Developing and Improved the Intelligent Search of Sequence of Patterns Using Fuzzy ontology and Semantic Similarities Approach

Classify and pattern selection in a set of data by applying pattern search algorithms or sequencing algorithm is called sequence mining .The purpose of identifying these patterns in data collection is analysis and interpretation of the data that are extracted from an event. In other words, we are looking to identify more detailed of systems that analysis of their events is desired. However, due to the complex and ambiguous nature of these systems, interpretations of the dependant events are always difficult. Depending on the events that their data should be analysis and interpret and also the type of extracted date structure, several algorithms have been proposed to find patterns. A criterion to classify and patterns selection is counting and number of repetitions of a particular data item in a sequence of data. Such an approach will be attention the schematic similarities and by selecting a sequence with this approach, perfect analysis and interpretation of systems event will not be expected. Ontology is clear and formal definition of a concept for the knowledge presentation that is understandable for humans and machine. So, the possibility of sharing it between different applications is provided. We proposed an intelligent search of sequence using fuzzy ontology and semantic similarity algorithm for looking at the similarity between items for identify more general patterns of sequence and number of repeats. Get sequences with such properties could facilitate the process of analysis and interpretation of case study events.

Keywords:

Data Mining , Sequence Mining Algorithm , Sequence Mining , Ontology , Fuzzy Systems , Fuzzy Sequence Mining , Semantic Similarities