Semantic Similarity Measure of Fuzzy XML DTDs with Extreme Learning Machine

Data integration for distributed and heterogeneous XML data sources is still an open challenging, and XML DTD matching is crucial task in this process. A considerable amount of algorithms for comparing XML DTDs have been proposed in the literature. Yet, the existing approaches fall short in ability to identify semantic similarities in fuzzy XML DTDs. To fill this gap, in this paper, we provide an approach to cope with semantic similarities in the fuzzy XML DTDs. The present paper makes two major contributions. First, we propose a novel fuzzy XML DTD tree model to represent fuzzy XML DTD. Second, based on the proposed tree model, we present an effective algorithm based on Extreme Learning Machine (ELM) to synthesize the semantic similarities between fuzzy XML DTDs. The corresponding computational experimental results demonstrate that our proposed approach has a prominent high performance.