[1]李林超,曲栩,张健,等.基于特征级融合的高速公路异质交通流数据修复方法[J].东南大学学报(自然科学版),2018,48(5):972-978.[doi:10.3969/j.issn.1001-0505.2018.05.029]
 Li Linchao,Qu Xu,Zhang Jian,et al.Missing value imputation method for heterogeneous traffic flow data based on feature fusion[J].Journal of Southeast University (Natural Science Edition),2018,48(5):972-978.[doi:10.3969/j.issn.1001-0505.2018.05.029]
点击复制

基于特征级融合的高速公路异质交通流数据修复方法()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
48
期数:
2018年第5期
页码:
972-978
栏目:
交通运输工程
出版日期:
2018-09-20

文章信息/Info

Title:
Missing value imputation method for heterogeneous traffic flow data based on feature fusion
作者:
李林超12曲栩1张健1王永岗3李汉初1冉斌12
1东南大学交通学院, 南京 210096; 2Department of Civil and Environmental Engineering, University of Wisconsin-Madison, Wisconsin 53705, USA; 3 长安大学公路学院, 西安 710064
Author(s):
Li Linchao12 Qu Xu1 Zhang Jian1 Wang Yonggang3 Li Hanchu1 Ran Bin12
1School of Transportation, Southeast University, Nanjing 210096, China
2Department of Civil and Environmental Engineering, University of Wisconsin-Madison, Wisconsin 53705, USA
3School of Highway, Chang’an University, Xi’an 710064, China
关键词:
交通工程 数据修复 深度学习 随机森林 多源数据 自编码网络
Keywords:
traffic engineering data imputation deep learning random forest multiple data auto-encoder
分类号:
U491.1
DOI:
10.3969/j.issn.1001-0505.2018.05.029
摘要:
为获取完整的交通流数据集,提出了一种交通流数据修复方法.结合多源数据的互补特性,基于深度学习模型构建了时空关联特征提取方法,将高速公路交通流数据缺失情况分为3类,并基于随机森林算法建立修正模型.模型以平均绝对误差最小为优化目标,基于测试集和选择集优化了模型的参数.利用高速公路固定检测器和浮动检测技术获取的多源数据,对比分析了单一数据源与多源数据的修正精度.结果表明:多源数据修正模型明显优于单一数据源修正模型,在点缺失、线缺失和面缺失3种情况下,MAPE的平均值分别提高了24.87%,39.87%和52.93%.此外,随着缺失比例的增加,较单一数据源模型,多源数据修正模型精度更为稳定,在点缺失、线缺失和面缺失3种情况下,其MAPE的方差仅为0.01,0.03和0.08,证明其具有较好的鲁棒性.
Abstract:
To obtain a complete traffic dataset, an imputation method for traffic flow data was proposed. Based on the complementary of different types of data and deep learning method, the spatial and temporal features of traffic flow data were extracted. The missing values were divided into three types and an imputation model was established based on a random forest algorithm to estimate the missing values. With the testing and selecting dataset, the model parameters were optimized by minimizing the mean absolute error. Finally, the models were validated using two real-world datasets from camera and fix detector installed in the highway. The results indicate that the proposed model based on multi-source data is better than the models based on single source data, especially when the missing rate is higher. When the missing pattern is point, line and blook, the average mean absolute percent error(MAPE)is improved by 24.87%, 39.87% and 52.93%. Moreover, the variances of MAPE are 0.01, 0.03 and 0.08. The proposed model performs steady with the increase of the missing rate, thus it has better robustness.

参考文献/References:

