基于相似数据聚合与变K值KNN的短时交通流量预测

doi:10.12082/dqxxkx.2018.180281

地球信息科学学报 ›› 2018, Vol. 20 ›› Issue (10): 1403-1411.doi: 10.12082/dqxxkx.2018.180281

• 地球信息科学理论与方法 • 上一篇下一篇

基于相似数据聚合与变K值KNN的短时交通流量预测

梁艳平^1,^2,³(), 毛政元^1,^2,^3,^*(), 邹为彬^1,^2,^3,⁴, 许锐⁵

1. 福州大学福建省空间信息工程研究中心,福州 350002
2. 福州大学空间数据挖掘与信息共享教育部重点实验室,福州 350002
3. 福州大学地理空间信息技术国家地方联合工程研究中心,福州 350002
4. 福建工程学院交通运输学院,福州 350118
5. 福建工程学院信息科学与工程学院,福州 350118

收稿日期:2018-06-11 修回日期:2018-07-19 出版日期:2018-10-25 发布日期:2018-10-17
通讯作者: 毛政元 E-mail:497336236@qq.com;zymao@fzu.edu.cn
作者简介:
作者简介：梁艳平（1993-）,男,硕士生,研究方向为短时交通流量预测、智能算法。E-mail: 497336236@qq.com
基金资助:
国家自然科学基金项目(41471333);福建省自然科学基金面上项目（2018J01619）

Short-term Traffic Flow Prediction Based on Similar Data Aggregation and KNN with Varying K-value

LIANG Yanping^1,^2,³(), MAO Zhengyuan^1,^2,^3,^*(), ZOU Weibin^1,^2,^3,⁴, XU Rui⁵

1. Provincial Spatial Information Engineering Research Center, Fuzhou University, Fuzhou 350002, China
2. Key Laboratory of Spatial Data Mining and Information Sharing of Ministry of Education, Fuzhou University, Fuzhou 350002, China
3. National Engineering Research Centre of Geospatial Space Information Technology, Fuzhou University, Fuzhou 350002, China
4. School of Transportation, Fujian University of Technology, Fuzhou 350118, China
5. School of Information Science and Engineering, Fujian University of Technology, Fuzhou 350002, China

Received:2018-06-11 Revised:2018-07-19 Online:2018-10-25 Published:2018-10-17
Contact: MAO Zhengyuan E-mail:497336236@qq.com;zymao@fzu.edu.cn
Supported by:
National Natural Science Foundation of China, No.41471333;Project of Science and Technology of Fujian Province, No.2018J01619.

摘要/Abstract

摘要：

短时交通流量预测是交通控制和诱导涉及的关键技术问题,由于短时交通流量存在不确定性和时变性,其预测难度较大,是相关研究领域与工程实践中亟待解决的难题。为提高短时交通流量预测的准确性,本文设计与实现了基于相似数据聚合和变K值KNN(KNN-SDA)的短时交通流量预测算法。该算法首先采用互信息法在经过预处理的交通流量数据集提取交通流量序列最佳延迟时间信息,生成状态向量,并构建交通流量历史数据库;然后以本文所提出的相似数据聚合方法完成历史数据的聚合与清洗得到训练数据集;最后通过交叉验证确定每个时刻的最优K近邻数,完成算法实现。实验结果表明,本文提出的变K值KNN-SDA算法在保证执行效率的同时能明显提高短时交通流量的预测精度。

关键词: 短时交通流预测, 互信息法, 相似数据聚合, KNN, 交叉验证

Abstract:

Real-time and accurate short-term traffic flow prediction, a critical technical problem in traffic control and guidance which is challenging and needs to be solved urgently in related research fields and engineering practice, still remains because of the hardship caused by the uncertainty and the temporal variability in traffic flow datasets acquired in different times. In order to improve the performance of the short-term traffic flow prediction, a new method based on similar data aggregation techniques and a modified KNN algorithm with varying K-value (KNN-SDA) was proposed and the related algorithm was also implemented and tested on actual measured datasets in this paper. Firstly state vectors were generated from the preprocessed traffic flow datasets by calculating the optimal time delay with the help of the mutual information theory. Each of our state vectors is composed of two parts, the first one of which is a regular state vector and the second one of which is a modified state vector which makes a contribution to a higher similarity between our state vectors and those in training datasets. Subsequently a historical traffic flow database of temporal series was constructed on the basis of results mentioned above for further experiments. After that, the proposed similar data aggregation techniques were applied to aggregate and clean data to obtain 144 training data sets in different times from historical traffic flow database, which would effectively improve the prediction accuracy and efficiency of the proposed algorithm. At last, the optimal K-values, each of which corresponded to a moment, were determined through the cross validation method. So far, the overall process of the KNN-SDA algorithm with varying K-value has been completed. In order to verify the performance of the proposed method, we compared the experimental results derived from our method with those from three other ones. It turns out that the KNN-SDA algorithm with varying K-value proposed in this article can improve the prediction accuracy significantly and ensure high execution efficiency as well.

