Using Fuzzy Ontologies to Extend Semantically Similar Data Mining
نویسندگان
چکیده
Association rule mining approaches traditionally generate rules based only on database contents, and focus on exact matches between items in transactions. In many applications, however, the utilization of some background knowledge, such as ontologies, can enhance the discovery process and generate semantically richer rules. Besides, fuzzy logic concepts can be applied on ontologies to quantify semantic similarity relations among data. In this context, we extended SSDM (Semantically Similar Data Miner) algorithm in order to obtain from a fuzzy ontology the semantic relations between items. As a consequence, the generated rules can be more understandable, improving the utility of the knowledge supplied by them.
منابع مشابه
SSDM: A Semantically Similar Data Mining Algorithm
Most of association rule mining approaches aim to mine association rules considering exact matches between items in transactions. In this paper we present a new algorithm called SSDM (Semantically Similar Data Miner), which considers not only exact matches between items, but also the semantic similarity between them. SSDM uses fuzzy logic concepts to represent the similarity degree between item...
متن کاملSemantic Translation for Rule-Based Knowledge in Data Mining
Considering data size and privacy concerns in a distributed setting, it is neither desirable nor feasible to translate data from one resource to another in data mining. Rather, it makes more sense to first mine knowledge from one data resource and then translate the discovered knowledge (models) to another for knowledge reuse. Although there have been successful research efforts in knowledge tr...
متن کاملNARFO Algorithm: Mining Non-redundant and Generalized Association Rules Based on Fuzzy Ontologies
Traditional approaches for mining generalized association rules are based only on database contents, and focus on exact matches among items. However, in many applications, the use of some background knowledge, as ontologies, can enhance the discovery process and generate semantically richer rules. In this way, this paper proposes the NARFO algorithm, a new algorithm for mining non-redundant and...
متن کاملCan Data Mining Techniques Ease The Semantic Tagging Burden?
The effective implementation of the Semantic Web vision is highly dependent upon the widespread availability of large collections of semantically rich resources which are trustworthy and meaningful. Since semantic classification is dependent upon complex ontologies, a recognised difficulty is the steep learning curve presented to human classifiers when attempting to utilise such ontologies. One...
متن کاملDeveloping a Course Recommender by Combining Clustering and Fuzzy Association Rules
Each semester, students go through the process of selecting appropriate courses. It is difficult to find information about each course and ultimately make decisions. The objective of this paper is to design a course recommender model which takes student characteristics into account to recommend appropriate courses. The model uses clustering to identify students with similar interests and skills...
متن کامل