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

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。

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.