[1] 李林超, 张健, 杨帆, 等. 基于核函数切换和支持向量回归的交通量短时预测模型[J]. 东南大学学报(自然科学版), 2017, 47(5): 1032-1036. DOI:10.3969/j.issn.1001-0505.2017.05.030.
Li Linchao, Zhang Jian, Yang Fan, et al. Traffic volume prediction based on support vector regression with switch kernel functions[J]. Journal of Southeast University(Natural Science Edition), 2017, 47(5): 1032-1036. DOI:10.3969/j.issn.1001-0505.2017.05.030. (in Chinese)
[2] 李林超, 何赏璐, 张健. 时空因素影响下在线短时交通量预测[J]. 交通运输系统工程与信息,2016,16(5):165-171. DOI:10.3969/j.issn.1009-6744.2016.05.025.
Li Linchao, He Shanglu, Zhang Jian. Online short-term traffic flow prediction considering the impact of temporal-spatial features[J]. Journal of Transportation Systems Engineering and Information Technology, 2016, 16(5): 165-171. DOI:10.3969/j.issn.1009-6744.2016.05.025. (in Chinese)
[3] Henrickson K, Zou Y J, Wang Y H. Flexible and robust method for missing loop detector data imputation[J]. Transportation Research Record: Journal of the Transportation Research Board, 2015, 2527: 29-36. DOI:10.3141/2527-04.
[4] Bie Y W, Wang X, Qiu T Z. Online method to impute missing loop detector data for urban freeway traffic control[J]. Transportation Research Record: Journal of the Transportation Research Board, 2016, 2593: 37-46. DOI:10.3141/2593-05.
[5] 陆化普, 孙智源, 屈闻聪. 基于时空模型的交通流故障数据修正方法[J]. 交通运输工程学报, 2015, 15(6): 92-100,117.
  Lu Huapu, Sun Zhiyuan, Qu Wencong. Repair method of traffic flow malfunction data based on temporal-spatial model[J]. Journal of Traffic and Transportation Engineering, 2015, 15(6): 92-100,117.(in Chinese)
[6] Zou H X, Yue Y, Li Q Q, et al. An improved distance metric for the interpolation of link-based traffic data using kriging: A case study of a large-scale urban road network[J]. International Journal of Geographical Information Science, 2012, 26(4): 667-689. DOI:10.1080/13658816.2011.609488.
[7] Shamo B, Asa E, Membah J. Linear spatial interpolation and analysis of annual average daily traffic data[J]. Journal of Computing in Civil Engineering, 2015, 29(1): 04014022. DOI:10.1061/(asce)cp.1943-5487.0000281.
[8] Li L C, Zhang J, Yang F, et al. Robust and flexible strategy for missing data imputation in intelligent transportation system[J]. IET Intelligent Transport Systems, 2018, 12(2): 151-157. DOI:10.1049/iet-its.2017.0273.
[9] Li L,Li Y B,Li Z H.Efficient missing data imputing for traffic flow by considering temporal and spatial dependence[J]. Transportation Research Part C: Emerging Technologies,2013,34: 108-120. DOI:10.1016/j.trc.2013.05.008.
[10] Ran B, Tan H C, Feng J S, et al. Estimating missing traffic volume using low multilinear rank tensor completion[J]. Journal of Intelligent Transportation Systems, 2016, 20(2):152-161. DOI:10.1080/15472450.2015.1015721.
[11] Hinton G E. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507. DOI:10.1126/science.1127647.
[12] Lv Y S,Duan Y J,Kang W W,et al.Traffic flow prediction with big data: A deep learning approach[J]. IEEE Transactions on Intelligent Transportation Systems,2015,16(2): 865-873. DOI:10.1109/TITS.2014.2345663.
[13] Ma X L,Tao Z M,Wang Y H,et al.Long short-term memory neural network for traffic speed prediction using remote microwave sensor data[J]. Transportation Research Part C: Emerging Technologies,2015,54: 187-197. DOI:10.1016/j.trc.2015.03.014.
[14] Duan Y J, Lv Y, Liu Y L, et al. An efficient realization of deep learning for traffic data imputation[J]. Transportation Research Part C: Emerging Technologies, 2016, 72: 168-181. DOI:10.1016/j.trc.2016.09.015.
[15] Ma X L, Dai Z, He Z B, et al. Learning traffic as images: A deep convolutional neural network for large-scale transportation network speed prediction[J]. Sensors, 2017, 17(4): E818. DOI:10.3390/s17040818.
[16] Wu Y K,Tan H C,Li Y,et al.Robust tensor decomposition based on Cauchy distribution and its applications[J]. Neurocomputing,2017,223: 107-117. DOI:10.1016/j.neucom.2016.10.030.
[17] Breiman L, Friedman J H. Estimating optimal transformations for multiple regression and correlation[J]. Journal of the American Statistical Association, 1985, 80(391): 580-598. DOI:10.1080/01621459.1985.10478157.
[18] Breiman L. Random forests[J]. Machine Learning, 2001, 45(1): 5-32. DOI:10.1023/a:1010933404324.
[19] Tan H C,Wu Y K,Shen B,et al.Short-term traffic prediction based on dynamic tensor completion[J]. IEEE Transactions on Intelligent Transportation Systems,2016,17(8): 2123-2133. DOI:10.1109/TITS.2015.2513411.
[20] Li L C,He S L,Zhang J,et al.Short-term highway traffic flow prediction based on a hybrid strategy considering temporal-spatial information[J]. Journal of Advanced Transportation,2016,50(8): 2029-2040. DOI:10.1002/atr.1443.

相似文献/References:

[1]周竹萍,任刚,王炜.基于方式分担需求的城市道路等级配置模型[J].东南大学学报(自然科学版),2009,39(5):1075.[doi:10.3969/j.issn.1001-0505.2009.05.041]
 Zhou Zhuping,Ren Gang,Wang Wei.Road network gradation optimization model according to traffic demand[J].Journal of Southeast University (Natural Science Edition),2009,39(5):1075.[doi:10.3969/j.issn.1001-0505.2009.05.041]
[2]卓曦,钱振东,张宁.大型公共建筑同向机动车出入口间距计算[J].东南大学学报(自然科学版),2012,42(3):560.[doi:10.3969/j.issn.1001-0505.2012.03.033]
 Zhuo Xi,Qian Zhendong,Zhang Ning.Spacing calculation for same-side vehicle access of large public building[J].Journal of Southeast University (Natural Science Edition),2012,42(5):560.[doi:10.3969/j.issn.1001-0505.2012.03.033]
[3]肖忠斌,王炜,李文权,等.城市高架路下匝道地面联接段最小长度模型[J].东南大学学报(自然科学版),2007,37(6):1071.[doi:10.3969/j.issn.1001-0505.2007.06.026]
 Xiao Zhongbin,Wang Wei,Li Wenquan,et al.Minimum-length-requirement model for expressway off-ramp joint[J].Journal of Southeast University (Natural Science Edition),2007,37(5):1071.[doi:10.3969/j.issn.1001-0505.2007.06.026]
[4]葛宏伟,王炜,陈学武,等.公交站点车辆停靠对信号交叉口进口道交通延误模型[J].东南大学学报(自然科学版),2006,36(6):1018.[doi:10.3969/j.issn.1001-0505.2006.06.029]
 Ge Hongwei,Wang Wei,Chen Xuewu,et al.Traffic delay at signal-controlled intersection with bus stop upstream[J].Journal of Southeast University (Natural Science Edition),2006,36(5):1018.[doi:10.3969/j.issn.1001-0505.2006.06.029]
[5]许项东,程琳,邱松林.交通分配自适应梯度投影算法的敏感性分析[J].东南大学学报(自然科学版),2013,43(1):226.[doi:10.3969/j.issn.1001-0505.2013.01.041]
 Xu Xiangdong,Cheng Lin,Qiu Songlin.Sensitivity analysis of self-adaptive gradient projection traffic assignment algorithm[J].Journal of Southeast University (Natural Science Edition),2013,43(5):226.[doi:10.3969/j.issn.1001-0505.2013.01.041]
[6]郭延永,刘攀,吴瑶,等.基于属性识别的高速公路交通安全设施系统评价[J].东南大学学报(自然科学版),2013,43(6):1305.[doi:10.3969/j.issn.1001-0505.2013.06.032]
 Guo Yanyong,Liu Pan,Wu Yao,et al.Evaluation of freeway traffic safety facility system based on attribute recognition[J].Journal of Southeast University (Natural Science Edition),2013,43(5):1305.[doi:10.3969/j.issn.1001-0505.2013.06.032]
[7]姜军,陆建,李娅.基于驾驶人视认特性的城市道路指路标志设置[J].东南大学学报(自然科学版),2010,40(5):1089.[doi:10.3969/j.issn.1001-0505.2010.05.039]
 Jiang Jun,Lu Jian,Li Ya.Setting of road guide signs based on driver’s recognition characteristics[J].Journal of Southeast University (Natural Science Edition),2010,40(5):1089.[doi:10.3969/j.issn.1001-0505.2010.05.039]
[8]沈家军,王炜,陈学武.城市道路交叉口混合交通流机动车与非机动车冲突概率[J].东南大学学报(自然科学版),2010,40(5):1093.[doi:10.3969/j.issn.1001-0505.2010.05.040]
 Shen Jiajun,Wang Wei,Chen Xuewu.Study on conflict probability of motor and non-motor mixed traffic at urban intersections[J].Journal of Southeast University (Natural Science Edition),2010,40(5):1093.[doi:10.3969/j.issn.1001-0505.2010.05.040]
[9]王炜,陈淑燕,胡晓健.“一路一线直行式”公交模式下公交车行驶诱导和调度集成方法[J].东南大学学报(自然科学版),2008,38(6):1110.[doi:10.3969/j.issn.1001-0505.2008.06.033]
 Wang Wei,Chen Shuyan,Hu Xiaojian.Novel integrated method of bus speed guidance and dispatching based on “one route one line and run straight mode”[J].Journal of Southeast University (Natural Science Edition),2008,38(5):1110.[doi:10.3969/j.issn.1001-0505.2008.06.033]
[10]李志斌,王炜,赵德,等.机非物理分隔道路上自行车超车事件模型[J].东南大学学报(自然科学版),2012,42(1):156.[doi:10.3969/j.issn.1001-0505.2012.01.029]
 Li Zhibin,Wang Wei,Zhao De,et al.Modeling bicycle passing events on physically separated roadways[J].Journal of Southeast University (Natural Science Edition),2012,42(5):156.[doi:10.3969/j.issn.1001-0505.2012.01.029]

备注/Memo

备注/Memo:
收稿日期: 2018-03-04.
作者简介: 李林超(1991—),男,博士生;张健(联系人),男,博士,讲师, jianzhang@seu.edu.cn.
基金项目: 国家自然科学基金资助项目(6161001115)、江苏省自然科学基金资助项目(BK20160685)、东南大学优秀博士学位论文基金资助项目(YBJJ1736).
引用本文: 李林超,曲栩,张健,等.基于特征级融合的高速公路异质交通流数据修复方法[J].东南大学学报(自然科学版),2018,48(5):972-978. DOI:10.3969/j.issn.1001-0505.2018.05.029.
更新日期/Last Update: 2018-09-20