Y, et al. Automatic and fast recognition of on-road high-emitting vehicles using an optical remote sensing system[J]. Sensors, 2019, 19(16): 3540.

[8] KANG Y, LI Z, LV W, et al. High-emitting vehicle identification by on-road emission remote sensing with scarce positive labels[J]. Atmospheric Environment, 2021, 244: 117877.

[9] SAMBASIVAM S, THEODOSOPOULOS N. Advanced data clustering methods of mining Web documents[J]. Issues in Informing Science & Information Technology, 2006(3): 563-579.

[10] 孙吉贵, 刘杰, 赵连宇. 聚类算法研究[J]. 软件学报, 2008(1): 48-61. [SUN J G, LIU J, ZHAO L Y. Research on clustering algorithm[J]. Journal of Software, 2008(1): 48-61.]

[11] 张馨露. 基于随机森林回归的出租车排放因子影响因素研究 [D]. 沈阳: 辽宁大学, 2020. [ZHANG X L. Research on influence factors of taxi emission factor based on random forest regression[D]. Shenyang: Liaoning University, 2020.]

[12] 曹正凤. 随机森林算法优化研究[D]. 北京: 首都经济贸易大学, 2014. [CAO Z F. Research on optimization of random forest algorithm[D]. Beijing: Capital University of Economics and Business, 2014.]

[1]	陈鼎, 周水庭, 陈云, 苏敏咸. 拥堵指数自适应调节的交通运行状态识别方法及应用研究[J]. 交通运输系统工程与信息, 2022, 22(2): 137-144.
[2]	李鑫，史天运，常宝，马小宁，刘军. 基于设备画像的机车标签体系构建方法研究[J]. 交通运输系统工程与信息, 2021, 21(2): 189-195.
[3]	李兴鑫，朱力强，余祖俊. 自适应铁路场景前景目标检测[J]. 交通运输系统工程与信息, 2020, 20(2): 83-90.
[4]	侯涛，伍海萍，牛宏侠. 改进MOG-LRMF 的铁轨动态异物检测[J]. 交通运输系统工程与信息, 2020, 20(2): 91-100.
[5]	杨蕴，李玉，赵泉华. 基于多标记像素匹配的高分辨率遥感图像道路提取[J]. 交通运输系统工程与信息, 2020, 20(1): 68-74.
[6]	魏广奇，苏跃江，吴德馨，袁敏贤. 基于高速公路流水数据的通勤车辆特征研究[J]. 交通运输系统工程与信息, 2019, 19(3): 237-244.
[7]	龙小强，苏跃江，余畅，吴德馨. 基于卡口车牌识别数据的车辆出行分析[J]. 交通运输系统工程与信息, 2019, 19(2): 66-72.
[8]	牛宏侠，张肇鑫，宁正，陈光武. 铁路轨道异物完整性检测与跟踪算法研究[J]. 交通运输系统工程与信息, 2019, 19(1): 45-54.
[9]	刘海洋，冯仲科，吴云鹏，呼诺，冯泽邦 . 车联网信息技术高速公路预警与应急避险模型[J]. 交通运输系统工程与信息, 2018, 18(6): 35-40.
[10]	周洋，杨超. 基于时空聚类算法的轨迹停驻点识别研究[J]. 交通运输系统工程与信息, 2018, 18(4): 88-95.
[11]	李浩，张运胜. 基于反馈背景模型的城市道路交叉口前景目标检测[J]. 交通运输系统工程与信息, 2017, 17(6): 63-69.
[12]	曾倩琳，孙秋碧. 信息化、空间溢出效应与物流业生产率的提升[J]. 交通运输系统工程与信息, 2017, 17(1): 40-46.
[13]	杨国元，史天运，张秋亮. 铁路客运乘务排班计划编制模型及算法[J]. 交通运输系统工程与信息, 2016, 16(4): 159-164.
[14]	马继辉，余明捷，陈鑫杰，宋翠颖，杨扬. 基于Hama并行蚁群算法模型及TSP应用研究[J]. 交通运输系统工程与信息, 2016, 16(3): 168-173.
[15]	丁建文，刘杨，费丹，钟章队. 铁路专用移动通信场强测量检波方式研究[J]. 交通运输系统工程与信息, 2016, 16(1): 71-77.

基于深度特征聚类的高排放移动污染源自动识别

Automatic Identification of High-emitting Vehicle Based on Deep Feature Clustering

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics