Human mobility has a significant impact on several layers of society, from infrastructural planning and economics to the spread of diseases and crime. Representing the system as a complex network, in which nodes are assigned to regions ( e . g ., a city) and links indicate the flow of people between two of them, physics-inspired models have been proposed to quantify the number of people migrating from one city to the other. Despite the advances made by these models, our ability to predict the number of commuters and reconstruct mobility networks remains limited. Here, we propose an alternative approach using machine learning and 22 urban indicators to predict the flow of people and reconstruct the intercity commuters network. Our results reveal that predictions based on machine learning algorithms and urban indicators can reconstruct the commuters network with 90.4% of accuracy and describe 77.6% of the variance observed in the flow of people between cities. We also identify essential features to recover the network structure and the urban indicators mostly related to commuting patterns. As previously reported, distance plays a significant role in commuting, but other indicators, such as Gross Domestic Product (GDP) and unemployment rate, are also driven-forces for people to commute. We believe that our results shed new lights on the modeling of migration and reinforce the role of urban indicators on commuting patterns. Also, because link-prediction and network reconstruction are still open challenges in network science, our results have implications in other areas, like economics, social sciences, and biology, where node attributes can give us information about the existence of links connecting entities in the network.

The interest for patient trajectory prediction, a sort of computer-aided medicine, has steadily increased with the pace of artificial intelligence innovation. Notwithstanding, the design of effective systems able to predict clinical outcomes based on the history of a patient is far from trivial. Works so far are based on neural architectures with low performance, especially when using low-cardinality datasets; alternatively, complex inference approaches are hard to reproduce and/or extrapolate as they are designed for very specific circumstances. We introduce LIG-Doctor, an artificial neural network architecture based on two Minimal Gated Recurrent Unit networks functioning in a bidirectional parallel manner, benefiting from temporal events both forward and backward. In comparison to state-of-the-art works, consistent improvements were achieved in prognosis prediction, as assessed with metrics Recall@k, Precision@k, F1-score, and AUC-ROC. Besides the detailed delineation of our architecture, a sequence of experiments is reported with insights that progressively guided design decisions to inspire future works on similar problems. Our results shall contribute to the improvement of computer-aided medicine and, more generally, to processes related to the design of neural network architectures.

Time-series forecasting is one of the most active research topics in artificial intelligence. It has the power to bring light to problems in several areas of knowledge, such as epidemiological studies, healthcare inference, and climate change analysis. Applications in real-world time series should consider two factors for achieving reliable predictions: modeling dynamic dependencies among multiple variables and adjusting the model's intrinsic hyperparameters. An open gap in the literature is that statistical and ensemble learning approaches systematically present lower predictive performance than deep learning methods. The existing applications consistently disregard the data sequence aspect entangled with multivariate data represented in more than one time series. Conversely, this work presents a novel neural network architecture for time-series forecasting that combines the power of graph evolution with deep recurrent learning on distinct data distributions, named after Recurrent Graph Evolution Neural Network (REGENN). The idea is to infer multiple multivariate relationships between co-occurring time-series by assuming that the temporal data depends not only on inner variables and intra-temporal relationships (i.e., observations from itself) but also on outer variables and inter-temporal relationships (i.e., observations from other-selves). An extensive set of experiments was conducted comparing REGENN with tens of ensemble methods and classical statistical ones. The results outperformed both statistical and ensemble-learning approaches, showing an improvement of 64.87% over the competing algorithms on the SARS-CoV-2 dataset of the renowned John Hopkins University for 188 countries simultaneously. For further validation, we tested our architecture in two other public datasets of different domains, the PhysioNet Computing in Cardiology Challenge 2012 and Brazilian Weather datasets. We also analyzed the Evolution Weights arising from the hidden layers of REGENN to describe how the variables of the dataset interact with each other; and, as a result of looking at inter and intra-temporal relationships simultaneously, we concluded that time-series forecasting is majorly improved if paying attention to how multiple multivariate data synchronously evolve.

No abstract

Complex networks provide a means to describe cities through their street mesh, expressing characteristics that refer to the structure and organization of an urban zone. Although other studies have used complex networks to model street meshes, we observed a lack of methods to characterize the relationship between cities by using their topological features. Accordingly, this paper aims to describe interactions between cities by using vectors of topological features extracted from their street meshes represented as complex networks. The methodology of this study is based on the use of digital maps. Over the computational representation of such maps, we extract global complex-network features that embody the characteristics of the cities. These vectors allow for the use of multidimensional projection and clustering techniques, enabling a similarity-based comparison of the street meshes. We experiment with 645 cities from the Brazilian state of Sao Paulo. Our results show how the joint of global features describes urban indicators that are deeprooted in the network's topology and how they reveal characteristics and similarities among sets of cities that are separated from each other.