The invention relates to a bus arrival time prediction method based on spatial-temporal feature deep learning, and belongs to the field of traffic information big data, and the method comprises the following steps: S1, generating a bus arrival and departure time table and a card punching number table of vehicles at each station; s2, time features and space features are extracted through feature correlation analysis; s3, performing feature selection on the time features and the space features by using a Pearson correlation coefficient, and performing data fusion to obtain fused prediction data; s4, sorting the corresponding fusion prediction data to obtain time sequence prediction data; s5, building a bus arrival time prediction model; and S6, processing the time sequence prediction data by using the bus arrival time prediction model to obtain a bus arrival time prediction value. According to the method, the time domain information and the frequency domain information of the data are reserved, global spatiotemporal feature information learning is carried out on the data, and the accuracy of bus arrival time prediction can be effectively improved.
本发明涉及基于时空特征深度学习的公交车到站时间预测方法,属于交通信息大数据领域,包含以下步骤:S1、生成公交车到站出站时刻表和车辆每站打卡人数表;S2、采用特征相关性分析提取时间特征和空间特征;S3、利用Pearson相关系数对所述的时间特征和空间特征进行特征选择,并进行数据融合,得到融合预测数据;S4、对应的融合预测数据进行排序,得到时间序列预测数据;S5、搭建公交车到站时间预测模型;S6:利用公交车到站时间预测模型对时间序列预测数据进行处理,得到公交车到站时间预测值。本发明保留了数据的时域信息和频域信息,对数据进行全局时空特征信息的学习,能够有效提高对公交车到站时间预测的准确率。
Bus arrival time prediction method based on spatial-temporal feature deep learning
基于时空特征深度学习的公交车到站时间预测方法
17.10.2023
Patent
Elektronische Ressource
Chinesisch
IPC: | G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES / G01S RADIO DIRECTION-FINDING , Funkpeilung / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / H04W WIRELESS COMMUNICATION NETWORKS , Drahtlose Kommunikationsnetze |
ARRIVAL TIME PREDICTION METHOD, ARRIVAL TIME PREDICTION DEVICE, AND ARRIVAL TIME PREDICTION PROGRAM
Europäisches Patentamt | 2022
|Full-period traffic flow prediction method based on spatial-temporal feature deep fusion
Europäisches Patentamt | 2025
|Flight Arrival Delay Prediction Using Deep Learning
IEEE | 2024
|Vehicle arrival time prediction method based on representation learning
Europäisches Patentamt | 2024
|IDA-RNN model-based spatial dimension bus arrival time prediction method
Europäisches Patentamt | 2023
|