| CLAB模型：一种乘客出租出行需求短时预测的深度学习模型 |
| |
| 引用本文： | 周榆欣,邬群勇.CLAB模型：一种乘客出租出行需求短时预测的深度学习模型[J].地球信息科学,2023,25(1):77-89. |
| |
| 作者姓名： | 周榆欣 邬群勇 |
| |
| 作者单位： | 1.福州大学 空间数据挖掘与信息共享教育部重点实验室，福州 3501082.卫星空间信息技术综合应用国家地方联合工程研究中心，福州 3501083.数字中国研究院（福建），福州 350003 |
| |
| 基金项目： | 国家自然科学基金项目(41471333);福建省科技计划引导项目(2021H0036) |
| |
| 摘 要： | 乘客出行需求预测是智能交通系统的组成部分，准确的出行需求预测，对于车辆调度具有重要的意义；然而现有的预测方法无法准确的挖掘其潜在的时空相关性，且大都忽略历史流入量对出行需求的影响。为了进一步挖掘时空大数据中的时空特性及提升模型预测乘客出行需求的精度，本文提出了一种乘客出租出行需求短时预测CLAB(Conv-LSTM Attention BiLSTM)模型。CLAB模型设置了3个模块分别为基于注意力机制的Conv-LSTM模块和2个BiLSTM模块，基于注意力机制的Conv-LSTM模块提取临近时刻乘客出行需求量中的空间特征和短时时间特征，其中注意力机制能自动分配不同的权重来判别不同时间的需求量序列重要性；为了探索长期时间特征，用2个BiLSTM模块来提取历史流入量序列时间特征和日乘客需求量序列的时间特征。采用厦门岛的网约车和巡游车的订单数据进行实验，结果表明：(1) CLAB模型更适用于使用30 min历史数据预测未来5 min短时乘客出行需求；(2)与基准预测模型相比，CLAB模型的整体的效果误差更低，具有更好的预测效果，CLAB模型比CNN-LSTM、LSTM、BiLSTM、CNN...
|
| 关 键 词： | 交通大数据 出行需求预测 深度神经网络 注意力机制 组合预测模型 时空融合 厦门岛 LSTM |
| 收稿时间： | 2022-09-06 |
CLAB Model: A Deep Learning Model for Short-term Prediction of Passenger Rental Travel Demand |
| |
| ZHOU Yuxin,WU Qunyong.CLAB Model: A Deep Learning Model for Short-term Prediction of Passenger Rental Travel Demand[J].Geo-information Science,2023,25(1):77-89. |
| |
| Authors: | ZHOU Yuxin WU Qunyong |
| |
| Institution: | 1. Key Lab of Spatial Data Mining and Information Sharing of Ministry of Education, Fuzhou University, Fuzhou 350108, China2. National & Local Joint Engineering Research Center of Satellite Geospatial Information Technology, Fuzhou 350108, China3. The Academy of Digital China (Fujian), Fuzhou 350003, China |
| |
| Abstract: | Passenger travel demand prediction is an integral part of intelligent transportation systems, and accurate travel demand prediction is of great significance for vehicle scheduling. However, existing prediction methods are unable to accurately explore its potential spatiotemporal correlation and mostly ignore the impact of historical inflow on travel demand. In order to further exploit the spatiotemporal characteristics of spatiotemporal big data and improve the accuracy of the model in predicting passenger travel demand, this paper proposes a Conv-LSTM Attention BiLSTM (CLAB) model for short-time prediction of passenger rental travel demand. The attention-based Conv-LSTM module extracts spatial features and short-term temporal features of passenger travel demand at the near moment, where the attention mechanism automatically assigns different weights to discriminate the importance of demand sequences at different times. To explore long-term temporal features, two BiLSTM modules are used to extract temporal features of historical inflow sequences and temporal features of daily passenger temporal features of the demand series. Experiments are conducted using the order data of online and cruising taxis on Xiamen Island, and the results show that: (1) the CLAB model is more suitable for predicting the future 5-min short-time passenger travel demand using 30-min historical data; (2) the overall effect error of the CLAB model is lower and has better prediction results compared with the benchmark prediction model. The CLAB model is more effective than the CNN-LSTM, LSTM, BiLSTM, CNN, and Conv-LSTM by 33.179%, 33.153%, 33.204%, 5.401%, and 5.914% in mean absolute error (MAE) and 34.389%, 34.423%, 34.524%, 6.772%, and 6.669% in Root Mean Square Error (RMSE), respectively; (3) the CLAB model performs better for weekday prediction with higher regularity than non-working day prediction, with best prediction for weekday morning peaks. |
| |
| Keywords: | traffic big data travel demand forecasting deep neural network attention mechanism combined forecasting model spatiotemporal fusion Xiamen Island LSTM |
|
| 点击此处可从《地球信息科学》浏览原始摘要信息 |
| 点击此处可从《地球信息科学》下载免费的PDF全文 |
|
