基于非线性主成分分析和GA-RBF的高速公路交通量预测方法

雷定猷; 马强; 徐新平; 刘青意

doi:10.19818/j.cnki.1671-1637.2018.03.021

基于非线性主成分分析和GA-RBF的高速公路交通量预测方法

doi: 10.19818/j.cnki.1671-1637.2018.03.021

中南大学交通运输工程学院, 湖南长沙 410075

基金项目:

国家自然科学基金项目 71771218

国家自然科学基金项目 71771218, 71501190

详细信息

作者简介:
雷定猷(1958-), 男, 湖南浏阳人, 中南大学教授, 工学博士, 从事交通运输决策支持研究

通讯作者:
徐新平(1991-), 男, 湖北武汉人, 中南大学工学硕士研究生

中图分类号: U49
计量
- 文章访问数: 713
- HTML全文浏览量: 148
- PDF下载量: 900
- 被引次数: 0
出版历程
- 收稿日期: 2017-12-12
- 刊出日期: 2018-06-25

Forecasting method of expressway traffic volume based on NPCA and GA-RBF

School of Traffic and Transportation Engineering, Central South University, Changsha 410075, Hunan, China

More Information

Author Bio:
LEI Ding-you(1958-), male, professor, PhD, ding@csu.edu.cn

XU Xin-ping(1991-), male, graduate student, xuxinping@csu.edu.cn

摘要

摘要: 为了提高高速公路交通量的预测精度, 综合考虑高速公路交通量的高度非线性和受多因素影响的特征, 提出一种基于非线性主成分分析和GA-RBF神经网络(NPCA-GA-RBF) 的高速公路交通量预测方法; 确定了高速公路交通量的主要影响指标, 运用非线性主成分分析法降低高速公路交通量影响指标的维数及其相关性, 用少数主成分代替原有的多指标, 以简化神经网络结构; 利用GA优化RBF神经网络的参数, 进一步提高交通量的预测精度; 以普洱市某高速公路为例, 对交通量预测方法进行实例验证。分析结果表明: 2组试验GA-RBF和NPCA-GA-RBF方法的平均相对误差分别比RBF方法降低1.62%、3.53%和2.27%、3.32%, 说明GA优化RBF神经网络能提高RBF方法的交通量预测精度; 与GA-RBF方法相比, 2组试验NPCA-GA-RBF方法的平均相对误差分别降低了1.91%、1.05%, 其交通量预测值更接近实际交通量, 预测结果更为可靠, 表明非线性主成分分析法消除了指标的相关性, 进一步提高了交通量预测精度, 减少了交通量预测复杂度。可见, NPCA-GA-RBF方法具有更高的交通量预测精度, 能为高速公路的良好管理提供可靠的决策依据, 满足高速公路合理运营管理的客观需求。
- 交通量 /
- 预测方法 /
- 高速公路 /
- RBF神经网络 /
- 非线性主成分分析 /
- 遗传算法
Abstract: To improve expressway traffic volume forecasting accuracy, on the basis of the features of expressway traffic volume which was obviously nonlinear and affected by many factors, a forecasting method based on the nonlinear principal component analysis and GA-optimized RBF neural network (NPCA-GA-RBF) method was presented. The main influencing index of expressway traffic volume was determined, and the nonlinear principal component analysis method was used to reduce the dimensionality and correlation of influencing factors. The original multiple indexes were replaced by a few principal components to simplify the structure of the neural network. The GA was used to optimize the parameters of the RBF neural network and further improve the forecasting accuracy of traffic volume. An expressway in Puer City was taken as the example to verify the traffic volume forecasting method. Analysis result shows that theaverage relative errors of the GA-RBF and NPCA-GA-RBF methods in two experiments are 1.62%, 3.53% and 2.27%, 3.32% smaller than that of the RBF model, respectively, so the GA-optimized RBF neural network improves the traffic volume forecasting accuracy of the RBF method. Compared to the GA-RBF method, the average relative error of the NPCA-GA-RBF method decreases by 1.91% and 1.05% in two experiments, respectively, its traffic volume forecasting result is closer to the actual traffic volume and more reliable, which demonstrates that the nonlinear principal component analysis eliminates the correlation of the indexes to further improve the traffic volume forecasting accuracy and reduces the forecasting complexity of traffic volume. So, the NPCA-GA-RBF method has higher traffic volume forecasting accuracy, can provide the reliable decision basis for expressway operations management, and satisfies the objective requirements of the reasonable management for expressway.
- traffic volume /
- forecasting method /
- expressway /
- RBF neural network /
- nonlinear principal component analysis /
- genetic algorithm

