Conditioning And Fast Three Traversal-based Association Rules Mining Algorithm, Based On Space-time

Data Ming is a most active and new research in the field of Artificial Intellegince and field of Database in the world. It's goal is to satisfy the users'need, process the great amount of ariginal data and identify the important and interesting patterns in it. And at last expressing them in the form of knowledge which people can recganize at their first sight. Data Ming is a kind of process that reveals potencial useful knowledge from massive data. It is an efficient way to tackle "Data Rich and Information Poor".Association rules are an important aspect of research of Data Ming. This dissertation reviews the problems of mining association rules.Associatin analysis is the discovery of association rules showing attribute value conditions that occur frequently together in a given set of data. Association analysis is widely used for market basket or transaction data analysis. In recent years, many algorithems have been proposed for the efficient mining of association rules. The discovery of association relationships among huge amount of data is useful in selective marketing,decisin analysis,and business management. A popular area of application is studing the buying habits of customers by searching for sets of items that are frequently purchased together. In the light of the defects of the other arithmatics of mining association rules, this dissertation suggests two algorithoms: Quick Association Rules Mining Algorithom Based on Three Times Scan of the Database and Association Rules Mining Algarithom Based on Balance Between Time and Space. Quick Association Rules Mining Algorithom Based on Three Times Scan of the Database scans the DB only three times, and produces a more small amount of candidate patterns when it looks for the frequent patterns of the DB, using theory that the parent pattern of the non_frequent pattern is non freqent pattern. So it can reduce the scale of the candidate frequent patterns greatly. It can be easily implemented, and can improves the efficiency greatly. Abstract Association Rules Mining Algarithom Based on Balance Between Time and Space finds association rules through the angle of memory space the users can offer, through setting a suitabale step length, and can do it more efficiently. The algorithoms has shown advantages such as: 1) High efficiency. Comparing with other association rules minimg algorithoms that have been exist, they can reduce the times they need to scan the DB. 2) Keep a good balance between the time and the memory space. Through adopting the methods of setting an suitabale step length, it can make fully use of the EMS memory the users can afford, so at the same time of reducing the times it need to scan the DB, it can keep a good balance between the running time and EMS memory it needs, and can achive an most suitabale precept for the users.