Research & Grants

Grants

		Covid-19 AI for Social Good program (2020-2021)

		Support for Scientific, Technological and/or Innovation Research to Face the New Coronavirus - Covid-19 (2020-2021)

		GCRF Global Multimorbidity - Seed Funding 2019 (2020-2022)

		Udacity / Bertelsmann Technology Scholarship (2019-2020)

		NVIDIA Large-scale Applied Data Science GPU Grant (2019-2021)

		Newton Fellowship Alumni Follow on Funding (2019-2020) (with Prof. Spiros Denaxas - IHI/UCL, UK)

		Affordable Health Technologies (2019) (with Dr. Amir Keshmiri - University of Manchester, UK and Dr. Juan Carlos Briceño Triana - University of Los Andes, Colombia)

		Frontiers of Engineering for Development - Seed funding (2018-2019) (PI: Dr. Alan Godfrey - University of Northumbria, UK)

		Grand Challenges Explorations - Brazil: Data Science Approaches to Improve Maternal and Child Health in Brazil (2018-2020) (PI: Dr. Muriel Gubert - UnB)

		UCL Research Catalyst Awards (2018) (with Prof. Spiros Denaxas - IHI/UCL, UK)

		Grand Challenges Explorations - Malaria analytics - Round 17 (2016-2018) (with Dr. Vanderson Sampaio - FVS/AM)

		Newton International Fellowship (2016-2018) (with Prof. Spiros Denaxas - IHI/UCL, UK)

		Hardware Grant Program (2015)
		Bahia Young Researchers' Call (2015)
		Master and Doctorate Scholarships (2015)
		Research and Knowledge Production on IT in Bahia (2015) (PI: Dr. Leobino Sampaio - UFBA)
		Support for Supercomputing Research in Bahia (2014) (PI: Dr. Davidson Moreira - CIMATEC)
		Research Programme for SUS (Brazilian Public Health) (2013) (PI: Dr. Rosemeire Fiaccone - UFBA)

Research topics

Big data science: linkage, analytics, visualisation.
Machine and deep learning.
Parallel and distributed systems & tools.
Ontologies and cloud robotics.

Current projects

AI as service for tackling the Covid-19 in Brazil.

Funding:

Principal investigator: Marcos Barreto (DCC/UFBA), Mauricio Barreto (CIDACS/FIOCRUZ).
Team: Robespierre Pita (CIDACS), Juracy Bertoldo (CIDACS), Daniela Almeida (UFBA), Everton Mendonça (UFBA), Elzo Junior (CIDACS), Julia Pescarini (CIDACS).
Period: 2020-2021
Scope: This project aims to establish a cloud-based AI platform to support research and inform decisions related to Covid-19 in Brazil. The emphasis will be on the activities conducted by Rede CoVida, a Brazilian network of around 180 academics, policymakers, health workers, and the general public established in March/2020 to monitor the spread of the disease in Brazil; design multi-purpose, real time prediction models; and synthesize and disseminate scientific evidence. We will focus on the following research goals: i) design of a large-scale data lake and integration platform; ii) design and validation of mixed AI models for prediction and decision-making support; and iii) design of an interactive bibliometrics platform focusing on synthesis of evidence and correlations within the increasing literature related to Covid-19. The major contribution of this proposal relies in providing a set of tools and platforms with up-to-date aggregated datasets, AI models tailored for complex scenarios, and solid evidence from the literature for health workers, governmental agencies, researchers and the general public.

+Lugar COVID-19: a gamified, geo-collaborative platform for coping of the new Coronavirus.

Funding:

Principal investigator: Marcos Barreto (DCC/UFBA).
Team: Alberto Sironi (DCC/UFBA), Carlos Daniel Cruz, Christina Chaves (DCC/UFBA), Daniel Bacellar, Daniela Claro (DCC/UFBA), Erika Cerqueira (IGEO/UFBA), Fabiana Palma (ISC/UFBA), Federico Costa (ISC/UFBA), Hussein Khalil (University of Liverpool, UK), Isa Beatriz da Cruz (IHAC/UFBA), João Gabriel Pereira (ISC/UFBA), Lynn Alves (IHAC/UFBA), Mitermayer Reis (IGM-FIOCRUZ, UFBA), Murilo Arouca (DCC/UFBA), Rafael Santana, Ricardo Lustosa (ISC/UFBA), Rodrigo Oliveira (PET/IHAC), Ronaldo Lyrio (EDBA), Tamires Jesus (PET/IHAC), Vaninha Vieira (DCC/UFBA), Yeimi Alexandra López (ISC/UFBA).
Period: 2020-2021
Scope: This partnership aims at to promote public engagement through the design of a gamified, geo-collaborative platform to face the new Coronavirus, especially by vulnerable groups. The proposed platform, composed of a mobile app and a dashboard for visual information mining, will be used for monitoring, guidance and cooperation between society, academia and government to identify possible outbreaks during the social isolation and post-outbreak phases of the pandemic, as well as for the survey and monitoring of demands and actions with the government.

