智慧地铁专注于铁路系统的新概念和新模式，是数据科学与工程的跨学科研究。智慧地铁是一个新兴的领域。本书介绍智慧地铁车站系统中数据科学和工程学的关键技术。本书可以为研究人员提供重要参考，并鼓励以后在智慧地铁、智能铁路、数据科学与工程、人工智能和其他相关领域进行后续研究。

Chapter 1 Exordium
1.1 Overview of data science and engineering
1.2 Framework of smart metro station systems
1.3 Human and smart metro station systems
1.4 Environment and smart metro station systems
1.5 Energy and smart metro station systems
1.6 Scope of this book
References
Chapter 2 Metro traffic flow monitoring and passenger guidance
2.1 Introduction
2.2 Description of metro traffic flow data
2.3 Prediction of metro traffic flow based on Elman neural network
2.4 Prediction of metro traffic flow based on deep echo state network
2.5 Passenger guidance strategy based on prediction results
2.6 Conclusions
References
Chapter 3 Individual behavior analysis and trajectory prediction
3.1 Introduction
3.2 Description of individual GPS data
3.3 Preprocessing of individual GPS data
3.4 Prediction of GPS trajectory based on optimized extreme learning machine
3.5 Prediction of GPS trajectory based on optimized support vector machine
3.6 Analysis of individual behavior based on prediction results
3.7 Conclusions
References
Chapter 4 Clustering and anomaly detection of crowd hotspot regions
4.1 Introduction
4.2 Description of crowd GPS data
4.3 Preprocessing of crowd GPS data
4.4 Clustering of crowd hotspot regions based on K-means
4.5 Clustering of crowd hotspot regions based on DBSCAN
4.6 Anomaly detection of crowd hotspot regions based on Markov chain
4.7 Conclusions
References
Chapter 5 Monitoring and deterministic prediction of station humidity
5.1 Introduction
5.2 Description of station humidity data
5.3 Deterministic prediction of station humidity based on optimization ensemble
5.4 Deterministic prediction of station humidity based on stacking ensemble
5.5 Evaluation of deterministic prediction results
5.6 Conclusions
References
Chapter 6 Monitoring and probabilistic prediction of station temperature
6.1 Introduction
6.2 Description of station temperature data
6.3 Interval prediction of station temperature based on quantile regression
6.4 Interval prediction of station temperature based on kernel density estimation
6.5 Evaluation of probabilistic prediction results
6.6 Conclusions
References
Chapter 7 Monitoring and spatial prediction of multi-dimensional air pollutants
7.1 Introduction
7.2 Description of multi-dimensional air pollutants data
7.3 Dimensionality reduction of multi-dimensional air pollutants data
7.4 Spatial prediction of air pollutants based on Long Short-Term Memory
7.5 Evaluation of spatial prediction results
7.6 Conclusions
References
Chapter 8 Time series feature extraction and analysis of metro load
8.1 Introduction
8.2 Description of metro load data
8.3 Feature extraction of metro load based on statistical methods
8.4 Feature extraction of metro load based on transform methods
8.5 Feature extraction of metro load based on model
8.6 Conclusions
References
Chapter 9 Characteristic and correlation analysis of metro load
9.1 Introduction
9.2 The theoretical basis of correlation analysis
9.3 Description of metro load data
9.4 Correlation analysis of metro load and environment data
9.5 Correlation analysis of metro load and operation data
9.6 Comprehensive correlation ranking of metro load and related data
9.7 Conclusions
References
Chapter 10 Metro load prediction and intelligent ventilation control
10.1 Introduction
10.2 Description of short-term and long-term metro load data
10.3 Short-term prediction of metro load data based on ANFIS model
10.4 Long-term prediction of metro load data based on SARIMA model
10.5 Performance evaluation of prediction results
10.6 Intelligent ventilation control based on prediction results
10.7 Conclusions
References