Short-Term Prediction of Passenger Demand in Multi-Zone Level: Temporal Convolutional Neural Network With Multi-Task Learning
Short-Term Prediction of Passenger Demand in Multi-Zone Level: Temporal Convolutional Neural Network With Multi-Task Learning
复制标题
多区域层面客运需求的短期预测：具有多任务学习的时域卷积神经网络
DOI：
10.1109/tits.2019.2909571
复制
发表时间：
2020-04-01
影响因子：
8.5
通讯作者：
Zheng, Liang
中科院分区：
文献类型：
--
作者：
Zhang, Kunpeng;Liu, Zijian;Zheng, Liang
准确的短期旅客需求预测有助于协调交通供需。本文提出了一种端到端多任务学习时间卷积神经网络（MTL-TCNN）来预测多区域级别的短期乘客需求。与称为时空动态时间规整（ST-DTW）算法的特征选择器一起，所提出的 MTL-TCNN 非常适合考虑时空相关性的多任务预测问题。然后，基于中国成都滴滴出行的叫车需求数据和纽约市的出租车需求数据，数值结果表明MTL-TCNN优于经典方法（即历史平均值（HA）、v-支持向量机（v-SVM）和XGBoost）和最先进的深度学习方法（例如长短期记忆（LSTM）和卷积LSTM） （ConvLSTM）]在单任务学习（STL）和多任务学习（MTL）场景中。总之，所提出的带有 ST-DTW 算法的 MTL-TCNN 是多区域级别短期乘客需求预测的一种有前途的方法。
Accurate short-term passenger demand prediction contributes to the coordination of traffic supply and demand. This paper proposes an end-to-end multi-task learning temporal convolutional neural network (MTL-TCNN) to predict the short-term passenger demand in a multi-zone level. Along with a feature selector named spatiotemporal dynamic time warping (ST-DTW) algorithm, this proposed MTL-TCNN is quite qualified for the multi-task prediction problem with the consideration of spatiotemporal correlations. Then, based on the car-calling demand data from Didi Chuxing, Chengdu, China, and taxi demand data from the New York City, the numerical results show that the MTL-TCNN outperforms both classic methods (i.e., historical average (HA), v -support vector machine (v -SVM), and XGBoost) and the state-of-the-art deep learning approaches [e.g., long short-term memory (LSTM) and convolutional LSTM (ConvLSTM)] in both the single task learning (STL) and multi-task learning (MTL) scenarios. In summary, the proposed MTL-TCNN with the ST-DTW algorithm is a promising method for short-term passenger demand prediction in a multi-zone level.