基于多源数据和响应面优化的公交客流预测深度学习方法  

Deep learning method for bus passenger flow prediction based on multi-source data and surrogate-based optimization

作　　者：巫威眺[1] 曾坤 周伟 李鹏 靳文舟[1] WU Wei-tiao;ZENG Kun;ZHOU Wei;LI Peng;JIN Wen-zhou(School of Civil Engineering and Transportation,South China University of Technology,Guangzhou 510641,China;School of Automotive and Transportation Engineering,Shenzhen Polytechnic,Shenzhen 518055,China)

机构地区：[1]华南理工大学土木与交通学院,广州510641 [2]深圳职业技术学院汽车与交通学院,广东深圳518055

出　　处：《吉林大学学报（工学版）》2023年第7期2001-2015,共15页Journal of Jilin University:Engineering and Technology Edition

基　　金：国家自然科学基金项目(72071079,52272310);广州市重点研发计划项目(202206030005,202103050002,202206010056);广东省基础与应用基础研究基金项目(2020A1515111024,2023A1515011696).

摘　　要：提出一种可扩展的深度学习框架实现多源数据预测公交客流。首先,在4个外部因素的基础上,引入3个内部因素作为公交线路客流的解释变量;其次,利用方差缩减法验证了内外部因素之间的耦合关系以及捕获多源数据耦合关系的必要性;然后,利用卷积神经网络中卷积运算处理二维数据的优势,将客流影响因素图像化,构建出小时客流细分矩阵适应其卷积运算,捕获多源数据之间的耦合性。为进一步提高预测性能,将矩阵结构优化问题转化为旅行商问题,运用响应面优化方法对客流细分矩阵结构进行高效优化。最后,以广州市281路公交线路实际数据为例进行验证,结果表明:通过优化小时客流细分矩阵结构,可以有效提高公交客流预测精度,实现数据资源的最优化利用;内部因素的独立效应不显著,而外部因素和内部因素的联合效应却作用显著;在预测精度上,与仅考虑外部因素的结果和其他深度学习模型相比存在一定优势。A scalable deep learning framework is proposed to leverage multi-source data in bus passenger flow prediction.First,on the basis of four external factors,three internal factors are introduced as explanatory variables of passenger flow of a bus route.The variance reduction method is used to verify the linkage relationship between internal factors and external factors,and the necessity of capturing the linkage relationship of multi-source data.Then,by utilizing the advantages of convolutional operations of convolutional neural networks in handling two-dimensional data,the influential factors of passenger flow are visualized and an hourly passenger flow subdivision matrix is constructed to adapt to convolutional operations,such that the linkage between multi-source data is captured.To further improve the prediction performance,the matrix structure optimization problem is transformed into a Traveling Salesman Problem,and the surrogate-based optimization technique is used to efficiently optimize the structure of hourly passenger flow subdivision matrix.Finally,the data from Route-281 bus in Guangzhou,China was used as an example for validation.The results show that,through optimizing the structure of hourly passenger flow subdivision matrix,the prediction accuracy can be effectively improved,and optimal usage of data resources can be achieved.The independent effect of internal factors was not significant,whereas the combined effect of external and internal factors is significant.In terms of prediction accuracy,the proposed method has certain advantages compared to the results only considering external factors and other deep learning models.

关 键 词：交通运输系统工程 客流预测 深度学习 公交客流 多源数据 响应面优化 

分 类 号：U491.1[交通运输工程—交通运输规划与管理]