《计算机应用研究》|Application Research of Computers

基于非凸低秩稀疏约束的船舶交通流量预测

Vessel traffic flow prediction using non-convex low-rank and sparsity constraints

免费全文下载 (已被下载 次)  
获取PDF全文
作者 杨双双,吴传生,刘钊,刘文,刘敬贤
机构 1.武汉理工大学 理学院,武汉 430070;2.武汉理工大学 航运学院,武汉 430063;3.内河航运技术湖北省重点实验室,武汉 430063
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2018)01-0043-05
DOI 10.3969/j.issn.1001-3695.2018.01.008
摘要 为有效预测船舶交通流量,利用非凸低秩稀疏分解模型将交通流量数据分解成低秩和稀疏两部分;然后采用自回归移动平均(autoregressive integrated moving average,ARIMA)模型分别预测低秩和稀疏部分,进而合并得到最终的船舶交通流量预测结果。最后以天津港2003—2014年船舶交通流量历史数据为例进行模型验证和预测分析,实验结果表明,非凸低秩稀疏分解模型能反映船舶交通流量的季节变化规律,较灰色系统、神经网络及组合预测模型能够显著地提高预测精度,为船舶交通流量预测提供了一种新的预测方法。
关键词 船舶交通流量;预测;非凸优化;交替方向乘子法;广义迭代阈值算法
基金项目 国家自然科学基金资助项目(51179147,51609195)
湖北省科技支撑计划资助项目(对外科技合作)(2015BHE004)
本文URL http://www.arocmag.com/article/01-2018-01-008.html
英文标题 Vessel traffic flow prediction using non-convex low-rank and sparsity constraints
作者英文名 Yang Shuangshuang, Wu Chuansheng, Liu Zhao, Liu Wen, Liu Jingxian
机构英文名 1.SchoolofSciences,WuhanUniversityofTechnology,Wuhan430070,China;2.SchoolofNavigation,WuhanUniversityofTechnology,Wuhan430063,China;3.HubeiKeyLaboratoryofInlandShippingTechnology,Wuhan430063,China
英文摘要 In order to predict the vessel traffic flow effectively, this paper used the non-convex low rank plus sparse decomposition model to decompose the traffic flow data into two parts with low rank matrix and sparse matrix. Then the framework used autoregressive integrated moving average (ARIMA) model to predict the low rank and sparse part respectively, and obtained the final result. Based on the data of vessel traffic flow in Tianjin port during 2003 to 2014, the results show that this model can reflect the seasonal variation of vessel traffic flow when compared with the gray system, neural network and combined forecasting model. It improves the prediction accuracy significantly and provides a new prediction method for vessel traffic flow.
英文关键词 vessel traffic flow; prediction; non-convex optimization; alternating direction method of multipliers; generalized iterated shrinkage algorithm
参考文献 查看稿件参考文献
  [1] 杨翔. 船舶交通流量预测方法研究[D] . 大连:大连海事大学, 2006.
[2] 吕靖, 方祥麟. 船舶交通量的组合系统预测模型与方法[J] . 大连海事大学学报, 1996, 22(2):33-35.
[3] 刘敬贤, 张涛, 刘文. 船舶交通流组合预测方法研究[J] . 中国航海, 2009, 32(3):80-84.
[4] 陈秀瑛, 古浩. 灰色线性回归模型在港口吞吐量预测中的应用[J] . 水运工程, 2010, 14(5):89-92.
[5] 沈振, 王捷. 基于灰色预测模型的长三角水运量预测[J] . 中国航海, 2010, 33(3):101-104.
[6] 田燕华, 陈锦标. 基于BP神经网络的船舶交通流量预测研究[J] . 船海工程, 2010, 39(1):122-125.
[7] 郝勇, 王怡. 基于优化RBF网络的港口船舶交通流量预测[J] . 中国航海, 2014, 37(2):81-84.
[8] Yang Shiming, Kalpakis K, Biem A. Detecting road traffic events by coupling multiple timeseries with a nonparametric bayesian method[J] . IEEE Trans on Intelligent Transportation Systems, 2013, 15(5):1936-1946.
[9] 游庆山, 徐海文, 雷开洪. 基于主成分追踪的航空货运量预测研究[J] . 武汉理工大学学报, 2013, 35(5):73-77.
[10] Wright J, Peng Yigang, Ma Yi, et al. Robust principal component analysis:exact recovery of corrupted low-rank matrices by convex optimization[C] //Advances in Neural Information Processing Systems. 2009:2080-2088.
[11] Shao Wenze, Ge Qi, Gan Zongliang, et al. A generalized robust mi-nimization framework for low-rank matrix recovery[C] //Proc of Mathematical Problems in Engineering. 2014:1-8.
[12] He Bingsheng, Yuan Xiaoming. On the O(1/t) convergence rate of alternating direction method[EB/OL] . (2011-09-31)[2016-10-07] . http://www. optimiz-ation-online. org/DB_HTML/2011/09/3157. html.
[13] Boyd S, Parikh N, Chu E, et al. Distributed optimization and statistical learning via the alternating direction method of multipliers[J] . Foundations and Trends in Machine Learning, 2011, 3(1):1-122.
[14] Cai Jianfeng, Candes E J, Shen Zuowei. A singular value thresholding algorithm for matrix completion[J] . SIAM Journal on Optimization, 2010, 20(4):1956-1982.
[15] Lyu Qin, Lin Zhouchen, She Yiyuan, et al. A comparison of typical lp minimization algorithms[J] . Neurocomputing, 2013, 119(16):413-424.
[16] Zuo Wangmeng, Meng Deyu, Zhang Lei, et al. A generalized iterated shrinkage algorithm for non-convex sparse coding[C] //Proc of IEEE International Conference on Computer Vision. Sydney:IEEE Xplore, 2013:217-224.
[17] Xu Dongwei, Dong Honghui, Li Haijian, et al. The estimation of road traffic states based on compressive sensing[J] . Transportmetrica B:Transport Dynamics, 2015, 3(2):131-152.
收稿日期 2016/8/9
修回日期 2016/10/10
页码 43-47
中图分类号 TP399
文献标志码 A