The invention discloses an underground space passenger flow prediction method and system based on TCN-LSTM, and the method comprises the steps: firstly obtaining the passenger flow data of each historical day of an underground space, then carrying out the preprocessing of the passenger flow data, dividing the passenger flow data according to the time granularity, and obtaining the passenger flow data of each time period of the underground space; matching the passenger flow data of each time period with corresponding feature data; then a fusion network model based on a TCN time sequence convolutional neural network and an LSTM long and short term memory network is constructed and trained, a self-attention mechanism is introduced to the output end of the LSTM network model, and a BWO optimization algorithm is adopted to perform hyper-parameter optimization on the fusion network model; and finally, passenger flow prediction is carried out according to the trained fusion network model. The method solves the problems that an existing passenger flow prediction method cannot consider sudden change factors, is poor in real-time performance, is too complex in model due to data volume redundancy, and is difficult to accurately predict the passenger flow, and can achieve the accurate prediction of the underground space passenger flow.
本发明公开了一种基于TCN‑LSTM的地下空间客流预测方法及系统,该方法首先获取地下空间各历史日的客流数据,然后对客流数据进行预处理并按照时间粒度进行划分,得到该地下空间的各时间段的客流数据,对各时间段的客流数据匹配对应的特征数据;再然后构建基于TCN时序卷积神经网络和LSTM长短时记忆网络的融合网络模型并训练,在LSTM网络模型输出端引入自注意力机制,并采用BWO优化算法对融合网络模型进行超参数优化;最后根据训练后的融合网络模型进行客流预测;该方法解决了现有客流预测方法无法考虑突变因素,实时性较差、数据量冗余导致模型过于复杂,难以精准的进行客流预测等问题,能够实现地下空间客流的精准预测。
TCN-LSTM-based underground space passenger flow prediction method and system
基于TCN-LSTM的地下空间客流预测方法及系统
2024-06-11
Patent
Electronic Resource
Chinese
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / 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 |
Characteristics Analysis and Prediction of Rail Transit Passenger Flow Based on LSTM
Springer Verlag | 2023
|Short-Term Passenger Flow Prediction of Urban Rail Transit Based on SDS-SSA-LSTM
DOAJ | 2022
|PASSENGER FLOW PREDICTOR, PASSENGER FLOW PREDICTION METHOD, AND PASSENGER FLOW PREDICTION PROGRAM
European Patent Office | 2024
|