Research Article
An Improved Apriori Algorithm Based on an Evolution-Communication Tissue-Like P System with Promoters and Inhibitors
Input: | The objects encoded from the transactional database and objects representing the support count | threshold . | Rule : | Copy all and to cells 1 to . | Method: | | Rule : | Generate for to form the candidate frequent 1-itemsets . | Rule : | Scan each object in cell 1 to count the frequency of each item. If is in cell 1, consume one and | generate one . Continue until all copies of have been consumed or all objects have been scanned. | Rule : | If all copies of have been consumed, generate an object to add to as a frequent 1-itemset | and pass to cells 2 and . Delete all remaining copies of and delete all copies of . | For ( and ) do the following in cell : | | Rule : | Scan the objects representing the frequent ()-itemsets to generate the objects | representing the candidate frequent -itemsets . | Rule : | Delete all objects after they have been used by rule . | Rule : | Scan the objects representing the database to count the frequency of each candidate frequent -itemset | . If the objects and are all in cell , consume one and generate one . | Continue until all copies of have been consumed or all objects have been scanned. | Rule : | If all copies of have been consumed, generate to add to as a frequent | -itemset and put in cells and . Delete all remaining copies of and delete all copies | of . | Let . | | Output: | The collection of all frequent itemsets encoded by objects . |
|