The risk of a chronic clinical condition following a previous hospitalisation by a psychiatric disorder: a linkage nationwide study in Brazil.

Funding:

Principal investigator: Mauricio Barreto (CIDACS).
Team: Luis Fernando Araujo (CIDACS), Daiane Machado (CIDACS), Marcos Barreto (UFBA/CIDACS), Liam Smeeth (London School of Hygiene and Tropical Medicine), Glynn Lewis (UCL), Spiros Denaxas (UCL)
Period: 2020-2022
Scope: This project aims primarily at answering how mental disorders interact with other chronic medical conditions. We will address the following objectives: i) estimate the risk of hospitalisations or death by diabetes, cardiovascular diseases or stroke following a hospitalisation due to depressive disorders, alcohol and substance use-related disorders, and schizophrenia; ii) estimate the risk of the occurrence or death by tuberculosis following the same exposure; and iii) investigate how these chronic conditions goes together in clusters and how these patterns evolve over time and ageing.

Scaling up multimodal data fusion and analytical models over multiple-GPU systems.

Funding:

Principal investigator: Marcos Barreto (UFBA).
Period: 2019-2021
Scope: This project focuses on the exploitation of multi-GPUs systems to i) accelerate our probabilistic data fusion tool (AtyImo), more specifically preprocessing and data linkage methods, and ii) deploy and validate complex machine and deep learning models to analyze huge amounts of data built from Brazilian socioeconomic and public health care databases (NVIDIA Large-scale Applied Data Science GPU Grant).

Design and validation of personalised risk prediction models over Brazilian health care data.

Funding:

Principal investigators: Marcos Barreto (UFBA), Prof. Spiros Denaxas (Institute of Health Informatics, UCL).
Period: 2019-2020
Scope: i) define a set of diseases, at individual and municipality level, for which risk prediction models can effectively contribute to early detection and/or guidance of treatment; ii) establish proof-of-concept studies; iii) identify existing models adjustable to the Brazilian population; iv) perform deep experimentation of the proposed models; v) generate a set of results to be validated by a panel of epidemiologists, statisticians and people from other related disciplines, as well as governmental staff. (Newton Fellowship Alumni Follow on Funding).

Stratification of patients suffering from myalgic encephalomyelitis/chronic fatigue syndrome.

Support:

Principal investigator: Marcos Barreto (UFBA).
Team: Nuno Sepulveda (London School of Hygiene & Tropical Medicine), Robespierre Pita (UFBA)
Period: 2019-2020
Scope: This study aims at to stratify ME/CFS patients into different clusters (or symptom subtypes). The respective objectives are the following: i) to distinguish ME/CFS patients from those suffering from multiple sclerosis (MS); ii) to identify sets of clinical symptoms that could characterize different clusters of ME/CFS patients; iii) to identify the best (or exclusive) predictive symptoms for CFS and compare the results with those obtained from different statistical/computational methods; (iv) to compare the stability of patients stratification using baseline and follow-up data.

Standardisation of wearable-based algorithms for healthcare applications in developing countries.

Funding:

Principal investigator: Alan Godfrey (Northumbria University, Newcastle-upon-Tyne, UK).
Team: Rodrigo Vitorio (UNESP), Marcos Barreto (UFBA), Azad Hussain (University of Birmingham), Clara Aranda-Jan (University College London)
Period: 2018-2019
Scope: This proposal aims to develop a novel standardised framework to better inform algorithms for a more harmonised gait assessment in Parkinson's disease (PD), particularly for developing countries where guidance is lacking. This project will lead to the design of an online simulation tool to test algorithms. Additionally, it will outline an educational process for all clinicians to better understand the functionality of wearables/algorithms and resulting outcomes. This will better guide PD assessment for sustainable health, promoting and encouraging low-cost wearables as routine diagnostics in developing countries. This framework will also be adapted to the needs of those in developed regions. More information here.