HTML全文

图 1 RBF神经网络

Figure 1. RBF neural network

下载: 全尺寸图片幻灯片

图 2 各主成分的特征值

Figure 2. Eigenvalues of principal components

下载: 全尺寸图片幻灯片

图 3 各主成分的方差贡献率

Figure 3. Variance contribution ratios of principal components

下载: 全尺寸图片幻灯片

图 4 主成分值

Figure 4. Values of principal components

下载: 全尺寸图片幻灯片

图 5 交通量数据

Figure 5. Traffic volume data

下载: 全尺寸图片幻灯片

图 6 三种预测方法的预测结果

Figure 6. Forecasting results of three forecasting methods

下载: 全尺寸图片幻灯片

表 1 主要指标统计结果

Table 1. Statistical results of main indicators

下载: 导出CSV

表 2 指标的Pearson相关系数

Table 2. Pearson's correlation coefficients of indicators

下载: 导出CSV

表 3 预测误差

Table 3. Forecasting errors

下载: 导出CSV

参考文献(27)

[1]	肖润谋, 李彬, 陈荫三. 基于大数据的高速公路运输趋势分析[J]. 交通运输工程学报, 2015, 15 (5): 85-90, 117. doi: 10.3969/j.issn.1671-1637.2015.05.011 XIAO Run-mou, LI Bin, CHEN Yin-san. Trend analysis of expressway transportation based on big data[J]. Journal of Traffic and Transportation Engineering, 2015, 15 (5): 85-90, 117. (in Chinese). doi: 10.3969/j.issn.1671-1637.2015.05.011
[2]	刘帅, 唐伯明, 陈坚. 区域综合客运通道多方式竞争力博弈模型[J]. 交通运输工程学报, 2017, 17 (2): 136-142. doi: 10.3969/j.issn.1671-1637.2017.02.015 LIU Shuai, TANG Bo-ming, CHEN Jian. Multi-mode competitiveness game model in regional comprehensive passenger transportation corridor[J]. Journal of Traffic and Transportation Engineering, 2017, 17 (2): 136-142. (in Chinese). doi: 10.3969/j.issn.1671-1637.2017.02.015
[3]	章锡俏, 王守恒, 孟祥海. 基于经济增长的高速公路诱增交通量预测[J]. 哈尔滨工业大学学报, 2007, 39 (10): 1618-1620. doi: 10.3321/j.issn:0367-6234.2007.10.025 ZHANG Xi-qiao, WANG Shou-heng, MENG Xiang-hai. Study of freeway induced traffic volume forecasting based on economic growth[J]. Journal of Harbin Institute of Technology, 2007, 39 (10): 1618-1620. (in Chinese). doi: 10.3321/j.issn:0367-6234.2007.10.025
[4]	张通, 张骏, 杨霄. 基于混合AGO-SVM的高速公路短时交通量预测研究[J]. 交通运输系统工程与信息, 2011, 11 (1): 157-162. doi: 10.3969/j.issn.1009-6744.2011.01.027 ZHANG Tong, ZHANG Jun, YANG Xiao. Short-term highway traffic flow prediction based on mixed AGO-SVM[J]. Journal of Transportation Systems Engineering and Information Technology, 2011, 11 (1): 157-162. (in Chinese). doi: 10.3969/j.issn.1009-6744.2011.01.027
[5]	林文新, 王建伟, 袁长伟. 高速公路交通量预测的GM (1, 1) 残差改进模型[J]. 长安大学学报: 自然科学版, 2011, 31 (5): 77-79, 96. https://www.cnki.com.cn/Article/CJFDTOTAL-XAGL201105015.htm LIN Wen-xin, WANG Jian-wei, YUAN Chang-wei. Residuals improved GM (1, 1) model of expressway traffic volume prediction[J]. Journal of Chang'an University: Natural Science Edition, 2011, 31 (5): 77-79, 96. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-XAGL201105015.htm
[6]	桂滨, 周伟. 基于运输需求函数的区域高速公路网交通量预测模型[J]. 公路, 2012 (1): 136-138. https://www.cnki.com.cn/Article/CJFDTOTAL-GLGL201201031.htm GUI Bin, ZHOU Wei. Traffic volume prediction model of regional expressway network based on transport demand function[J]. Highway, 2012 (1): 136-138. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-GLGL201201031.htm
[7]	钱超, 许宏科, 徐娜, 等. 基于OLAM的高速公路交通量多维预测研究[J]. 交通运输系统工程与信息, 2013, 13 (2): 48-56. doi: 10.3969/j.issn.1009-6744.2013.02.008 QIAN Chao, XU Hong-ke, XU Na, et al. OLAM-based multi-dimensional prediction of expressway traffic volume[J]. Journal of Transportation Systems Engineering and Information Technology, 2013, 13 (2): 48-56. (in Chinese). doi: 10.3969/j.issn.1009-6744.2013.02.008
[8]	王慧勇, 晏秋. 基于灰色线性回归组合模型的高速公路交通量预测[J]. 交通运输工程与信息学报, 2016, 14 (1): 53-57. doi: 10.3969/j.issn.1672-4747.2016.01.009 WANG Hui-yong, YAN Qiu. Forecast of expressway traffic volume based on the grey linear regression combined model[J]. Journal of Transportation Engineering and Information, 2016, 14 (1): 53-57. (in Chinese). doi: 10.3969/j.issn.1672-4747.2016.01.009
[9]	丁志坤, 朱梦炼, 宋义勇. 基于改进"四阶段法"的高速公路交通量预测研究[J]. 重庆交通大学学报: 自然科学版, 2017, 36 (5): 86-90. doi: 10.3969/j.issn.1674-0696.2017.05.15 DING Zhi-kun, ZHU Meng-lian, SONG Yi-yong. Traffic forecast of highway based on improved"four-stage method"[J]. Journal of Chongqing Jiaotong University: Natural Science, 2017, 36 (5): 86-90. (in Chinese). doi: 10.3969/j.issn.1674-0696.2017.05.15
[10]	JIA Zhu-zheng, CAO Jin-xin, ZHU Yuan. Traffic volume forecasting based on radial basis function neural network with the consideration of traffic flows at the adjacent intersections[J]. Transportation Research Part C: Emerging Technologies, 2014, 47 (2): 139-154.
[11]	HUANG Xiao-lin, MAIER A, HORNEGGER J, et al. Indefinite kernels in least squares support vector machines and principal component analysis[J]. Applied and Computational Harmonic Analysis, 2017, 43 (1): 162-172. doi: 10.1016/j.acha.2016.09.001
[12]	MORETTI F, PIZZUTI S, PANZIERI S, et al. Urban traffic flow forecasting through statistical and neural network bagging ensemble hybrid modeling[J]. Neurocomputing, 2015, 167: 3-7. doi: 10.1016/j.neucom.2014.08.100
[13]	TATAR A, NASERI S, SIRACH N, et al. Prediction of reservoir brine properties using radial basis function (RBF) neural network[J]. Petroleum, 2015, 1 (4): 349-357. doi: 10.1016/j.petlm.2015.10.011
[14]	ABDI J, MOSHIRI B, ABDULHAI B, et al. Forecasting of short-term traffic-flow based on improved neurofuzzy models via emotional temporal difference learning algorithm[J]. Engineering Applications of Artificial Intelligence, 2012, 25 (5): 1022-1042.
[15]	王炎, 王华. 基于BP-NN和遗传算法的高速公路交通量预测[J]. 计算机工程与应用, 2006, 42 (4): 226-228. doi: 10.3321/j.issn:1002-8331.2006.04.070 WANG Yan, WANG Hua. Prediction of highway traffic based on BP-neural network and genetic algorithms[J]. Computer Engineering and Applications, 2006, 42 (4): 226-228. (in Chinese). doi: 10.3321/j.issn:1002-8331.2006.04.070
[16]	王锡伟, 高军伟, 张彬, 等. 改进粒子群算法优化RBF的交通流预测研究[J]. 青岛大学学报: 工程技术版, 2015, 30 (4): 43-46. https://www.cnki.com.cn/Article/CJFDTOTAL-QDDX201504010.htm WANG Xi-wei, GAO Jun-wei, ZHANG Bin, et al. Traffic forecasting application based on improved particle swarm optimization and RBF neural Network[J]. Journal of Qingdao University: Engineering and Technology Edition, 2015, 30 (4): 43-46. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-QDDX201504010.htm
[17]	YANG Hong-jun, HU Xu. Wavelet neural network with improved genetic algorithm for traffic flow time series prediction[J]. Optik, 2016, 127 (19): 8103-8110.
