Fuzzy-Based Approach in Clustering Data Sources-A Case Study
In order to improve the effectiveness of community-wide cooperation, the capability of extracting sharable knowledge from heterogeneous documents produced by multiple sources and in a timely fashion is therefore crucial. To this kind of demand is to supply a suite of tools for the end user and for the developer as well, to create, maintain and navigate an ontology generated from an varied amount of data. To wrap the set of data sources in a structured format, such as XML and, using fuzzy techniques in order to compare the incoming dataflow, cluster them in a semi-automatic way. The final purpose is to generate a browsable ontology of the processed resources.