From Cities to Series: Complex Networks and Deep Learning for Improved Spatial and Temporal Analytics*

Abstract

Graphs have often been used to answer questions about the interaction between real-world entities by taking advantage of their capacity to represent complex topologies. Complex networks are known to be graphs that capture such non-trivial topologies; they are able to represent human phenomena such as epidemic processes, the dynamics of populations, and the urbanization of cities. The investigation of complex networks has been extrapolated to many fields of science, with particular emphasis on computing techniques, including artificial intelligence. In such a case, the analysis of the interaction between entities of interest is transposed to the internal learning of algorithms, a paradigm whose investigation is able to expand the state of the art in Computer Science. By exploring this paradigm, this thesis puts together complex networks and machine learning techniques to improve the understanding of the human phenomena observed in pandemics, pendular migration, and street networks. Accordingly, we contribute with: (i) a new neural network architecture capable of modeling dynamic processes observed in spatial and temporal data with applications in epidemics propagation, weather forecasting, and patient monitoring in intensive care units; (ii) a machine-learning methodology for analyzing and predicting links in the scope of human mobility between all the cities of Brazil; and, (iii) techniques for identifying inconsistencies in the urban planning of cities while tracking the most influential vertices, with applications over Brazilian and worldwide cities. We obtained results sustained by sound evidence of advances to the state of the art in artificial intelligence, rigorous formalisms, and ample experimentation. Our findings rely upon real-world applications in a range of domains, demonstrating the applicability of our methodologies.

arXiv commentThis piece refers to an extended abstract of the Ph.D. thesis under the same name defended in the Graduate Program in Computer Science and Computational Mathematics (PPG-CCMC) of the Institute of Mathematics and Statistics (ICMC) from the University of Sao Paulo (USP) - Brazil on July 12, 2021. The authors here listed refer to the Ph.D. candidate and his advisor, respectively

References in corpus (54)

• Adam: A Method for Stochastic Optimization
• Scikit-learn: Machine Learning in Python
• XGBoost: A Scalable Tree Boosting System
• Modularity and community structure in networks
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Assortative mixing in networks
• T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction
• Link Prediction in Complex Networks: A Survey
• Spatial Networks
• Characterization of complex networks: A survey of measurements
• Hierarchical structure and the prediction of missing links in networks
• Clustering and preferential attachment in growing networks
• The worldwide air transportation network: Anomalous centrality, community structure, and cities' global roles
• A universal model for mobility and migration patterns
• Multiscale mobility networks and the large scale spreading of infectious diseases
• CatBoost: gradient boosting with categorical features support
• Prediction and predictability of global epidemics: the role of the airline transportation network
• Human Mobility: Models and Applications
• The complex network of global cargo ship movements
• Representation Learning on Graphs with Jumping Knowledge Networks
• Missing and spurious interactions and the reconstruction of complex networks
• The Network Analysis of Urban Streets: A Primal Approach
• Centrality Measures in Spatial Networks of Urban Streets
• Saving Human Lives: What Complexity Science and Information Systems can Contribute
• Structure of urban movements: polycentric activity and entangled hierarchical flows
• Structural Properties of Planar Graphs of Urban Street Patterns
• Uncovering space-independent communities in spatial networks
• Gravity model in the Korean highway
• Modeling urban street patterns
• Gravity vs radiation model: on the importance of scale and heterogeneity in commuting flows
• Uncovering the spatial structure of mobility networks
• Predicting commuter flows in spatial networks using a radiation model based on temporal ranges
• The structure of borders in a small world
• Distance to the scaling law: a useful approach for unveiling relationships between crime and urban metrics
• Modeling the polycentric transition of cities
• Multivariate Time series Anomaly Detection:A Framework of Hidden Markov Models
• Urban street networks: a comparative analysis of ten European cities
• Limited Urban Growth: London's Street Network Dynamics since the 18th Century
• Human mobility and COVID-19 initial dynamics
• The Backbone of a City
• Energy saving mechanisms, collective behavior and the variation range hypothesis in biological systems: A review
• Pay Attention to Evolution: Time Series Forecasting with Deep Graph-Evolution Learning
• Time2Graph: Revisiting Time Series Modeling with Dynamic Shapelets
• Human Mobility in Large Cities as a Proxy for Crime
• Scale-adjusted metrics for predicting the evolution of urban indicators and quantifying the performance of cities
• Elementary processes governing the evolution of road networks
• Large Graph Analysis in the GMine System
• Suppressing epidemic spreading by risk-averse migration in dynamical networks
• Spatial Patterns in Urban Systems
• Long-Range Connections in Transportation Networks
• Topological characterization of world cities
• Complex Network Tools to Understand the Behavior of Criminality in Urban Areas
• Patient trajectory prediction in the Mimic-III dataset, challenges and pitfalls
• Change-point detection using spectral PCA for multivariate time series