Key words: short-term traffic prediction, mutual information method, similar data aggregation, KNN, cross validation

梁艳平, 毛政元, 邹为彬, 许锐. 基于相似数据聚合与变K值KNN的短时交通流量预测[J]. 地球信息科学学报, 2018, 20(10): 1403-1411.DOI:10.12082/dqxxkx.2018.180281

LIANG Yanping,MAO Zhengyuan,ZOU Weibin,XU Rui. Short-term Traffic Flow Prediction Based on Similar Data Aggregation and KNN with Varying K-value[J]. Journal of Geo-information Science, 2018, 20(10): 1403-1411.DOI:10.12082/dqxxkx.2018.180281

图/表 10

图1

图2

图3

图4

图5

表1

表2

表3

表4

图6

参考文献 22

[1]	Sun S, Zhang C, Yu G.A bayesian network approach to traffic flow forecasting[J]. IEEE Transactions on Intelligent Transportation Systems, 2006,7(1):124-132. doi: 10.1109/TITS.2006.869623
[2]	Guo J, Huang W, Williams B M.Adaptive Kalman filter approach for stochastic short-term traffic flow rate prediction and uncertainty quantification[J]. Transportation Research Part C, 2014,43:50-64. doi: 10.1016/j.trc.2014.02.006
[3]	赵建东,王浩,刘文辉.高速公路旅行时间的自适应插值卡尔曼滤波预测[J].华南理工大学学报(自然科学版),2014,42(2):109-115.
	[ Zhao J D, Wang H, Liu W H.Prediction of expressway travel time based on adaptive interpolation Kalman filtering[J]. Journal of South China University of Technology (Natural Science Edition), 2014,42(2):109-115. ]
[4]	Oh S D, Kim Y J, Hong J S.Urban traffic flow prediction system using a multifactor pattern recognition model[J]. IEEE Transactions on Intelligent Transportation Systems, 2015,16(5):2744-2755. doi: 10.1109/TITS.2015.2419614
[5]	Xing Y, Ban X, Guo C.Probabilistic forecasting of traffic flow using multikernel based extreme learning machine[J].Scientific Programming, 2017(2):1-12.
[6]	商强,杨兆升,李志林,等.基于相空间重构和RELM的短时交通流量预测[J].华南理工大学学报(自然科学版),2016,44(4):109-114. doi: 10.3969/j.issn.1000-565X.2016.04.016
	[ Shang Q, Yang Z S, Li Z L, et al.Short-term traffic flow prediction based on phase space reconstruction and RELM[J]. Journal of South China University of Technology (Natural Science Edition), 2016,44(4):109-114. ] doi: 10.3969/j.issn.1000-565X.2016.04.016
[7]	杨兆升,王媛,管青.基于支持向量机方法的短时交通流量预测方法[J].吉林大学学报(工学版),2006,36(6):881-884. doi: 10.3969/j.issn.1671-5497.2006.06.010
	[ Yang Z S, Wang Y, Guan Q.Short-term traffic flow prediction method based on SVM[J]. Journal of Jilin University (Engineering and Technology Edition), 2016,36(6):881-884. ] doi: 10.3969/j.issn.1671-5497.2006.06.010
[8]	姚卫红,方仁孝,张旭东.基于混合人工鱼群优化SVR的交通流预测模型[J].大连理工大学学报,2015,55(6):632-637.
	[ Yao W H, Fang R X, Zhang X D.Traffic flow forecasting based on optimized SVR with hybrid artificial fish swarm algorithm[J]. Journal of Dalian University of Technology, 2015,55(6):632-637. ]
[9]	Zhang L, Liu Q, Yang W, et al.An improved K -nearest neighbor model for short-term traffic flow prediction[J]. Procedia - Social and Behavioral Sciences, 2013,96:653-662. doi: 10.1016/j.sbspro.2013.08.076
[10]	Bernaś M, Płaczek B, Porwik P, et al. Segmentation of vehicle detector data for improved k-nearest neighbours-based traffic flow prediction[J]. IET Intelligent Transport Systems, 2014,9(3):264-274.
[11]	Davis G A, Nihan N L.Nonparametric regression and short-term freeway traffic forecasting[J]. Journal of Transportation Engineering, 1991,117(2):178-188. doi: 10.1061/(ASCE)0733-947X(1991)117:2(178)
[12]	Smith B L, Williams B M, Oswald R K.Comparison of parametric and nonparametric models for traffic flow forecasting[J]. Transportation Research Part C, 2002,10(4):303-321. doi: 10.1016/S0968-090X(02)00009-8
[13]	刘洋,马寿峰.基于聚类分析的非参数回归短时交通流预测方法[J].交通信息与安全,2013,31(2):27-31. doi: 10.3963/j.issn.1674-4861.2013.02.007
	[ Liu Y, Ma S F.Non-parametric regression for short-term traffic flow forecasting based on cluster analysis[J]. Journal of Transport Information and Safety, 2013,31(2):27-31. ] doi: 10.3963/j.issn.1674-4861.2013.02.007
[14]	张晓利,陆化普.非参数回归方法在短时交通流预测中的应用[J].清华大学学报(自然科学版),2009,49(9):1471-1475.
	[ Zhang X L, Lu H P.Non-parametric regression and application for short-term traffic flow forecasting[J]. Journal of Tsinghua University (Science and Technology), 2009,49(9):1471-1475. ]
[15]	张涛,陈先,谢美萍,等.基于K近邻非参数回归的短时交通流预测方法[J].系统工程理论与实践,2010,30(2):376-384.
	[ Zhang T, Chen X, Xie M P, et al.K-NN based nonparametric regression method for short-term traffic flow forecasting[J]. Systems Engineering-Theory & Practice, 2010,30(2):376-384. ]
[16]	张晓利,贺国光,陆化普.基于K-邻域非参数回归短时交通流预测方法[J].系统工程学报,2009,24(2):178-183.
	[ Zhang X L, He G G, Lu H P, Short-term traffic flow forecasting based on K-nearest neighbors non-parametric regression[J]. Journal of Systems Engineering, 2009,24(2):178-183. ]
[17]	Meng M, Wang B B, Shao C F, et al.A two-stage short-term traffic flow prediction method based on AVL and AKNN techniques[J]. Journal of Central South University,2015,22(2):779-786. doi: 10.1007/s11771-015-2582-y
[18]	Frank B.Time-Aware Multivariate Nearest Neighbor Regression Methods for Traffic Flow Prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2015,16(6):3393-3402. doi: 10.1109/TITS.2015.2453116
[19]	Xia D, Li H, Wang B, et al.A map reduce-based nearest neighbor approach for big-data-driven traffic flow prediction[J]. IEEE Access, 2016,4:2920-2934. doi: 10.1109/ACCESS.2016.2570021
[20]	张晓利. 基于非参数回归的短时交通流量预测方法研究[D].天津:天津大学,2007.
	[ Zhang X L.A study on short-term traffic volume forecasting based on non-parametric regression[D]. Tianjin: Tianjin University, 2007. ]
[21]	吕小青,曹彪,曾敏,等.确定延迟时间互信息法的一种算法[J].计算物理,2006,23(2):184-188. doi: 10.3969/j.issn.1001-246X.2006.02.010
	[ Lv X Q, Cao B, Zeng M, et al.An algorithm of selecting delay time in the mutual information method[J]. Chinese Journal of Computational Physics, 2006,23(2):184-188. ] doi: 10.3969/j.issn.1001-246X.2006.02.010
[22]	翟东海,李同亮,段维夏,等.基于矩阵相似度的最佳样本块匹配算法及其在图像修复中的应用[J].计算机科学,2014,41(1):307-310. doi: 10.3969/j.issn.1002-137X.2014.01.062
	[ Zhai D H, Li T L, Duan W X, et al.Optimal exemplar metching algorithm based on matrix similarity and its application in image inpainting[J]. Computer Science, 2014,41(1):307-310. ] doi: 10.3969/j.issn.1002-137X.2014.01.062

