基于融合模型动态权值的短期客流预测方法

PDF(1508 KB)

交通运输研究 ›› 2019, Vol. 5 ›› Issue (4) : 127-132.

城市交通

基于融合模型动态权值的短期客流预测方法

马晓旦,武经纬,梁士栋,赵天羽

作者信息 +

Short-Term Passenger Flow Prediction Method Based on Dynamic Weight of Fusion Model

Ma Xiao-dan, Wu Jing-wei, Liang Shi-dong and Zhao Tian-yu

Author information +

文章历史 +

摘要

针对传统交通系统中短期客流预测精度低的问题，考虑城市交通站点客流数据在横纵向时间序列的规律性，基于卡尔曼滤波算法和K近邻（K-Nearest Neighbor, ANN）算法，分别根据当日数据和历史数据对客流量进行预测，然后利用权重系数方程对两个预测值加以融合，从而构建基于融合模型动态权值的短期客流预测方法。以某城市的某公交站点客流数据为研究对象，对所建融合模型短期客流预测的准确性和适用性加以验证。结果表明，新建模型、单一的卡尔曼滤波模型和KNN模型的平均相对误差分别为3.6%, 9.0%和7.7%，可见新建模型能更好地拟合客流变化趋势且评价效率更高。

Abstract

In order to solve the problem of low accuracy of short-term passenger flow prediction in traditional transportation system, considering the regularity of transverse and longitudinal time series for passenger flow data at urban traffic stations, the short-term passenger flow was predicted according to current data and historical data respectively based on Kalman filter algorithm and K-Nearest Neighbor(KNN) algorithm respectively. By using the dynamic weights coefficient equation to fuse the two predicting values of the Kalman filter algorithm and KNN algorithm, a new short-term passenger flow prediction method based on the fusion model was constructed. Taking the passenger flow data of a bus station in one city as an example, the accuracy and applicability of the proposed fusion model for short-term passenger flow prediction was verified. The results show that the average relative error of the new model, the single Kalman filter model and KNN model is 3.6%, 9.0% and 7.7%. It means that the new model can better fit the trend of passenger flow and has higher efficiency.

导出引用

马晓旦,武经纬,梁士栋,赵天羽. 基于融合模型动态权值的短期客流预测方法[J]. 交通运输研究. 2019, 5(4): 127-132

Ma Xiao-dan, Wu Jing-wei, Liang Shi-dong and Zhao Tian-yu. Short-Term Passenger Flow Prediction Method Based on Dynamic Weight of Fusion Model[J]. Transport Research. 2019, 5(4): 127-132

参考文献

[1] 蒋婷婷. 基于鸡群算法的小波神经网络短时交通流预测研究[D]. 成都：西南交通大学，2018.
[2] 张多. 基于支持向量回归机和多变量相空间重构的短时交通流预测[D]. 重庆：重庆交通大学，2014.
[3] Mei D, Xu E, Yan Q. Short-term Traffic Flow Prediction Method Based on Grey Adaptive Particle Swarm Support Vector Machine[C]// Proceedings of 2016 2nd IEEE Internationl Conference on Computer & Communications (ICCC). Chengdu: IEEE, 2016: 1294-1298.
[4] Yang H J, Hu X. Wavelet Neural Network with Improved Genetic Algorithm for Traffic Flow Time Series Prediction[J]. Optik-International Journal for Light and Electron Optics, 2016, 127(19): 8103-8110.
[5] Jiang X S, Zhang L, Chen X Q. Short-term Forecasting of High-Speed Rail Demand: A Hybrid Approach Combining Ensemble Empirical Mode Decomposition and Gray Support Vector Machine with Real-World Applications in China[J]. Transportation Research Part C: Emerging Technologies, 2014, 44(4): 110-127.
[6] 罗向龙，焦琴琴，牛力瑶，等. 基于深度学习的短时交通流预测[J]. 计算机应用研究，2017，34（1）：91-93.
[7] 高慧，赵建玉，贾磊. 短时交通流预测方法综述[J]. 济南大学学报（自然科学版），2008（1）：88-94.
[8] Van Hinsbergen C P I, Van Lint J W C, Van Zuylen H J. Bayesian Committee of Neural Networks to Predict Travel Times with Confidence Intervals[J]. Transportation Research Part C: Emerging Technologies, 2009, 17(5): 498-509.
[9] Polson N, Sokolov V. Deep Learning Predictors for Traffic Flows[J]. Transportation Research Part C: Emerging Technologies, 2017, 79: 1-17.
[10] Cong Y L, Wang J W, Li X L. Traffic Flow Forecasting by A Least Squares Support Vector Machine with a Fruit Fly Optimization Algorithm[J]. Procedia Engineering, 2016, 137: 59-68.
[11] 邹艾娟，尤子菻，吴丹. 基于ARIMA模型的高速公路交通量短期预测[J]. 国防交通工程与技术，2015，13（6）：34-36.
[12] 刘亚迪. 基于开方变换和偏最小二乘的交通流预测优化[D]. 天津：天津大学，2016.
[13] 郭建校. 改进的高维非线性偏最小二乘回归模型及应用[M]. 北京：中国物资出版社，2010.
[14] 唐小我，马永开，曾勇，等. 现代组合预测和组合投资决策方法及应用[M]. 北京：科学出版社，2003.
[15] Marcot B G, Penman T D. Advances in Bayesian Network Modelling: Integration of Modelling Technologies[J]. Environmental Modelling & Software, 2018, 111: 386-393.