改进人工蜂群算法优化RBF神经网络的短时交通流预测

摘要/Abstract

摘要：

为了提高径向基函数RBF神经网络预测模型对短时交通流的预测准确性，提出了一种基于改进人工蜂群算法优化RBF神经网络的短时交通流预测模型。利用改进人工蜂群算法确定RBF网络隐含层的中心值以及隐含层单元数，然后训练改进的人工蜂群算法RBF神经网络预测模型，并将其应用到某城市4天的短时交通流量数据的验证。将实验结果与传统RBF神经网络预测模型、BP神经网络预测模型和小波神经网络预测模型进行了比较。对比结果表明，该方法对短时交通流具有更高的预测准确性。

关键词: 交通流预测, RBF神经网络, BP神经网络, 小波神经网络, 人工蜂群算法

Abstract:

In order to improve the prediction accuracy of radial basis function (RBF) neural network model for shortterm traffic flow, we propose a prediction model for shortterm traffic flow of optimized RBF neural networks based on the modified artificial bee colony (ABC) algorithm. The modified ABC algorithm is used to confirm center value and unit numbers of the hidden layers of the RBF neural networks. Then the modified RBF neural network prediction model is trained, and the efficiency of the proposed prediction model is tested through simulations on the shortterm traffic flow data of a city in four days. Experimental results of the proposed model are compared with the traditional RBF neural network model, the BP neural network model and the wavelet neural network model, which verify the higher prediction accuracy of the proposed method.

Key words: traffic flow prediction;RBF neural network;BP neural network;wavelet neural network;artificial bee colony algorithm

黄文明，徐双双，邓珍荣，雷茜茜. 改进人工蜂群算法优化RBF神经网络的短时交通流预测[J]. J4, 2016, 38(04): 713-719.

HUANG Wenming，XU Shuangshuang，DENG Zhenrong,LEI Qianqian. Shortterm traffic flow prediction of optimized RBF neural
networks based on the modified ABC algorithm [J]. J4, 2016, 38(04): 713-719.

参考文献［16］

［1］	Okutani I,Stephanedes Y J.Dynamic prediction of traffic volume through Kalman filtering theory［J］.Transportation Research Part B:Methodological,1984,18(1):111.
［2］	Vlahogianni E I,Karlaftis M G,Golias J C.Optimized and metaoptimized neural networks for shortterm traffic flow prediction:A genetic approach ［J］.Transportation Research Part C:Emerging Technologies,2005,13(3):211234.
［3］	Liu Yang,Ma Feng.Nonparametric regression for shortterm traffic flow forecasting based on cluster analysis［J］.Journal of Transportation Information and Safety,2013,31(2):2732.(in Chinese)
［4］	Gong Xiaoyan,Tang Shuming.Integrated traffic flow forecasting and traffic incident detection algorithm based on nonparametric regression［J］.China Journal of Highway and Transport,2003,16(1):5256.(in Chinese)
［5］	Jia Xianchao,Chen Xumei,Gong Jinli,et al.Multistep shortterm traffic flow prediction based on chaotic theory［J］.Journal of Transportation Information and Safety,2013,31(6):2735.(in Chinese)
［6］	Li Song,Liu Lijun,Xie Yongle.Chaotic prediction for shortterm traffic flow of optimized BP neural network based on genetic algorithm［J］.Control and Decision,2011,26(10):15811585.(in Chinese)
［7］	Hong W C,Dong Y C,Zheng F F,et al.Forecasting urban traffic flow by SVR with continuous ACO ［J］.Applied Mathematical Modeling,2011,35(3):12821291.
［8］	Fu Gui,Han Guoqiang,Lu Feng,et al.Shortterm traffic flow forecasting model based on support vector machine regression［J］.Journal of South China University of Technology,2013,41(9):7176.(in Chinese)
［9］	Yu Bin, Wu Shanhua, Wang Minghua,et al.Knearest neighbor model of shortterm traffic flow forecast［J］.Journal of Traffic and Transportation Engineering,2012,12(2):105111.(in Chinese)
［10］	Li Song, Liu Lijun, Zhai Man. Prediction for shortterm traffic flow based on modified PSO optimized BP neural network［J］.Systems EngineeringTheory & Practice,2012,32(9):20452049.(in Chinese)
［11］	Li Jingyu,Li Qiqiang,Hou Haiyan,et al.Traffic flow prediction based on the wavelet neural network with genetic algorithm［J］.Journal of Shandong University,2007,37(2):109112.(in Chinese)
［12］	Deng Jie,Lu Baichuan,Liu Quanfu,et al.Forecasting model of trip generation based on RBF neural network［J］.Journal of WUT(Information & Management Engineering),2014,36(1):4348.(in Chinese)
［13］	Jiang Zongli.Introduction to artificial neural networks［M］.Beijing:Higher Education Press,2001.(in Chinese)
［14］	Karaboga D,Basturk B.On the performance of artificial bee colony (ABC) algorithm［J］.Applied Soft Computing,2008,8(1):687697.
［15］	Wang Xudong, Shao Huihe. Application of RBF neural network in theory and control［J］.Information and Control,1997,26(4):5665.(in Chinese)
［16］	Yang Xiaoqin,Li Ming,Zhou Linxia.Entropy based genetic algorithm with dual subpopulations［J］.Pattern Recogni
	tion and Artificial Intelligence,2005,18(3):286289.(in Chinese)
［17］	Chun J S,Kim M K,Jung H K.Shape optimization of electromagnetic devices using immune algorithm［J］.IEEE Transactions on Magnetics,1997,33(2):18761879.
［18］	Bbeeaou M,Slarry P.A genetic algorithm with realvalue coding to optimize multimodal continuous functions［J］.Structure Multidiscipline Optimization,2001,23(1):6374.
	附中文参考文献：
［3］	刘洋，马峰.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32.
［4］	宫晓燕，汤淑明.基于非参数回归的短时交通流量预测与事件检测综合算法［J］.中国公路学报，2003，16(1)：5256.
［5］	贾显超，陈旭梅，弓晋丽，等.基于混沌理论的短期交通流量多步预测［J］.交通信息与安全，2013，31(6):2735.
［6］	李松，刘力军，解永乐.遗传算法优化BP神经网络的短时交通流混沌预测［J］.控制与决策，2011，26(10):15811585.
［8］	傅贵，韩国强，逯峰，等.基于支持向量机回归的短时交通流预测模型［J］.华南理工大学学报，2013，41(9):7176.
［9］	于滨，邬珊华，王明华，等.K近邻短时交通流预测模型［J］.交通运输工程学报，2012，12(2):105111.
［10］	李松，刘力军，翟曼.改进粒子群算法优化BP神经网络的短时交通流预测［J］.系统工程理论与实践，2012，32(9):20452049.
［11］	李婧瑜，李歧强，侯海燕，等.基于遗传算法的小波神经网络交通流预测［J］.山东大学学报，2007，37(2):109112.
［12］	邓捷，陆百川，刘权富，等.基于RBF神经网络的交通生成预测模型［J］.武汉理工大学学报（信息与管理工程版），2014，36(1):4348.
［13］	蒋宗礼.人工神经网络导论［M］.北京：高等教育出版社，2001.
［15］	王旭东，邵惠鹤.RBF神经网络理论及在控制中的应用.信息与控制，1997,26(4):5665.
［16］	杨小芹，黎明，周琳霞.基于熵的双群体遗传算法研究［J］.模式识别与人工智能，2005,18(3):286289.

