-
摘要: 为了充分利用交通流的时空过程特性, 进行交通流的实时预测, 将过程神经元网络和数据流在线学习技术引入到短时交通流预测中。充分考虑交通流的日周期、周周期等内在特性, 结合过程神经元网络和小波变换, 实现对历史数据的多尺度过程特征处理。构建了路网整体预测过程神经元网络模型, 并采用主成分分析方法, 利用交通流空间相似性的影响对模型进行优化。基于Harr小波技术提出具有自适应和实时性预测特征的在线学习算法。试验结果表明: 该模型的预测准确性优于普通神经网络, 平均百分比相对误差降低6%~8%, 预测时间至少降低67%, 具有较高的性能, 能满足短时交通流实时预测的需求。Abstract: In order to fully utilize the spatio-temporal process characteristic of traffic flow and predict traffic flow in real time, both process neural network and the online learning technology of data stream were imported into short-term traffic prediction. Considering the inherent traffic features of daily-periodicity and weekly-periodicity, process neural network and wavelet transform were combined to deal with the multi-scale process characteristic of historical data. A road network prediction model was constructed, and was optimized by adopting principal component analysis and utilizing the influence of traffic flow space similarity. An online learning algorithm was proposed based on Hart wavelet technology, which has the characteristics of selfadaptability and real-time prediction. Experimental result shows that the forecasting accuracy of the model is better than ordinary neural networks, its relative error of mean percentage reduces by 6%-8%, and its prediction time reduces by 67% at least, so the model has good performance and can meet the demand of real-time prediction of short-term traffic flow.
-
Key words:
- traffic prediction /
- short-time traffic flow /
- process neural network /
- wavelet transform
-
[1] SUN Shi-liang, ZHANG Chang-shui. The selective random subspace predictor for traffic flow forecasting[J]. IEEE Transactions on Intelligent Transportation Systems, 2007, 8(2): 367-373. doi: 10.1109/TITS.2006.888603 [2] YU Guo-qiang, ZHANG Chang-shui. Switching ARIMA model based forecasting for traffic flow[C]∥ IEEE. IEEE International Conference on Acoustics, Speech, Signal Processing. Quebec: IEEE, 2004: 429-432. [3] GHOSH B, BASU B, O'MAHONY M. Bayesian time-series model for short-term traffic flow forecasting[J]. Journal of Transportation Engineering, 2007, 133(3): 180-189. doi: 10.1061/(ASCE)0733-947X(2007)133:3(180) [4] 杨兆升, 朱中. 基于卡尔曼滤波理论的交通流量实时预测模型[J]. 中国公路学报, 1999, 12(3): 63-67. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL199903008.htmYANG Zhao-sheng, ZHU Zhong. A real-time traffic volume prediction model based on the Kalman filtering theory[J]. China Journal of Highway and Transport, 1999, 12(3): 63- 67. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL199903008.htm [5] 何兆成, 余志. 城市道路网络动态OD估计模型[J]. 交通运输工程学报, 2005, 5(2): 94-98. doi: 10.3321/j.issn:1671-1637.2005.02.023HE Zhao-cheng, YU Zhi. Dynamic OD estimation model of urban network[J]. Journal of Traffic and Transportation Engineering, 2005, 5(2): 94-98. (in Chinese) doi: 10.3321/j.issn:1671-1637.2005.02.023 [6] SUN Shi-liang, ZHANG Chang-shui, Yu Guo-qiang. A Bayesian network approach to traffic flow forecasting[J]. IEEE Transactions on Intelligent Transportation Systems, 2006, 7(1): 124-132. doi: 10.1109/TITS.2006.869623 [7] 刘洁, 魏连雨, 杨春风. 基于遗传-神经网络的交通量预测[J]. 长安大学学报: 自然科学版, 2003, 23(1): 68-70. https://www.cnki.com.cn/Article/CJFDTOTAL-XAGL200301018.htmLIU Jie, WEI Lian-yu, YANG Chun-feng. Traffic prediction based on genetic-neural network[J]. Journal of Chang'an University: Natural Science Edition, 2003, 23(1): 68-70. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-XAGL200301018.htm [8] 何新贵, 梁久祯. 过程神经元网络的若干理论问题[J]. 中国工程科学, 2000, 2(12): 40-44. https://www.cnki.com.cn/Article/CJFDTOTAL-GCKX200012007.htmHE Xin-gui, LIANG Jiu-zhen. Some theoretical issues on procedure neural networks[J]. Engineering Science, 2000, 2(12): 40-44. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GCKX200012007.htm [9] 何新贵, 许少华. 输入输出均为时变函数的过程神经网络及应用[J]. 软件学报, 2003, 14(4): 764-769. https://www.cnki.com.cn/Article/CJFDTOTAL-RJXB200304006.htmHE Xin-gui, XU Shao-hua. Process neural network with timevaried input and output functions and its applications[J]. Journal of Software, 2003, 14(4): 764-769. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-RJXB200304006.htm [10] SONG Guo-jie, YANG Dong-qing, WU Ling, et al. A mixed process neural network and its application to churn prediction in mobile communications[C]∥ IEEE. Proceedings of the 6th IEEE International Conference on Data Mining Workshop. Hong Kong: IEEE, 2006: 798-802. [11] RENAUD O, STARCK J L, MURTAGH F. Prediction based on a multiscale decomposition[J]. International Journal of Wavelets, Multiresolution and Information Processing, 2003, 1(2): 217-232. doi: 10.1142/S0219691303000153 [12] CHEN Shao-hui, SU Hong-bo, ZHANG Ren-hua, et al. Fusing remote sensing images usingàtrous wavelet transform and empirical mode decomposition[J]. Pattern Recognition Letters, 2007, 29(3): 330-342. http://pdfs.semanticscholar.org/0b17/e8bce056a8a9ddd3a0316917057efa2b8961.pdf -
下载:
点击查看大图
图(5)
计量
- 文章访问数: 616
- HTML全文浏览量: 112
- PDF下载量: 506
- 被引次数: 0
