Titulo Estágio
BIGODE - BIG Open Data in Epidemology
Áreas de especialidade
Sistemas Inteligentes
Local do Estágio
LARN - Laboratório de Redes Neuronais
Enquadramento
Big Data is a thriving field and infrastructure software is already available. On the other hand, Open Data is starting to be available from public and private institutions and the EU has already several directives to force their enforcement.
In this work we propose the study and development of a distributed infrastructure to store, process and extract information from large sets of data, usually defined as big data. The proposed infrastructure must extract data from heterogeneous data sources and different types of data formats, storing into NoSQL databases located in a distributed file system, allowing faster and improved results, while reducing processing reducing processing time and cost. Although application areas are immense, the infrastructure should collect, fuse, store and analyze epidemiological geo-localized data. Google Flu Trends (https://www.google.org/flutrends/) is a stepping-stone but fails to provide rich information. Here we propose to diversify and enrich data.
Objetivo
There are already some approaches in Europe to collect epidemiological data, e.g. https://www.influenzanet.eu/.
Nevertheless, such approaches are still scarce, rather homogeneous in the collected data, and shallow in terms of pattern analysis.
The main goal of this research project is to develop an infrastructure based on the open-source framework Apache Hadoop to sustain the ecosystem with distributed and parallel processing methodologies and heterogeneous data integration, which provides better data quality and easier information extraction that can be most valuable in decision
making both for private and public institutions.
Plano de Trabalhos - Semestre 1
- State of the Art Review (September 2016)
- Data Gathering & Infrastructure Definition (October 2016)
- Evaluation of Classification and Machine-Learning Methodologies (November-December 2016)
- Intermediate MSc Report (January 2017)
Plano de Trabalhos - Semestre 2
- System & Algorithm Implementations (February - May 2017)
- Testing & Results Evaluation (March - May 2017)
- MSc Dissertation (May - June 2017)
Condições
The student should be ambitious, confident and with strong interest in intelligent systems.
Observações
Logistics given to the students @Laboratory of Neural Networks (LARN)
DEI-FCTUC
Orientador
Bernardete Ribeiro (bribeiro@dei.uc.pt) e Catarina Silva (catarina@ipleiria.pt)
bribeiro@dei.uc.pt 📩