دانلود رایگان مقاله قوانین انجمن متا برای انجمن های جالب توجه استخراج معدن

Abstract

Association rules have been widely used in many application areas to extract new and useful information expressed in a comprehensive way for decision makers from raw data. However, raw data may not always be available, it can be distributed in multiple datasets and therefore there resulting number of association rules to be inspected is overwhelming. In the light of these observations, we propose meta-association rules, a new framework for mining association rules over previously discovered rules in multiple databases. Meta-association rules are a new tool that convey new information from the patterns extracted from multiple datasets and give a “summarized” representation about most frequent patterns. We propose and compare two different algorithms based respectively on crisp rules and fuzzy rules, concluding that fuzzy meta-association rules are suitable to incorporate to the meta-mining procedure the obtained quality assessment provided by the rules in the first step of the process, although it consumes more time than the crisp approach. In addition, fuzzy meta-rules give a more manageable set of rules for its posterior analysis and they allow the use of fuzzy items to express additional knowledge about the original databases. The proposed framework is illustrated with real-life data about crime incidents in the city of Chicago. Issues such as the difference with traditional approaches are discussed using synthetic data.

7. Conclusions and future work

Meta-association rules are proposed in this paper as rules about rules that can be employed when the available information about several datasets is in the form of association rules. The main advantage of the meta-rules is that they can extract information that is not achieved by simple regular rules and that they allow the analysis of associations coming frequently in a group of databases,thatin many cases, may overwhelm the user. Moreover, meta-association rules can incorporate contextual information related to the original datasets in order to enrich the associations obtained by the meta-rules. We have proposed different types of meta-association rules: crisp and fuzzy meta-rules. Fuzzy meta-rules take advantage of the assessment measures provided when mining rules from the original datasets.We have compared the different approaches obtaining that, in general, mining fuzzy meta-rules gives a more manageable set of rules for its posterior analysis and that they allow the use of fuzzy items to express additional knowledge about the original databases. In the near future we plan to develop an intuitive interface for setting the input parameters as well as showing obtained metarules in a understandable way. Moreover, this work opens several issues to be addressed in the future. For instance, when the description of attributes is not the same in all the databases, we may have a problem, since the set of regular rules obtained in the first step of the process may contain different attribute names although they refer to the same item. A solution to this could be to have a “dictionary” or a knowledge repository that links similar concepts. Another interesting application is to consider meta-rules for analysing streaming data. In this case, the proposed process could be adapted to take into account different time granularities. We plan to advance in this line for analysing data collected from sensors in different time periods.