Presenter/Author Information

Noel Conruyt
David Grosser
Régine Vignes Lebbe

Keywords

data mining, sign management, knowledge discovery, environmental sciences, biodiversity informatics

Start Date

1-7-2012 12:00 AM

Abstract

Knowledge discovery from data in environmental sciences is becomingmore and more important nowadays because of the deluge of information found indatabases of digital ecosystems, coming altogether from institutions and amateurs.For example in biodiversity science, all these data need to be validated byspecialists with the help of Intelligent Environmental Decision Support Systems(IEDSSs), then enhanced and certified into qualitative knowledge before reachingtheir audience. Data mining through classification or clustering is the dedicatedinductive process of grouping descriptions based on similarity measures, thenbuilding classes and naming them. Later, the formed concepts can be reused foridentification purpose with new observations. The problem is that when using suchknowledge-based systems, we tend to forget the fundamental role of subjects (endusers)in the definition, observation and description of objects. In order to get goodidentification results, a consensus must be found between these experts andamateurs for interpreting correctly the observed objects. Thus, a new method ofKnowledge discovery is necessary by switching from Data mining to Signmanagement. The method focuses on the process of building knowledge bysharing signs and significations (Semiotic Web), more than on knowledgetransmission with intelligent object representations (Semantic Web). Signmanagement is the shift of paradigm for Biodiversity Informatics that we haveinvestigated in such domains as enhancing natural heritage with ICT. In this paper,we will present Sign management and illustrate this concept with two knowledgebases built in La Reunion Island for corals’ classification with IKBS (IterativeKnowledge Base System) and plants identification with Xper2 software platform.

COinS
 
Jul 1st, 12:00 AM

Knowledge Discovery for Biodiversity: from Data Mining to Sign Management

Knowledge discovery from data in environmental sciences is becomingmore and more important nowadays because of the deluge of information found indatabases of digital ecosystems, coming altogether from institutions and amateurs.For example in biodiversity science, all these data need to be validated byspecialists with the help of Intelligent Environmental Decision Support Systems(IEDSSs), then enhanced and certified into qualitative knowledge before reachingtheir audience. Data mining through classification or clustering is the dedicatedinductive process of grouping descriptions based on similarity measures, thenbuilding classes and naming them. Later, the formed concepts can be reused foridentification purpose with new observations. The problem is that when using suchknowledge-based systems, we tend to forget the fundamental role of subjects (endusers)in the definition, observation and description of objects. In order to get goodidentification results, a consensus must be found between these experts andamateurs for interpreting correctly the observed objects. Thus, a new method ofKnowledge discovery is necessary by switching from Data mining to Signmanagement. The method focuses on the process of building knowledge bysharing signs and significations (Semiotic Web), more than on knowledgetransmission with intelligent object representations (Semantic Web). Signmanagement is the shift of paradigm for Biodiversity Informatics that we haveinvestigated in such domains as enhancing natural heritage with ICT. In this paper,we will present Sign management and illustrate this concept with two knowledgebases built in La Reunion Island for corals’ classification with IKBS (IterativeKnowledge Base System) and plants identification with Xper2 software platform.