算法	改进状态向量	数据聚合	变K值
F1
F2		√	√
F3	√		√
F4	√	√
F5	√	√	√

算法	MAE	MAPE/%	RMSE	EC
F1	15.64	7.92	21.47	0.899
F2	13.25	6.78	18.93	0.945
F3	13.67	7.0	19.35	0.944
F4	11.61	5.93	16.84	0.952
F5	11.07	5.69	16.29	0.969

数据类型	MAE	MAPE/%	RMSE	EC
全部数据	11.07	5.69	16.29	0.969
工作日数据	10.53	5.62	15.6	0.973
非工作日数据	11.81	5.91	17.38	0.952

算法	MAE	MAPE/%	RMSE	EC	时间/s
KNN	16.01	8.41	641.64	0.898	14.59
SVR	14.84	7.72	536.68	0.935	5.86
BP	13.08	6.70	378.79	0.943	6.31
KNN-SDA	11.75	6.22	332.55	0.949	6.17

基于相似数据聚合与变K值KNN的短时交通流量预测

Short-term Traffic Flow Prediction Based on Similar Data Aggregation and KNN with Varying K-value

RichHTML

PDF (PC)

赞

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 22

相关文章 4

Metrics

本文评价

推荐阅读 0

[1]	王景云, 杨军, 杨俊兴, 雷梅, 万小铭, 周小勇, 陈同斌, 张红日, 赵相伟. 基于空间自相关和概率论的土壤重金属异常值的识别方法[J]. 地球信息科学学报, 2017, 19(5): 605-612.
[2]	苏巧梅, 赵尚民, 郭建立. 霍西煤矿区地表滑坡灾害敏感性数值建模与等级划分[J]. 地球信息科学学报, 2017, 19(12): 1613-1622.
[3]	宋敦江, 岳天祥, 龚云, 杜正平. 散乱数据插值的HASM方法[J]. 地球信息科学学报, 2007, 9(3): 45-51.
[4]	徐新良, 曹明奎. 森林生物量遥感估算与应用分析[J]. 地球信息科学学报, 2006, 8(4): 122-128.