Early childhood development friendly index: assessing the enabling environment for Nurturing Care.

Funding:

Principal investigator: Muriel Gubert (UnB).
Team: Marcos Barreto (UFBA), Gabriela Buccini (Yale School of Public Health), Rafael Perez-Escamilla (Yale School Of Public Health), Sonia Isoyama Venancio (Health Institute of São Paulo)
Period: 2018-2020
Scope: This project aims to develop an ECD (Early Childhood Development) friendly index (ECD-FI), based on a core set of evidence-based Nurturing Care indicators, to assess the enabling environment and promote ECD at the municipality level by monitoring and identifying opportunities to scale up ECD programs locally. More information here.

The 100 million Brazilian linked data and datacentre.

Funding:

Principal investigators: Mauricio Barreto (FIOCRUZ/BA), Laura Rodrigues (London School of Hygiene and Tropical Medicine).
Period: 2017-2022
Scope: i) link electronic health records from Brazilian governmental databases; ii) build the CIDACS datacentre and its public interface. More information here.

Treating heterogeneity and uncertainty in data integration: case study on Brazilian databases.

Funding:

Principal investigators: Marcos Barreto (UFBA), Prof. Spiros Denaxas (Institute of Health Informatics, UCL).
Period: 2016-2018
Scope: i) design and validation of a data integration model and related computing tools addressing heterogeneity, uncertainty and scalability targeted to big data integration; ii) support for some Brazil-UK ongoing projects: the 100 million cohort, the surveillance platform for Zika and microcephaly, and predictive analytics methods applied to Malaria data (Post-doctoral proposal). More information here.

Integrating socioeconomic and health data to combat malaria.

Funding:

Principal investigator: Marcos Barreto (UFBA), Prof. Spiros Denaxas (Farr Institute of Health Informatics Research).
Period: 2016-2019
Scope: i) develop a platform to integrate surveillance data from Malaria with other sources (socioeconomic and public health data); ii) design and validate predictive analytics methods to help on Malaria elimination. More information here.

Long-term surveillance platform for Zika virus and microcephaly

Funding:

Principal investigators: Maurício Barreto (FIOCRUZ/BA), Maria Glória Teixeira (UFBA), Cláudio Henriques Maierovisch (Ministry of Health).
Period: 2016-2020
Scope: i) Design a cohort based on live births (from SINASC database) from 2001 to 2030; ii) assessment of health and educational outcomes related to Zika virus and microcephaly.
More information here.

Design of a scientific repository (data lake) for big data applications

Funding:

Principal investigator: Marcos Barreto (UFBA).
Period: 2016-2019
Scope: Design and deployment of a data repository (data lake) for big data applications. The first prototype comprises malaria surveillance data to support predictive analytics.

The 100 million Brazilian cohort

Funding:

Principal investigators: Maurício Barreto (FIOCRUZ BA), Gerson Penna (FIOCRUZ DF), Laura Rodrigues (London School of Hygiene and Tropical Medicine), Liam Smeeth (London School of Hygiene and Tropical Medicine).
Period: 2015-2019
Scope: i) integration of socioeconomic data from Cadastroúnico and Bolsa Família (conditional cash transfer programme) databases to build a huge population-based cohort covering the period 2007-2015. Current cohort size is 114 million records; ii) design a probabilistic data linkage tool (AtyImo) to link this cohort with Public Health databases and generate domain-specific data from several epidemiological studies on HIV, tuberculosis, leprosy etc; iii) propose and validate statistical approaches to probabilistic linkage of huge datasets; iv) promote technology transfer and capacity building on big data integration. More information here.

BAMBU - Metropolitan network for trial and innovation on future internet

Funding:

Principal investigator: Leobino Sampaio (UFBA).
Period: 2015-2019
Scope: develop and implement BAMBU - an experimental metropolitan network for trial and innovation on future internet issues. This network will be based on the REMESSA existing network. Besides serving as an experimental sandbox for educational and research institutions of Bahia, we plan to link BAMBU with other national and international networks, through the FIBRE project. More information here (in Portuguese).

