Querying Health Databases by Content and Context – Challenges and Real Applications
Brown Bag Lecture by Agma J. Machado Traina and Caetano Traina Junior | 11/28/2017 11:00AM – 12PM | 7th Floor Conference Room, Bldg 38A
The amount and complexity of data generated and managed by health systems bring several challenges to the data analysis and management development team, in order to comply with the expectation of the users and data owners. Not only do most applications require searching complex data by queries considering several different aspects of the same data, but also getting answers in a timely manner is mandatory. In this scenario, content and context-based queries should be associated. Context-based retrieval is helpful, mainly due to representing information that is related to human understanding; but it may be subjective and could miss part of the data elements. Content-based similarity retrieval enables performing queries and analyses using the required features automatically extracted from the data elements without user intervention. In this talk, we will discuss the challenges posed to the medical image and database fields in developing techniques and tools to overcome the precision and time concerns regarding similarity queries over complex data. We will present examples and results obtained with data from the Clinical Hospitals of University of Sao Paulo, Brazil.
Agma J. Machado Traina is a Professor with the Computer Science Department of the Mathematics and Computer Science Institute at the University of São Paulo at São Carlos, Brazil. She received her PhD in Computational Physics from this university and spent two years as a Visiting Scholar at Carnegie Mellon University working on multimedia databases. Agma´s research interests ranges from image processing techniques and applications, complex data indexing and retrieval by content, similarity queries to data visualization and visual data mining. She has focused her research on medical applications supported by image processing techniques.
Caetano Traina Junior is a Professor with the Computer Science Department of the Mathematics and Computer Science Institute at the University of São Paulo at São Carlos, from where he received his Ph.D. in Computational Physics. He spent two years as a Visiting Scholar at Carnegie Mellon University working on indexing and selectivity estimation for databases. Caetano is an Electrical and Computing Engineer from the University of São Paulo and got his MSc in Computer Science from the Mathematics and Computer Science Institute at the University of São Paulo at São Carlos. Caetano’s research interests includes management of complex and big data, indexing, similarity queries, diversity, and systems development for medical applications. He has focused his research on medical applications supported by similarity retrieval in databases.