Biodiversity knowledge extraction techniques (BioKET)

Somsack Inthasone 1
1 Laboratoire d'Informatique, Signaux, et Systèmes de Sophia-Antipolis (I3S) / Projet MinD
Laboratoire I3S - SPARKS - Scalable and Pervasive softwARe and Knowledge Systems
Abstract : Biodiversity data are generally stored in different formats. This makes it difficult for biologists to combine and integrate them in order to retrieve useful information and discover novel knowledge for the purpose of, for example, efficiently classifying specimens. In this work, we present the BioKET data warehouse which is a consolidation of heterogeneous data stored in different formats and originating from different sources. For the time being, the scope of BioKET is botanical. Its construction required, among others things, to identify and analyze existing botanical ontologies, to standardize and relate terms in BioKET. We also developed a methodology for mapping and defining taxonomic terminologies, that are controlled vocabularies with hierarchical structures from authoritative plant ontologies, Google Maps, and OpenStreetMap geospatial information system. Data from four major biodiversity and botanical data providers and from the two previously mentioned geospatial information systems were then integrated in BioKET. The usefulness of such a data warehouse was demonstrated by applying classical knowledge pattern extraction methods, based on the classical Apriori and Galois closure based approaches, to several datasets generated from BioKET extracts. Using these methods, association rules and conceptual bi-clusters were extracted to analyze the risk status of plants endemic to Laos and Southeast Asia. Besides, BioKET is interfaced with other applications and resources, like the GeoCAT Geospatial Conservation Assessment Tool, to provide a powerful analysis tool for biodiversity data.
Document type :
Theses
Complete list of metadatas

Cited literature [1 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-01166027
Contributor : Abes Star <>
Submitted on : Monday, June 22, 2015 - 6:58:38 AM
Last modification on : Monday, November 5, 2018 - 3:52:10 PM
Long-term archiving on : Tuesday, September 15, 2015 - 8:11:27 PM

File

2015NICE4013.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-01166027, version 1

Collections

Citation

Somsack Inthasone. Biodiversity knowledge extraction techniques (BioKET). Other [cs.OH]. Université Nice Sophia Antipolis, 2015. English. ⟨NNT : 2015NICE4013⟩. ⟨tel-01166027⟩

Share

Metrics

Record views

517

Files downloads

425