![]() ![]() There are also some other proposed solutions that can not only reduce the number of PARs, but also reserve the same information(see, for instance,, ,, ,, ,, ,, ). One typical solution is to increase the minimum confidence, but this will lose a lot of important information. ![]() In fact, this problem has been found and solved when researchers mined PARs only, ,, ,, ,. A typical situation is that a large number of PNARs will be mined and this will increase the difficulties for users to retrieve relevant decision-information. Many problems would occur when mining PNARs. Hence, many researchers have focused on mining positive and negative association rules (PNARs) simultaneously, ,,. Many studies, ,, ,, , have mentioned that NARs can provide more valuable information, and sometimes play irreplaceable roles by PARs alone in many areas. And the rules at other three forms A⇒¬ B, ¬ A⇒ B, ¬ A⇒¬ B, which can indicate the negative relations between items, are called negative association rules (NARs). Generally, a rule at the form A⇒ B, which can indicate the positive relations between different items, is called positive association rule (PAR). ![]() An association rule is called a valid rule if its support is greater than a user-defined minimum support ( ms) threshold and its confidence greater than a user-defined minimum confidence ( mc) threshold. Association rules, which can discover the positive or negative relations between different items, have received a great deal of attention recently in many applications, such as web mining, recommender systems, and intrusion detection. ![]()
0 Comments
Leave a Reply. |