Fuzzy based Hybrid Improvised High Utility Itemset Mining

The High Utility Itemset(HUI) in a big transactional database is analysed utilising a variety of methodologies, algorithms, and procedures. This research is beneficial for highlighting the issues associated in High Utility Itemset Mining (HUIM), and the suggested solution Hybrid Improvised High Utility Itemset Mining with Fuzzy is offered based on these challenges. The transaction database is changed into the fuzzy transaction database at first. The fuzzy transaction database is used to build a Fuzzy Utility Pattern Tree. Then, the memory management strategy is used on the Fuzzy Utility Pattern Tree, which fixes the problems with poor spatial and temporal locality. LS- Hash is used to index the itemset in a fuzzy transaction database to cut down on the amount of memory it needs. It also cuts down on the number of times a transaction database has to go through sets of items that aren't used very often. So, the combination of memory management and LS-Hash-based indexing reduces the amount of memory needed, avoids unnecessary traversal of itemsets that aren't used often, and makes it easy to get the itemsets back, which improves the HUIM. The results of the experiments show that the proposed Hybrid Improvised High Utility Itemset Mining Using Fuzzy (HIHUIM - F) runs faster and uses less memory than other methods already in use for the special children dataset.