Past projects

Computational infrastructure to support big data applications in Health

Period: 2014 - 2016.
Principal investigators: Marcos Barreto (UFBA), Rosemeire Fiaccione (UFBA), Leila Amorim (UFBA), Maria Yuri Travassos (UFBA), Maurício Barreto (FIOCRUZ BA), Davide Rasella (FIOCRUZ RJ), Gerson Penna (FIOCRUZ DF).
Team: Clícia Santos, Robespierre Dantas, Pedro Novaes, Amanda Chagas, Malu de Leon, Marcos Figueiredo, George Barbosa, Samila Sena, Jackson Conceição.
Partners: Institute of Public Health (ISC), Computer Science Department (DCC), Department of Statistics (DE), Oswaldo Cruz Foundation (FioCruz), University of Brasília (UnB), London School of Hygiene and Tropical Medicine, and Farr Institute of Health Informatics Research.
Sponsors: UFBA (PRODOC 2013, PIBIC 2014-2015), FAPESB (PPSUS 2013).
Abstract: This project aims at to design a middleware for probabilistic record linkage of some governmental databases: Cadastro único (socioeconomic data), PBF (payments from Bolsa Família) and SUS (3 databases from the Brazilian National Health System). This middleware provides some data warehouse (ETL) routines for data quality assessment, data cleansing, and anonymization, as well as a Spark-based execution engine to support data linkage from these databases. The generated data marts are used by statisticians and epidemiologists to assess the efficiency of some social programmes related to the incidence of some diseases (leprosy, tuberculosis, HIV/AIDS) on the beneficiary population.

Cloud computing infrastructure to support Bioinformatics and Robotics applications

Period: 2013 - 2015.
Role: Principal investigator.
Team: Danilo Azevedo, Raphael Carmo, Genicleito Gonçalves, Danilo Pires, Prof. Rodrigo Zucoloto (GENEV), Prof. Murilo Boratto (ACSO/INCO²).
Partners: Computer Science Department (DCC/UFBA), GENEV / Institute of Biology (UFBA), ACSO / State University of Bahia (UNEB), INCO² / Universidad Politécnica de Valencia (UPV).
Sponsors: UFBA (PIBIC 2013-2014, PERMANECER 2014-2015).
Abstract: In this project, we are improving our BOINC implementation designed for the GT-MC² and developing a new implementation to support highly distributed applications based on Hadoop. We evaluated a number of Bioinformatics applications in both implementations (SGA for BOINC and SGA for Hadoop). We are also considering the utilization of hybrid parallel architectures (multicore + multi-GPU) in order to efficiently run these applications.

JiT-Clouds: Highly scalable Infrastructure-as-a-Service

Period: 2011 - 2013.
Role: Researcher.
Principal investigators: Francisco Brasileiro (UFCG) and Philippe Navaux (UFRGS).
Team (UFBA): Prof. Marcos Barreto, Prof. Raimundo Macêdo, Prof. Alírio Sá, Allan Edgard Freitas, Felipe Gutierrez, Marivaldo Bispo Jr., Vinícius Santos.
Partners: A consortium of 14 universities and laboratories led by UFCG and UFRGS.
Sponsors: Brazilian Ministry of Sciences, Technology and Innovation (MCTI), RNP.
Abstract: The JiT-Clouds project is a research effort carried out by a group of Brazilian Universities and Research Centers, sponsored by the Centro de Pesquisa e Desenvolvimento em Tecnologias Digitais para Informação e Comunicação (CTIC) held by the Ministry of Sciences and Technology. It aims at developing an alternative way to build public cloud infrastructures, based on the concept of Just-in-Time (JiT) deployment of the computing infrastructure. More information here.

GT-MC²: My sCientific Cloud

Period: 2011 - 2013.
Role: Researcher and principal investigator at UFBA.
Principal investigators: Antonio Tadeu Gomes (LNCC) and Francisco Brasileiro (UFCG).
Team (UFBA): Prof. Marcos Barreto, Felipe Gutierrez, David Pinho, Fernando Carneiro, Marino Souza.
Partners: LNCC, UFCG, UFBA, PUC-RJ, FIOCRUZ, CESUP/UFRGS, CENAPAD-CE.
Sponsors: Brazilian Ministry of Sciences, Technology and Innovation (MCTI), RNP.
Abstract: MC² is a cloud computing platform aimed to support scientific (e-science) applications. It provides access to a large amount of computational resources for brief time intervals, storage, reproducibility of experiments and control of data provenance. This platform uses a PaaS model, allowing for the easy development and deployment of customized services and portals, accessed at the SaaS level. At the IaaS level, MC² employs a broker to efficiently provide access to high performance clusters, volunteer computing resources (based on BOINC), peer-to-peer computing resources (based on OurGrid) and cloud resources (based on Eucalyptus). More information here.

