Please wait a minute...
 首页  期刊介绍 期刊订阅 联系我们 横山亮次奖 百年刊庆
 
最新录用  |  预出版  |  当期目录  |  过刊浏览  |  阅读排行  |  下载排行  |  引用排行  |  横山亮次奖  |  百年刊庆
清华大学学报(自然科学版)  2014, Vol. 54 Issue (3): 348-353    
  论文 本期目录 | 过刊浏览 | 高级检索 |
基于ARIMA与信息粒化SVR组合模型的交通事故时序预测
孙轶轩1,邵春福1(),计寻1,朱亮2
2. 中国铁道科学研究院 运输及经济研究所, 北京 100081
Urban traffic accident time series prediction model based on combination of ARIMA and information granulation SVR
Yixuan SUN1,Chunfu SHAO1(),Xun JI1,Liang ZHU2
1. Key Laboratory for Urban Transportation Complex Systems Theory and Technology of Ministry of Education, Beijing Jiaotong University, Beijing 100044, China
2.Transportation & Economic Research Institute, China Academy of Railway Sciences, Beijing 100081, China
全文: PDF(1505 KB)   HTML
输出: BibTeX | EndNote (RIS)       背景资料
文章导读  
摘要 

该文基于自回归滑动平均(ARIMA)模型和支持向量回归机(SVR)模型,构建时间序列组合预测模型,对道路交通事故相关指标进行趋势预测。通过ARIMA预测模型进行线性拟合; 基于模糊信息粒化方法,将ARIMA预测模型残差季度变化趋势映射为包含最小值Low、 中值R、 最大值Up三个参数的模糊信息粒; 并以其为输入构建SVR模型,对季度残差变化趋势进行预测; 最后根据SVR残差预测值修正ARIMA模型预测值。实证研究结果表明: 时间序列组合预测模型精度优于单一ARIMA模型,由模糊信息粒子确定的预测区间较好描述了实证数据的季度变化趋势。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
孙轶轩
邵春福
计寻
朱亮
关键词 事故预测时间序列自回归移动平均法(ARIMA)模糊信息粒化支持向量回归机(SVR)    
Abstract

A hybrid prediction model was established to implement the time series forecasting of traffic accident statistical index based on the ARIMA model and the SVR model. The ARIMA model was used to complete the linear fitting of original time series, with the residual error of the ARIMA model then transformed into fuzzy information granulation particles made up of Low, R and Up. An SVR model was developed to describe the seasonal trend of the residual error with Low, R and Up as input. The predicted value of the ARIMA model was fixed based on the SVR regression result of the seasonal residual error, with the predicted value of the hybrid model being calculated. Empirical research results show that the accuracy of the hybrid model is higher than that of the single ARIMA model and that the seasonal trends of empirical time series are precisely represented by fuzzy information granulation particles.

