Antônio Tadeu A. Gomes

Antonio Tadeu A. Gomes, Weslley S. Pereira, Frederic Valentin et al.

The family of Multiscale Hybrid-Mixed (MHM) finite element methods has received considerable attention from the mathematics and engineering community in the last few years. The MHM methods allow solving highly heterogeneous problems on coarse meshes while providing solutions with high-order precision. It embeds independent local problems which are responsible for upscaling unresolved scales into the numerical solution. These local contributions are brought together through a global problem defined on the skeleton of the coarse partition. Since the local problems are completely independent, they can be easily computed in parallel. In this paper, we present two simulator prototypes specifically crafted for the MHM methods, which adopt two different implementation strategies: (i) a multi-programming language approach, each language tackling different simulation issues; and (ii) a classical, single-programming language approach. Specifically, we use C++ for numerical computation of the global and local problems in a modular way; for process distribution in the simulator, we adopt the Erlang concurrent language in the first approach, and the MPI standard in the second approach. The aim of exploring these different approaches is twofold: (i) allow for the deployment of the simulator both in high-performance computing (with MPI) and in cloud computing environments (with Erlang); and (ii) pave the way for further exploration of quality attributes related to software productivity and fault-tolerance, which are key to Exascale systems. We present a performance evaluation of the two simulator prototypes taking into account their efficiency.

Antonio Tadeu Azevedo Gomes, Larissa Miguez da Silva, Frederic Valentin

Physics-Informed Neural Networks (PINNs) are machine learning tools that approximate the solution of general partial differential equations (PDEs) by adding them in some form as terms of the loss/cost function of a Neural Network. Most pieces of work in the area of PINNs tackle non-linear PDEs. Nevertheless, many interesting problems involving linear PDEs may benefit from PINNs; these include parametric studies, multi-query problems, and parabolic (transient) PDEs. The purpose of this paper is to explore PINNs for linear PDEs whose solutions may present one or more boundary layers. More specifically, we analyze the steady-state reaction-advection-diffusion equation in regimes in which the diffusive coefficient is small in comparison with the reactive or advective coefficients. We show that adding information about these coefficients as predictor variables in a PINN results in better prediction models than in a PINN that only uses spatial information as predictor variables. This finding may be instrumental in multiscale problems where the coefficients of the PDEs present high variability in small spatiotemporal regions of the domain, and therefore PINNs may be employed together with domain decomposition techniques to efficiently approximate the PDEs locally at each partition of the spatiotemporal domain, without resorting to different learned PINN models at each of these partitions.

Caroline de Oliveira Costa Souza Rosa, Marcia Ito, Alex Borges Vieira et al.

The sequence of visits and procedures performed by the patient in the health system, also known as the patient's pathway or trajectory, can reveal important information about the clinical treatment adopted and the health service provided. The rise of electronic health data availability made it possible to assess the pathways of a large number of patients. Nevertheless, some challenges also arose concerning how to synthesize these pathways and how to mine them from the data, fostering a new field of research. The objective of this review is to survey this new field of research, highlighting representation models, mining techniques, methods of analysis, and examples of case studies.

Caroline de Oliveira Costa Souza Rosa, Márcia Ito, Alex Borges Vieira et al.

The automatic discovery of a model to represent the history of encounters of a group of patients with the healthcare system -- the so-called "pathway of patients" -- is a new field of research that supports clinical and organisational decisions to improve the quality and efficiency of the treatment provided. The pathways of patients with chronic conditions tend to vary significantly from one person to another, have repetitive tasks, and demand the analysis of multiple perspectives (interventions, diagnoses, medical specialities, among others) influencing the results. Therefore, modelling and mining those pathways is still a challenging task. In this work, we propose a framework comprising: (i) a pathway model based on a multi-aspect graph, (ii) a novel dissimilarity measurement to compare pathways taking the elapsed time into account, and (iii) a mining method based on traditional centrality measures to discover the most relevant steps of the pathways. We evaluated the framework using the study cases of pregnancy and diabetes, which revealed its usefulness in finding clusters of similar pathways, representing them in an easy-to-interpret way, and highlighting the most significant patterns according to multiple perspectives.

Lucas Giusti, Leonardo Carvalho, Antonio Tadeu Gomes et al.

Flight delays impose challenges that impact any flight transportation system. Predicting when they are going to occur is an important way to mitigate this issue. However, the behavior of the flight delay system varies through time. This phenomenon is known in predictive analytics as concept drift. This paper investigates the prediction performance of different drift handling strategies in aviation under different scales (models trained from flights related to a single airport or the entire flight system). Specifically, two research questions were proposed and answered: (i) How do drift handling strategies influence the prediction performance of delays? (ii) Do different scales change the results of drift handling strategies? In our analysis, drift handling strategies are relevant, and their impacts vary according to scale and machine learning models used.

Vivian Medeiros, Antonio Tadeu Azevedo Gomes

In this paper we present OSC, a scientific workflow specification language based on software architecture principles. In contrast with other approaches, OSC employs connectors as first-class constructs. In this way, we leverage reusability and compositionality in the workflow modeling process, specially in the configuration of mechanisms that manage non-functional attributes.