Chun Wei Lin

An effective tree structure for mining high utility itemsets

Research highlights? In this paper, the high utility pattern tree (HUP tree) is designed. ? The HUP-growth mining algorithm is proposed to derive high utility patterns effectively and efficiently. ? The proposed approach integrates the previous two-phase procedure for utility mining and the FP-tree concept to utilize the downward-closure property and generate a compressed tree structure. In the past, many algorithms were proposed to mine association rules, most of which were based on item frequency values. Considering a customer may buy many copies of an item and each item may have different profits, mining frequent patterns from a traditional database is not suitable for some real-world applications. Utility mining was thus proposed to consider costs, profits and other measures according to user preference. In this paper, the high utility pattern tree (HUP tree) is designed and the HUP-growth mining algorithm is proposed to derive high utility patterns effectively and efficiently. The proposed approach integrates the previous two-phase procedure for utility mining and the FP-tree concept to utilize the downward-closure property and generate a compressed tree structure. Experimental results also show that the proposed approach has a better performance than Liu et al.s two-phase algorithm in execution time. At last, the numbers of tree nodes generated from three different item ordering methods are also compared, with results showing that the frequency ordering produces less tree nodes than the other two.

The Pre-FUFP algorithm for incremental mining

The frequent pattern tree (FP-tree) is an efficient data structure for association-rule mining without generation of candidate itemsets. It was used to compress a database into a tree structure which stored only large items. It, however, needed to process all transactions in a batch way. In real-world applications, new transactions are usually incrementally inserted into databases. In the past, we proposed a Fast Updated FP-tree (FUFP-tree) structure to efficiently handle new transactions and to make the tree update process become easier. In this paper, we attempt to modify the FUFP-tree construction based on the concept of pre-large itemsets. Pre-large itemsets are defined by a lower support threshold and an upper support threshold. It does not need to rescan the original database until a number of new transactions have been inserted. The proposed approach can thus achieve a good execution time for tree construction especially when each time a small number of transactions are inserted. Experimental results also show that the proposed Pre-FUFP maintenance algorithm has a good performance for incrementally handling new transactions.

Incrementally fast updated sequential pattern trees

In the past, the FUFP-tree maintenance algorithm is proposed to efficiently handle the association rules in incremental mining. In this paper, we attempt to modify the FUFP-tree maintenance algorithm for maintaining sequential patterns based on the concept of pre-large sequences to reduce the need for rescanning original databases in incremental mining. A fast updated sequential pattern trees (FUSP trees) structure and the maintenance algorithm are proposed, which makes the tree update process become easier. It does not require rescanning original customer sequences until the accumulative amount of newly added customer sequences exceed a safety bound, which depends on database size. The proposed approach thus becomes efficiently and effectively for handling newly added customer sequences.

Linguistic data mining with fuzzy FP-trees

Due to the increasing occurrence of very large databases, mining useful information and knowledge from transactions is evolving into an important research area. In the past, many algorithms were proposed for mining association rules, most of which were based on items with binary values. Transactions with quantitative values are, however, commonly seen in real-world applications. In this paper, the frequent fuzzy pattern tree (fuzzy FP-tree) is proposed for extracting frequent fuzzy itemsets from the transactions with quantitative values. When extending the FP-tree to handle fuzzy data, the processing becomes much more complex than the original since fuzzy intersection in each transaction has to be handled. The fuzzy FP-tree construction algorithm is thus designed, and the mining process based on the tree is presented. Experimental results on three different numbers of fuzzy regions also show the performance of the proposed approach.

An Incremental FUSP-Tree Maintenance Algorithm

In this paper, we attempt to handle the maintenance of sequential patterns. New transactions may come from both the new customers and old customers. A fast updated sequential pattern tree (called FUSP-tree) structure is proposed to make the tree update process become easy. An incremental FUSP-tree maintenance algorithm is also proposed for reducing the execution time in reconstructing the tree. The proposed approach is expected to achieve a good trade-off between execution time and tree complexity.

An Efficient Tree-based Fuzzy Data Mining Approach

In the past, many algorithms were proposed for mining association rules, most of which were based on items with binary values. In this paper, a novel tree structure called the compressed fuzzy frequent pattern tree (CFFP tree) is designed to store the related information in the fuzzy mining process. A mining algorithm called the CFFP-growth mining algorithm is then proposed based on the tree structure to mine the fuzzy frequent itemsets. Each node in the tree has to keep the membership value of the contained item as well as the membership values of its super-itemsets in the path. The database scans can thus be greatly reduced with the help of the additional information. Experimental results also compare the performance of the proposed approach both in the execution time and the number of tree nodes at two different numbers of regions, respectively.

Efficiently mining high average utility itemsets with a tree structure

The average utility measure has recently been proposed to reveal a better utility effect of combining several items than the original utility measure. It is defined as the total utility of an itemset divided by its number of items within it. In this paper, a new mining approach with the aid of a tree structure is proposed to efficiently implement the concept. The high average utility pattern tree (HAUP tree) structure is first designed to help keep some related information and then the HAUP-growth algorithm is proposed to mine high average utility itemsets from the tree structure. Experimental results also show that the proposed approach has a better performance than the Apriori-like average utility mining.

An Efficient FUSP-Tree Update Algorithm for Deleted Data in Customer Sequences

In the past, the fast-updated sequential-pattern tree (call FUSP-tree) structure was proposed for mining sequential patterns from a set of customer sequences. An incremental mining algorithm was also designed for handling newly added transactions. Since data may also be deleted in real applications, an FUSP-tree maintenance algorithm for deletion of customer sequences is thus proposed in this paper for reducing the execution time in reconstructing the tree. Experimental results also show that the proposed treeupdate algorithm has a good performance than the batch FUSP-tree algorithm for handling the deletion of customer sequences. The proposed tree-update algorithm thus makes the tree update process become easy and efficient.

Incremental Mining with Prelarge Trees

In the past, we proposed a Fast Updated FP-tree (FUFP-tree) structure to efficiently handle new transactions and to make the tree-update process become easy. In this paper, we propose the structure of prelarge trees to incrementally mine association rules based on the concept of pre-large itemsets. Due to the properties of pre-large concepts, the proposed approach does not need to rescan the original database until a number of new transactions have been inserted. Experimental results also show that the proposed approach has a good performance for incrementally handling new transactions.

Using the Structure of Prelarge Trees to Incrementally Mine Frequent Itemsets

The frequent pattern tree (FP-tree. is an efficient data structure for association-rule mining without generation of candidate itemsets. It was used to compress a database into a tree structure which stored only large items. It, however, needed to process all transactions in a batch way. In the past, we proposed a Fast Updated FP-tree (FUFP-tree. structure to efficiently handle new transactions and to make the tree update process become easier. In this paper, we propose the structure of prelarge trees to incrementally mine association rules based on the concept of pre-large itemsets. Due to the properties of pre-large concepts, the proposed approach does not need to rescan the original database until a number of new transactions have been inserted. The proposed approach can thus achieve a good execution time for tree construction especially when a small number of transactions are inserted each time. Experimental results also show that the proposed approach has a good performance for incrementally handling new transactions.