Analysis of performance models applied to high-performance hybrid architectures

Period: 2011 - 2013.
Role: Principal investigator.
Team (UFBA): Prof. Marcos Barreto, Cairo Andrade, Tarço Dourado.
Partners: UFBA, UNEB (Prof. Murilo Boratto), UNIVASF (Prof. Brauliro Leal).
Sponsor: UFBA (PERMANECER 2011-2012, PERMANECER 2012-2013).
Abstract: This project aims at to study performance models used for high performance processing in hybrid architectures composed by multicore CPUs and manycore GPUs. We want to identify and measure some metrics related to performance and processing capacity/elasticity, as well as limitations related to application execution, tools for applications development and other aspects related to each architecture. A set of applications belonging to different classes (highly coupled, bag of tasks and data-intensive) will be evaluated in terms of their requirements (resources needed, data movement etc), aiming at to define a set of operating characteristics for each class. As major outcomes, the project must generate a detailed analysis on the suitability of current performance models applied to hybrid architectures and propose some extensions in order to efficiently support such architectures.

GT-UniT: Monitoring the BitTorrent universe

Period: 2010 - 2012.
Role: Researcher.
Principal investigators: Marinho Barcellos (UFRGS) and Luciano Gaspary (UFRGS).
Partners: UFRGS, UFCG.
Sponsor: Brazilian Ministry of Sciences, Technology and Innovation (MCTI), RNP.
Abstract: Working group funded by RNP (Rede Nacional de Ensino e Pesquisa) that aims at to develop a software infrastructure to monitor BitTorrent networks. Specific goals comprise the monitoring of Portuguese content, the popularity of specific contents and the traffic observed in some sub-networks. Experiments were executed in 6 servers hosted in the Brazilian internet backbone (points of presence) and more than 95 nodes in PlanetLab. More information here.

PMM: Modular multimedia platform.

Period: 2006 - 2008.
Role: Collaborative researcher.
Principal investigator: Valter Roesler (UFRGS).
Partners: UFRGS, UNILASALLE, UFSC, Digitel.
Sponsor: FINEP.
Abstract: Design of a middleware and applications for a modular multimedia platform, offering services for digital video recording and interaction focused on digital television. More information here.

MultiCluster: Support for parallel programming on multiple clusters.

Period: 2000 - 2006.
Role: Ph.D student.
Advisor: Phillipe Navaux (UFRGS).
Partners: UFRGS, Universität Paderborn, Laboratoire d'Informatique de Grenoble (LIG/UJF).
Sponsor: CAPES.
Abstract: The MultiCluster project aims at to define an integration model for heteregeneous cluster-based architectures composed by Myrinet, SCI, and Fast Ethernet. The main goals are to identify hardware and software requirements and provide a complete programming environment that allows the user to configure such architecture and distribute tasks according to his application needs. For such, we integrate different DECK implementations and use JXTA to aggregate resources from heterogeneous clusters.

DECK: Parallel programming applied to cluster computing.

Period: 1998 - 2000.
Role: M.Sc. student.
Advisor: Phillipe Navaux (UFRGS), Jacques Briat (LIG/UJF - co-advisor).
Partners: UFRGS, Laboratoire d'Informatique de Grenoble (LIG/UJF).
Sponsor: CAPES.
Abstract: This project focuses on the development of a parallel programming library called DECK (Distributed Execution and Communication Kernel) applied to clusters composed by different communication technologies (Fast Ethernet, Myrinet, and SCI). We developed a DECK version for each communication technology and evaluate its performance against MPI, Athapascan-0 and other tools.

DPC++: Distributed processing in C++

Period: 1995 - 1998.
Role: Research initiation scholarship.
Advisor: Phillipe Navaux (UFRGS).
Sponsor: CNPq.
Abstract: DPC++ applies object-orientation as a basis for distributed programming. The main focus is to extend the C++ programming language with abstractions for object distribution and communication, as well as a good load balancing among the resources. The user is not aware of such operating aspects as the DPC++ preprocessor performs all operations needed to distribute, communicate and coordinate distributed tasks and objects.

ArMA-GAPP: Study and application of vector architectures

Period: 1993 - 1994.
Role: Research initiation scholarship.
Advisor: Phillipe Navaux (UFRGS).
Sponsor: CNPq.
Abstract: This project uses a vector processor architecture (NCR GAPP) and some C-based tools we have developed to run and evaluate image processing applications.