[1]	谢俊标, 江峰, 杜军威, 赵军. 基于改进人工鱼群算法与RBF神经网络的股票价格预测[J]. 计算机工程与科学, 2022, 44(11): 2080-2090.
[2]	周伯荣, 程伟国, 许镇义, 温秀兰. 基于改进在线极限学习机的短时交通流预测模型研究[J]. 计算机工程与科学, 2022, 44(05): 944-950.
[3]	庄鹤林, 杨火根, 夏小云, 廖伟志. 关于矩阵乘法问题的人工蜂群优化算法研究[J]. 计算机工程与科学, 2021, 43(12): 2131-2138.
[4]	胡新荣, 刘嘉文, 刘军平, 彭涛, 何儒汉, . 基于改进GA-BP-MC神经网络的人体三维尺寸预测[J]. 计算机工程与科学, 2021, 43(08): 1443-1453.
[5]	邓翔宇, 张屹南, 杨雅涵. 一种用于交通标识分类的形状识别算法[J]. 计算机工程与科学, 2021, 43(02): 322-328.
[6]	沈晓燕, 王雪梅, 王燕. 基于样本熵和模式识别的脑电信号识别算法研究[J]. 计算机工程与科学, 2020, 42(08): 1482-1488.
[7]	包敏泽, 胡秀婷, 谢玉莹, 蒋波. 基于人工蜂群算法的p-center问题求解算法[J]. 计算机工程与科学, 2020, 42(06): 1127-1133.
[8]	赵凤1,2，孔令润1,2，马改妮1,2. 多目标粒子群和人工蜂群混合优化的阈值图像分割算法[J]. 计算机工程与科学, 2020, 42(02): 281-290.
[9]	陈丽芳,冯力静,刘保相. 神经网络规则优化建模与应用[J]. 计算机工程与科学, 2019, 41(12): 2247-2254.
[10]	吴曼曼1，徐建新 1，2. 基于EMD改进的Elman神经网络对股票的短期预测模型[J]. 计算机工程与科学, 2019, 41(06): 1119-1127.
[11]	文常保，马文博，刘鹏里. 基于改进遗传算法的RBF神经网络结构优化研究[J]. 计算机工程与科学, 2019, 41(05): 917-923.
[12]	常小刚1，赵红星2. 动态调节因子的邻域搜索人工蜂群算法[J]. 计算机工程与科学, 2019, 41(04): 673-681.
[13]	张毅，张珉浩. 基于机器学习的能力评价与匹配研究[J]. 计算机工程与科学, 2019, 41(02): 363-369.
[14]	丁红卫，万良，邓烜堃. 改进的HS算法优化BP神经网络的入侵检测研究[J]. 计算机工程与科学, 2019, 41(01): 65-72.
[15]	张莹杰，张树群. 改进约束鸡群算法在神经网络的应用[J]. 计算机工程与科学, 2018, 40(12): 2252-2257.