Multifactor prediction model for traffic accident based on grey-radial basis function neural network
-
摘要: 为实现多影响因素作用下的道路交通事故预测, 将灰色系统理论和神经网络理论相结合, 发挥灰色理论提高可用信息利用率、弱化数据序列波动性的优点及神经网络特有的非线性适应性信息处理能力, 提出道路交通事故灰色-径向基函数神经网络多元预测模型, 并以某算例进行了不同预测方法结果对比。分析结果表明: 与灰色系统预测和径向基函数神经网络预测相比, 多元预测模型平均绝对误差、平均绝对百分比误差分别降低50.0%和12.5%, 不等系数降低54.5%和16.6%, 有效度提高2.7%和0.3%, 说明该组合预测能够有效提高系统建模效率与模型精度。Abstract: In order to realize the traffic accident prediction under various road factors, a muhifactor prediction model based on grey-radial basis funetion(RBF) neural network was put forward, which combined grey system theory with neural network theory. Grey theory could improve the utilization of available information and weaken the undulation of data sequence. Neural network had the processing ability of nonlinear adaptability information. The muhifactor prediction model was compared with different prediction methods by a case. Analysis result shows that in comparison with grey prediction and RBF neural network prediction, the mean absolute error and mean absolute percent error of muhifaetor prediction model decrease by 50% and 12.5%, the Theil coefficient decreases by 54.5% and 16.6%, the validity increases by 2.7% and 0.3% respectively, so the combined prediction method can improve the efficiency of system modeling and the precision of prediction model.
-
表 1 道路影响因素原始数据
Table 1. Original data of road influence factors
表 2 模拟数据与实际数据对比
Table 2. Comparison between simulation data and actual data
表 3 精度检验结果
Table 3. Precision test results
表 4 逆归一化结果
Table 4. Results of reverse normalization
表 5 预测结果对比
Table 5. Comparison of prediction results
表 6 预测效果评价
Table 6. Estimation of prediction effects
-
[1] 王福建, 李铁强, 俞传正. 道路交通事故灰色Verhulst预测模型[J]. 交通运输工程学报, 2006, 6(1): 122-126. doi: 10.3321/j.issn:1671-1637.2006.01.026WANG Fu-jian, LI Tie-qiang, YU Chuan-zheng. Grey Verhulst predictive model of road traffic accidents[J]. Journal of Traffic and Transportation Engineering, 2006, 6(1): 122- 126. (in Chinese) doi: 10.3321/j.issn:1671-1637.2006.01.026 [2] 刘兆惠. 高等级公路交通安全综合评价及多元事故预测模型研究[D]. 长春: 吉林大学, 2007.LIU Zhao-hui. A study on comprehensive evaluation for the traffic safety of high-grade highways and multifactorial prediction model for the traffic accidents[D]. Changchun: Jilin University, 2007. (in Chinese) [3] 陈淑燕, 王炜. 交通量的灰色神经网络预测方法[J]. 东南大学学报: 自然科学版, 2004, 34(4): 541-544. doi: 10.3321/j.issn:1001-0505.2004.04.026CHEN Shu-yan, WANG Wei. Grey neural network forecasting for traffic flow[J]. Journal of Southeast University: Natural Science Edition, 2004, 34(4): 541-544. (in Chinese) doi: 10.3321/j.issn:1001-0505.2004.04.026 [4] 马超群, 王玉萍, 陈宽民, 等. 基于灰色加权关联度的城市轨道线网方案评价[J]. 长安大学学报: 自然科学版, 2007, 27(3): 84-87, 110. https://www.cnki.com.cn/Article/CJFDTOTAL-XAGL200703018.htmMA Chao-qun, WANG Yu-ping, CHEN Kuan-min, et al. Comprehensive evaluation for urban rail transit network based on grey weight relation[J]. Journal of Chang'an University: Natural Science Edition, 2007, 27(3): 84-87, 110. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-XAGL200703018.htm [5] 许洪国, 刘兆惠, 王超. 道路安全等级定权聚类评价模型及因素辨析[J]. 交通运输工程学报, 2007, 7(2): 94-98. http://transport.chd.edu.cn/article/id/200702020XU Hong-guo, LIU Zhao-hui, WANG Chao. Road safety level evaluation based on grey fixed weight clustering model and factors analysis[J]. Journal of Traffic and Transportation Engineering, 2007, 7(2): 94-98. (in Chinese) http://transport.chd.edu.cn/article/id/200702020 [6] AMIN S M, RODIN E Y, LIU A P, et al. Traffic prediction and management via RBF neural nets and semantic control [J]. Computer-Aided Civil and Infrastructure Engineering, 1998, 13(5): 315-327. doi: 10.1111/0885-9507.00110 [7] SCHILLING R J, CARROLL J R, AL-AJLOUNI A F. Approximation of nonlinear systems with radial basis function neural networks[J]. IEEE Transactions on Neural Networks, 2001, 12(1): 1-15. doi: 10.1109/72.896792 [8] 张玉梅, 曲仕茹, 温凯歌. 基于混沌和RBF神经网络的短时交通流量预测[J]. 系统工程, 2007, 25(11): 26-30. https://www.cnki.com.cn/Article/CJFDTOTAL-GCXT200711006.htmZHANG Yu-mei, QU Shi-ru, WEN Kai-ge. A short-term traffic flow forecasting method based on chaos and RBF neural network[J]. Systems Engineering, 2007, 25(11): 26- 30. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GCXT200711006.htm [9] 张刚刚, 王春生, 徐岳. 基于径向基函数神经网络的斜拉桥损伤识别[J]. 长安大学学报: 自然科学版, 2006, 26(1): 49-53. https://www.cnki.com.cn/Article/CJFDTOTAL-XAGL200601010.htmZHANG Gang-gang, WANG Chun-sheng, XU Yue. Damage detection of cable-stayed bridge based on RBF neural networks[J]. Journal of Chang'an University: Natural Science Edition, 2006, 26(1): 49-53. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-XAGL200601010.htm [10] PARK J, SANDBERG I W. Universal approximation using radial-basis-function networks[J]. Neural Computation, 1991, 3(2): 246-257. doi: 10.1162/neco.1991.3.2.246 [11] HARPHAM C, DAWSON C W. The effect of different basis functions on a radial basis function network for time series prediction: a comparative study[J]. Neurocomputing, 2006, 69(16): 2161-2170. http://fulltext.study/preview/pdf/410993.pdf -
下载:
点击查看大图
计量
- 文章访问数: 627
- HTML全文浏览量: 88
- PDF下载量: 478
- 被引次数: 0