Key wordsaccident prediction    time series    ARIMA    fuzzy information granulation    SVR
收稿日期: 2014-02-10      出版日期: 2014-03-15
ZTFLH:     
基金资助:国家 “九七三” 重点基础研究项目 (2012CB725403);国家自然科学基金国际合作重大项目 (71210001)
引用本文:   
孙轶轩, 邵春福, 计寻, 朱亮. 基于ARIMA与信息粒化SVR组合模型的交通事故时序预测[J]. 清华大学学报(自然科学版), 2014, 54(3): 348-353.
Yixuan SUN, Chunfu SHAO, Xun JI, Liang ZHU. Urban traffic accident time series prediction model based on combination of ARIMA and information granulation SVR. Journal of Tsinghua University(Science and Technology), 2014, 54(3): 348-353.
链接本文:  
http://jst.tsinghuajournals.com/CN/  或          http://jst.tsinghuajournals.com/CN/Y2014/V54/I3/348
  2006—2013年死亡和受伤人数月度时间序列
  1阶差分时间序列
模型 AIC SC
ARIMA(0,1,1) 6.98 7.03
ARIMA(4,1,0) 7.03 7.18
ARIMA(4,1,1) 7.05 7.22
  模型AIC和SC检验值
  ARIMA(0,1,1)模型预测结果
  粒化结果图
  测试集SVR预测结果对比
  参数网格寻优结果
日期(窗口化) 受伤人数
观测值
ARIMA
预测值
ARIMA相
对误差
残差SVR
预测值
组合模型
预测值
组合模型
相对误差
残差变化范围
(由模糊粒子描述)
2013年一季度 29 29.96 3.3% -0.15 29.81 2.8% [-8.14, 5.85, 6.92]
2013年二季度 33.33 31.92 4.2% 2.67 34.57 3.8% [-7.61, 6.07, 8.29]
  组合模型预测结果
[1] 高海龙, 阚伟生, 李长城, 等. 双车道等级公路路侧事故回归模型研究[J]. 公路交通科技, 2007, 24(7): 127-131. GAOHailong, KAN Weisheng, LI Changcheng. Roadside accident prediction model for two-lane highway[J]. Journal of Highway and Transportation Research and Development, 2007, 24(7): 127-131. (in Chinese)
[2] 吕晓夫, 杨亚东. 回归分析方法在船舶交通事故预测中的应用[J]. 武汉理工大学学报: 交通科学与工程版, 2006, 30(3): 546-547. Lü Xiaofu, YANG Yadong. Application of regression analysis method in vessel traffic accident forecasting[J]. Journal of Wuhan University of Technology: Transportation Science & Engineering, 2006, 30(3): 546-547. (in Chinese)
[3] 张杰, 刘晓明, 贺玉龙, 等. ARIMA模型在交通事故预测中的应用[J]. 北京工业大学学报, 2007, 33(12): 1295-1299. ZHANGJie, LIU Xiaoming, HE Yulong, et al.Application of ARIMA model in forecasting traffic accidents[J]. Journal of Beijing University of Technology, 2007, 33(12): 1295-1299. (in Chinese)
[4] 蒋宏, 方守恩, 陈雨人, 等. 基于时间序列和灰色模型的交通事故预测[J]. 交通信息与安全, 2012, 4(30): 93-98. JIANG Hong, FANG Shouen, CHEN Yuren, et al.Traffic accidents prediction based on time series and grey model[J]. Journal of Transport Information and Safety, 2012, 4(30): 93-98. (in Chinese)
[5] 蒋勋国, 刘宝新, 李百川. 灰色马尔可夫链在道路交通事故预测中的应用[J]. 人类工效学, 2006, 12(3): 26-28. JIANGE Xunguo, LIU Baoxin, LI Baichuan. The Application in the prediction of road acc idents based on gray Markov chain model[J]. Chinese Journal of Ergonomics, 2006, 12(3): 26-28. (in Chinese)
[6] 钱卫东, 刘志强. 基于灰色马尔可夫的道路交通事故预测[J]. 中国安全科学学报, 2008, 18(3): 33-36. QIANWeidong, LIU Zhiqiang. Road traffic accident forecast based on gray-Markov model[J]. China Safety Science Journal, 2008, 18(3): 33-36. (in Chinese)
[7] 唐秋生, 杜营营. 基于BP神经网络的交通事故预测模型及仿真[J]. 交通信息与安全, 2011, 29(1): 68-70. TANGQiusheng, DU Yingying. A model of traffic accident forecast based on BP neural network[J]. Journal of Transport Information and Safety, 2011, 29(1): 68-70. (in Chinese)
[8] 甘旭升, 端木京顺, 从伟, 等. 基于ARIMA与SVM的飞行事故组合预测方法[J]. 中国安全科学学报, 2011, 21(7): 79-84. GANXusheng, DUANMU Jingshun, CONG Wei, et al.Flight accident prediction method based on the combination of ARIMA and SVM[J]. China Safety Science Journal, 2011, 21(7): 79-84. (in Chinese)
[9] 王淑花. 基于时间序列模型的组合预测模型研究 [D]. 秦皇岛: 燕山大学, 2011. WANGShuhua. Research of combined forecasting model based on time series model [D]. Qinhuangdao: Yanshan University, 2011. (in Chinese)
[10] 谭满春, 李英俊, 徐建闽. 基于小波消噪的ARIMA与SVM组合交通流预测[J]. 公路交通科技, 2009, 26(7): 127-132. TAN Manchun, LI Yingjun, XU Jianmin. A hybrid ARIMA and SVM model for traffic flow prediction based on wavelet denoising[J]. Journal of Highway and Transportation Research and Development, 2009, 26(7): 127-132. (in Chinese)
[11] 姚智胜, 邵春福, 熊志华. 基于小波包和最小二乘支持向量机的短时交通流组合预测方法研究[J]. 中国管理科学, 2007, 5(1): 64-68. YAOZhisheng, SHAO Chunfu, XIONG Zhihua. Research on short-term traffic flow combined forecasting based on wavelet package and least square support vector machines[J]. Chinese Journal of Management Science, 2007, 5(1): 64-68. (in Chinese)
[12] 房靖, 高尚. 基于支持向量机的交通事故组合预测方法研究[J]. 交通与计算机, 2007, 25(2): 103-105. FANGJing, GAO Shang. Traffic accidents combining forecasting method based on support vector machine[J]. Computer and Communications, 2007, 25(2): 103-105. (in Chinese)
[13] 徐国祥. 统计预测和决策 [M]. 上海: 上海财经大学出版社, 1998: 174-176.
[14] 王燕. 应用时间序列分析(第三版) [M]. 北京: 中国人民大学出版社, 2005: 206.
[15] 喻胜华, 肖雨峰. 基于信息粒化和支持向量机的股票价格预测[J]. 财经理论与实践, 2011, 32(6): 44-47. YUShenghua, XIAO Yufeng. Forecasting method of stock price based on information granulation and support vector machine[J]. The Theory and Practice of Finance and Economics, 2011, 32(6): 44-47. (in Chinese)
[16] 董春娇, 邵春福, 谢坤, 等. 道路网交通流状态变化趋势判别方法[J]. 同济大学学报: 自然科学版, 2012, 40(9): 1323-1328. DONGChunjiao, SHAO Chunfu, XIE Kun, et al.Identification of traffic state variation trend in road network[J]. Journal of Tongji University: Natural Science, 2012, 40(9): 1323-1328. (in Chinese)
[17] 田英杰. 支持向量回归机及其应用研究 [D]. 北京: 中国农业大学, 2005. TIANYingjie. Support vector regression and its applications [D]. Beijing: China Agricultural University, 2005. (in Chinese)
[1] 王远见, 傅旭东, 王光谦. 黄河流域降雨时空分布特征[J]. 清华大学学报(自然科学版), 2018, 58(11): 972-978.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 《清华大学学报(自然科学版)》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn