Towards Scientific Data Synthesis Using Deep Learning and Semantic Web

Alsayed Algergawy, Hamdi Hamed, Birgitta Koenig-Ries

Keywords: Scientific datasets analysis, semantic web, deep learning

TL;DR: Analysis and summarizing scientific datasets making use of semantic web and deep learning

Abstract: One of the added values of long-running and large-scale collaborative projects is the ability to answer complex research questions based on the extensive use of collected data. In practice, however, finding and identifying related data in the central repository of these projects often proves to be a demanding task. In this paper, we aim to release data from silos, thereby enabling cross-cutting analyses that were earlier out of reach. To achieve that we introduce a new data summarization and profiling approach exploiting the semantics of annotated datasets using a domain-specific ontology and making use of the capability of machine learning to extract hidden links across data attributes from different datasets. The proposed approach has been developed and has been applied to datasets collected in the CRC AquaDiva.