[18]	黄文明, 徐双双, 邓珍容, 等. 改进人工蜂群算法优化RBF神经网络的短时交通流预测[J]. 计算机工程与科学, 2016, 38 (4): 713-719. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJK201604016.htm HUANG Wen-ming, XU Shuang-shuang, DENG Zhen-rong, et al. Short-term traffic flow prediction of optimized RBF neural networks based on the modified ABC algorithm[J]. Computer Engineering and Science, 2016, 38 (4): 713-719. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-JSJK201604016.htm
[19]	HE Hong-di, WANG Jun-li, WEI Hai-rui, et al. Fractal behavior of traffic volume on urban expressway through adaptive fractal analysis[J]. Physica A: Statistical Mechanics and Its Applications, 2016, 443: 518-525.
[20]	MIRGOLBABAEI H, ECHEKKI T, SMAOUI N. A nonlinear principal component analysis approach for turbulent combustion composition space[J]. International Journal of Hydrogen Energy, 2014, 39 (9): 4622-4633.
[21]	刘兴彬, 万发祥. RBF神经网络主成分分析法在交通量预测中应用[J]. 山西科技, 2007 (1): 54-56. https://www.cnki.com.cn/Article/CJFDTOTAL-SXKJ200701024.htm LIU Xing-bin, WANG Fa-xiang. Application of RBF main neural network analytic approach in traffic volume prediction[J]. Shanxi Science and Technology, 2007 (1): 54-56. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-SXKJ200701024.htm
[22]	姚智胜, 邵春福, 熊志华, 等. 基于主成分分析和支持向量机的道路网短时交通流量预测[J]. 吉林大学学报: 工学版, 2008, 38 (1): 48-52. https://www.cnki.com.cn/Article/CJFDTOTAL-JLGY200801010.htm YAO Zhi-sheng, SHAO Chun-fu, XIONG Zhi-hua, et al. Short-term traffic volumes forecasting of road network based on principal component analysis and support vector machine[J]. Journal of Jilin University: Engineering and Technology Edition, 2008, 38 (1): 48-52. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-JLGY200801010.htm
[23]	肖智, 李玲玲. PSO-SVM在高速公路交通量预测中的应用[J]. 管理评论, 2011, 23 (12): 32-37, 67. https://www.cnki.com.cn/Article/CJFDTOTAL-ZWGD201112005.htm XIAO Zhi, LI Ling-ling. Forecast of highway traffic volume using PSO-SVM[J]. Management Review, 2011, 23 (12): 32-37, 67. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-ZWGD201112005.htm
[24]	孙超平, 杨善林, 施敏加. 基于非线性主成分分析法的SWOT战略定位模型研究[J]. 合肥工业大学学报: 自然科学版, 2012, 35 (12): 1702-1708. https://www.cnki.com.cn/Article/CJFDTOTAL-HEFE201212027.htm SUN Chao-ping, YANG Shan-lin, SHI Min-jia. Research on SWOT strategic model based on non-linear principal component analysis[J]. Journal of Hefei University of Technology: Natural Science Edition, 2012, 35 (12): 1702-1708. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-HEFE201212027.htm
[25]	KAGODA P A, NDIRITU J, NTULI C, et al. Application of radial basis function neural networks to short-term streamflow forecasting[J]. Physics and Chemistry of the Earth, 2010, 35 (13/14): 571-581.
[26]	AIBINU A M, SALAU H B, RAHMAN N A, et al. A novel clustering based genetic algorithm for route optimization[J]. Engineering Science and Technology, 2016, 19 (4): 2022-2034.
[27]	ZHAO Ze-hui, KANG Hai-gui, LI Ming-wei. Expressway traffic flow prediction using chaos cloud particle swarm algorithm and PPPR model[J]. Journal of Southeast University: English Edition, 2013, 29 (3): 328-335.