Informace o projektu
Big Data Analytics for Unstructured Data
(Big Data Analytics for Unstructured Data)
- Kód projektu
- GA16-18889S
- Období řešení
- 1/2016 - 12/2018
- Investor / Programový rámec / typ projektu
-
Grantová agentura ČR
- Standardní projekty
- Fakulta / Pracoviště MU
- Fakulta informatiky
Development of new foundations for Big Data Analytics requires an effective and efficient content-based access to data that is prevalently unstructured. For this data, to achieve the needed integration of large-scale knowledge discovery techniques with statistical modelling, it is necessary to first uncover descriptive knowledge of complex and heterogeneous objects to make them findable. Then, scalable search structures are needed to efficiently execute similarity access operations, considering also simultaneous execution of multiple queries. Such supporting technologies should serve for semantic data integration and enrichment technologies able to make sense of Big Data for high-level services. We plan to elaborate on these topics and report results, supported by advanced prototype implementations, in respective scientific publication platforms.
Publikace
Počet publikací: 15
2017
-
Popularity-Based Ranking for Fast Approximate kNN Search
Informatica, rok: 2017, ročník: 28, vydání: 1, DOI
-
Towards High Similarity Search Throughput by Dynamic Query Reordering and Parallel Processing
Advances in Databases and Information Systems : 21st European Conference, ADBIS 2017, Nicosia, Cyprus, September 24-27, 2017, Proceedings, rok: 2017
2016
-
Enhancing Similarity Search Throughput by Dynamic Query Reordering
Database and Expert Systems Applications: 27th International Conference, DEXA 2016, Porto, Portugal, September 5-8, 2016, Proceedings, Part II, rok: 2016
-
Optimizing Query Performance with Inverted Cache in Metric Spaces
Advances in Databases and Information Systems, 20th East European Conference, ADBIS 2016, rok: 2016
-
Speeding up Similarity Search by Sketches
Similarity Search and Applications (SISAP 2016), rok: 2016