Passenger flow prediction is the key to operation efficiency and safety of urban rail transit (URT). This paper combines the deep learning (DL) theory and support vector machine (SVM) into the DL-SVM model for URT passenger flow prediction. Firstly, the deep belief network (DBN) was adopted to extract the features and inherent variation of passenger flow data. On this basis, an SVM regression model was constructed to predict passenger flow. Then, the proposed model was compared with three shallow prediction models through experiments on Qingdao Metro. The results show that the DL-SVM outperformed the other models in accuracy and stability. The research findings shed important new light on the passenger flow prediction in the URT system.

/pdf/prediction-of-passenger-flow-in-urban-rail-transit-based-on-2dmrbzadxv.pdf

Prediction of Passenger Flow in Urban Rail Transit Based on Big Data Analysis and Deep Learning

Artificial Intelligence (AI) is becoming pervasive in most engineering domains, and railway transport is no exception. However, due to the plethora of different new terms and meanings associated with them, there is a risk that railway practitioners, as several other categories, will get lost in those ambiguities and fuzzy boundaries, and hence fail to catch the real opportunities and potential of machine learning, artificial vision, and big data analytics, just to name a few of the most promising approaches connected to AI. The scope of this paper is to introduce the basic concepts and possible applications of AI to railway academics and practitioners. To that aim, this paper presents a structured taxonomy to guide researchers and practitioners to understand AI techniques, research fields, disciplines, and applications, both in general terms and in close connection with railway applications such as autonomous driving, maintenance, and traffic management. The important aspects of ethics and explainability of AI in railways are also introduced. The connection between AI concepts and railway subdomains has been supported by relevant research addressing existing and planned applications in order to provide some pointers to promising directions.

Artificial Intelligence in Railway Transport: Taxonomy, Regulations, and Applications

Artificial Intelligence (AI) is becoming pervasive in most engineering domains, and railway transport is no exception. However, due to the plethora of different new terms and meanings associated with them, there is a risk that railway practitioners, as several other categories, will get lost in those ambiguities and fuzzy boundaries, and hence fail to catch the real opportunities and potential of machine learning, artificial vision, and big data analytics, just to name a few of the most promising approaches connected to AI. The scope of this paper is to introduce the basic concepts and possible applications of AI to railway academics and practitioners. To that aim, this paper presents a structured taxonomy to guide researchers and practitioners to understand AI techniques, research fields, disciplines, and applications, both in general terms and in close connection with railway applications such as autonomous driving, maintenance, and traffic management. The important aspects of ethics and explainability of AI in railways are also introduced. The connection between AI concepts and railway subdomains has been supported by relevant research addressing existing and planned applications in order to provide some pointers to promising directions. 

The existing rail station passenger flow prediction models are inefficient, due to that most of them use single-source data to predict. In this paper, a novel method is proposed based on multi-layer LSTM, which integrates multi-source traffic data and multi-techniques (including feature selection based on Spearman correlation and time feature clustering), to improve the performance of predicting passenger flow. The experimental results show that the multi-source data and the techniques integrated in the model are helpful, and the proposed method obtains a higher prediction accuracy which outperforms other methods (e.g. SARIMA, SVR and BP network) greatly.

Passenger Flow Forecast of Rail Station Based on Multi-Source Data and Long Short Term Memory Network

Train capacity utilization (TCU), usually represented by passenger load factor (PLF), is a critical measure of effectiveness for rail operation In literature, efforts are usually made to improve capacity utilization by optimizing rail operation and management strategies Comparably little attention is paid to analyzing the factors that affect TCU and to understanding the behavioral patterns behind it This paper applies exploratory data mining techniques to a 3-month long real world train operation data of the Beijing-Shanghai High-Speed Railway Principal component analysis (PCA) is conducted to find the principal components that can efficiently represent the collected data Clustering techniques are then applied to understand the unique characteristics that affect PLF and the travel pattern The findings can be further used to guide train operation planning and facilitate better decision-making

/pdf/analyzing-capacity-utilization-and-travel-patterns-of-2vbhpw0lpz.pdf

Analyzing Capacity Utilization and Travel Patterns of Chinese High-Speed Trains: An Exploratory Data Mining Approach

Based on analyzing the principle of BP neural network and time sequence characteristics of railway passenger flow, the forecast model of railway short-term passenger flow based on BP neural network was established. This paper mainly researches on fluctuation characteristics and short-time forecast of holiday passenger flow. Through analysis of passenger flow and then be used in passenger flow forecasting in order to guide the transport organization program especially the train plan of extra passenger train. And the result shows the forecast model based on BP neural network has a good effect on railway passenger flow prediction.

The Research of Railway Passenger Flow Prediction Model Based on BP Neural Network

This paper through studying the theory of data warehouse and data mining, applies these technologies to deal with the large number data in the Ticket Selling and Reserving System of Chinese Railway (TRS), uses the effective data mining to the passenger flow analysis, builds up the logical forecasting and analysis model. This paper firstly discusses the current situation and problems faced by forecasting of passenger flow, then applies the data warehouse technology to design the data mart of this subject. Next, samples and analyses this data which collecting in data mart adopting neural network method, builds data analysis model carrying out research and the experiment, finally puts forward a feasible forecast model for the passenger flow forecasting.

Yao Wang

Papers

The Research of Railway Passenger Flow Prediction Model Based on BP Neural Network

Application of Data Mining in the Forecasting of Railway Passenger Flow