优化BP_AdaBoost算法及其交通事件检测
CSTR:
作者:
作者单位:

同济大学 交通运输工程学院;江苏科技大学 计算机科学与工程学院,江苏科技大学 计算机科学与工程学院,同济大学

中图分类号:

U491.3

基金项目:

国家八六三高技术研究发展计划(2013AA12A206);国家自然科学基金(51008143)


Improved BP_AdaBoost Algorithm and its Application in Traffic Incident Detection
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [15]
  • |
  • 相似文献 [20]
  • |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    为了及时检测出高速公路上发生的交通事件,减少由于交通事件带来的损失,提出了一种基于遗传优化的BP_AdaBoost算法用于交通事件检测.提取高速公路上下游的车流量、车速与占有率作为BP(back propagation)神经网络的输入值,利用遗传算法全局搜索的性能优化BP神经网络初始连接权值和输出阈值,再通过多个新的BP神经网络弱分类器构建成AdaBoost强分类器,设计基于遗传算法优化BP_AdaBoost算法的交通事件分类器.以在东京高速公路采集的真实数据进行性能验证,试验结果表明,该算法可以提高BP弱分类器的性能,检测率达到97%,误报率降至3.34%,适用于高速公路交通事件的检测.

    Abstract:

    In order to detect the traffic incidents occurred on highway and reduce the loss brought by traffic incident, this paper presents an improved BP_AdaBoost algorithm based on genetic algorithm for traffic incident detection. The inputs of BP(Back Propagation)neural network value are vehicle quantity, velocity and occupancy in upstream and downstream of highway. Genetic algorithm is used for each BP neural network classification model for optimizing weights and thresholds due to its performance of global searching. The optimized BP neural network model is applied as a new weak classifier,then through the AdaBoost algorithm,many of these new weak classifier is composed as strong classifier model.This improved algorithm is validated with real data from Tokyo expressway ultra sonic sensors. The experimental results show that the algorithm can improve the performance of BP weak classifier. The detection rate of improved BP_AdaBoost algorithm is up to 97%, and false alarm rate is lower to 3.34%. Experiment indicate that the algorithm is suitable for detecting highway traffic incidents.

    参考文献
    [1]Zhang K, Taylor M A P. Towards universal freeway incident detection algorithms[J]. Transportation Research Part C: Emerging Technologies, 2006, 14(2): 68-80.
    [2]Cheu R L, Srinivasan D, Teh E T. Support vector machine models for freeway incident detection [C] . Intelligent Transportation Systems, 2003.// Proceedings. 2003 IEEE. IEEE, 2003, 1: 238-243.
    [3]Jeong Y S, Castro-Neto M, Jeong M K, et al. A wavelet-based freeway incident detection algorithm with adapting threshold parameters[J]. Transportation Research Part C: Emerging Technologies, 2011, 19(1): 1-19.
    [4]张轮, 杨文臣, 刘拓, 等. 基于朴素贝叶斯分类的高速公路交通事件检测[J]. 同济大学学报: 自然科学版, 2014, 42(4): 558-563.Zhang Lun,Yang wencheng,Liu Tuo,et al. Freeway Traffic Incident Detection Based on Naive Bayesian Classification [J]. Journal of Tongji University: Natural Science Edition, 2014, 42(4): 558-563.
    [5]牛世峰, 姜桂艳, 李红伟, 等. 基于纵向时间序列的快速路交通事件检测算法[J]. 哈尔滨工业大学学报, 2011, 43(2): 144-148.Niu Shifeng,Jiang guiyan,Li hongwei,et al. Freeway traffic incident detection algorithm based on time sequence of longitudinal [J]. Journal of Harbin Institute of Technology, 2011, 43 (2): 144-148.
    [6]童飞. 基于BP神经网络的水上交通事故预测及MATLAB实现[D]. 武汉理工大学, 2005.Tong Fei. BP neural network prediction and MATLAB on water traffic accident based on the realization of [D]. Wuhan University of Technology, 2005
    [7]陈君, 李聪颖, 丁光明. 基于BP神经网络的高速公路交通安全评价[J]. 同济大学学报:自然科学版, 2008, (7):927-931.
    [8]Yu L, Yu L, Wang J, et al. Back-Propagation Neural Network for Traffic Incident Detection Based on Fusion of Loop Detector and Probe Vehicle Data[C]. //Natural Computation, 2008. ICNC '08. Fourth International Conference on. IEEE, 2008:116 - 120.
    [9]Liu Z, Liu A, Wang C, et al. Evolving neural network using real coded genetic algorithm (GA) for multispectral image classification[J]. Future Generation Computer Systems, 2004, 20:1119–1129.
    [10]Shen C, Wang L, Li Q. Optimization of injection molding process parameters using combination of artificial neural network and genetic algorithm method[J]. Journal of Materials Processing Technology, 2007, 183:412–418.
    [11]段侯峰. 基于遗传算法优化BP神经网络的变压器故障诊断[D]. 北京交通大学, 2008.Duan Houfeng. Beijing Jiaotong University transformer fault diagnosis [D]. genetic algorithm optimization based on BP neural network, 2008.
    [12]Ding S, Su C, Yu J. An optimizing BP neural network algorithm based on genetic algorithm[J]. Artificial Intelligence Review, 2011, 36:153-162.
    [13]Li Z, Lei Q, Kouying X, et al. A Novel BP Neural Network Model for Traffic Prediction of Next Generation Network[C]. //Natural Computation, Icnc 09, Fifth International Conference on. IEEE, 2009:32 - 38..
    [14]朱红斌. LVQ 神经网络在交通事件检测中的应用[J]. 计算机工程与应用, 2009, 44(34): 213-215.Zhu Hongbin. Application of neural network in traffic incident detection [J]. Computer engineering and application, 2009, 44 (34): 213-215.
    [15] 彭宇. 基于小波分析的高速公路事件检测算法[J]. 湖南交通科技, 2011, 37(3): 123-126.Peng Yu. Freeway incident detection method based on wavelet analysis [J]. Hunan traffic science and technology, 2011, 37 (3): 123-126.
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

刘庆华,丁文涛,涂娟娟,方守恩.优化BP_AdaBoost算法及其交通事件检测[J].同济大学学报(自然科学版),2015,43(12):1829~1833

复制
分享
文章指标
  • 点击次数:1990
  • 下载次数: 1132
  • HTML阅读次数: 44
  • 引用次数: 0
历史
  • 收稿日期:2015-01-29
  • 最后修改日期:2015-11-06
  • 录用日期:2015-10-10
  • 在线发布日期: 2015-12-28
文章二维码