Research On Association Rules Mining Based On Temporal Data

Temporal data mining has become an important branch and quite study circumstance of data mining field. At present, most of the studies about its association rule mining lack united theoretical frameworks, and model and correspcaiding algorithm based on tenporaal data are only applied to some special date type. What's more, along with introducing of fuzzy set and rough set theory, how to applied uncertainty theory to mine isn't also solved etc.In this thesis, at first by means of analysis and study of idea of association rule of transaction database based on mutuality set and with the aid of including degree of uncertainty reasoning, confidence degree based on including degree is compared with accuracy of rough set We discover that they are the same formula of mathematics derivation. What' more, increment computing formulas of confidence degree is deduced,, .In Ihe studies of mining of time series, with the aid of rough set theory, pure mathematics methods of tradition are transformed into artificial intelligence and mathematics methods. Mining thoughts and methods with rough set theory are studied Tactics of mining with rough set are summarized.Secondly for the issue of depicting valid-time of association rule, science description of temporal type andaccording support degree confidence degree and association rule of temporal data of different type are studied. By applying them to transaction database, we discover that they possess better analysis and applied value.At last, it is necessary to apply fuzzy idea into mining of association rule of temporal data.