Incremental mining of weighted maximal frequent itemsets from dynamic databases

Yun, Unil; Lee, Gangin

doi:10.1016/j.eswa.2016.01.049

Cited by 64 publications

(12 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Incremental in itemsets means an additional new items being added or deleted to the existing itemsets in database whereas incremental in records of transaction means the additional transactions to the existing database transaction. The algorithm for mining weighted maximal frequent itemsets from incremental databases is introduced [26]. By scanning a given incremental database only once, the proposed algorithm extracts a smaller number of important itemsets and provide more meaningful pattern results reflecting characteristics of given incremental databases and threshold settings.…”

Section: The Incremental Approach 51 Incremental Based On Apriori Amentioning

confidence: 99%

i-Eclat: performance enhancement of eclat via incremental approach in frequent itemset mining

Bakar

Man

et al. 2020

TELKOMNIKA

View full text Add to dashboard Cite

One example of the state-of-the-art vertical rule mining technique is called equivalence class transformation (Eclat) algorithm. Neither horizontal nor vertical data format, both are still suffering from the huge memory consumption. In response to the promising results of mining in a higher volume of data from a vertical format, and taking consideration of dynamic transaction of data in a database, the research proposes a performance enhancement of Eclat algorithm that relies on incremental approach called an Incremental-Eclat (i-Eclat) algorithm. Motivated from the fast intersection in Eclat, this algorithm of performance enhancement adopts via my structured query language (MySQL) database management system (DBMS) as its platform. It serves as the association rule mining database engine in testing benchmark frequent itemset mining (FIMI) datasets from online repository. The MySQL DBMS is chosen in order to reduce the preprocessing stages of datasets. The experimental results indicate that the proposed algorithm outperforms the traditional Eclat with 17% both in chess and T10I4D100K, 69% in mushroom, 5% and 8% in pumsb_star and retail datasets. Thus, among five (5) dense and sparse datasets, the average performance of i-Eclat is concluded to be 23% better than Eclat.

show abstract

Section: The Incremental Approach 51 Incremental Based On Apriori Amentioning

confidence: 99%

i-Eclat: performance enhancement of eclat via incremental approach in frequent itemset mining

Bakar

Man

et al. 2020

TELKOMNIKA

View full text Add to dashboard Cite

show abstract

“…Lin and Lo (2013) recommended some set of algorithms such as, equal working set (EWS), request on demand (ROD), small size working set (SSWS) and progressive size working set (PSWS) to provide a scalable and fast mining service for frequent mining pattern. Yun and Lee (2016) developed an incremental mining algorithm to find the frequent item sets from the dynamic databases. In this paper, the correctness of the proposed algorithm was guaranteed based on the incremental pattern mining.…”

Section: Related Workmentioning

confidence: 99%

A novel single scan distributed pattern mining algorithm for frequent pattern identification

Yousuf¹,

Devi²

2019

IJDATS

View full text Add to dashboard Cite

In data mining, the extraction of frequent patterns from large databases is still a challenging and difficult task due to the various drawbacks such as, high response time, communication cost to alleviates such issues, a new algorithm namely single scan distributed pattern mining algorithm (SSDPMA) is proposed in this paper for frequent mining. The frequent patterns are extracted in a single scan of the database. Then, it is split into multiple files, which will be shared to multiple virtual machines (VMs) to store and compute the weight for the distinct records. Then, the support, confidence and threshold values are estimated. If the limit is greater than the given data, the frequent data are mined by using the proposed SSDPMA algorithm. The experimental results evaluate the performance of the proposed system in terms of response time, message size, execution time, run time and memory usage.

show abstract

“…To obtain concise and lossless representations, the problems of frequent closed itemset mining (FCIM) [6] and frequent maximal itemset mining [7] were proposed. Then, based on the concept of these compact representations, researchers conducted further studies [8][9][10][11][12][13][14]. However, FIM has the drawback that the importance of all items in a database is equal, which cannot fully reflect the characteristics of real-world databases.…”

Section: Introductionmentioning

confidence: 99%

FCHUIM: Efficient Frequent and Closed High-Utility Itemsets Mining

et al. 2020

View full text Add to dashboard Cite

Mining a closed high-utility itemset is a prevalent research task in analyzing transaction databases. However, numerous target itemsets are generated in the closed high-utility itemset mining task. As a result, too many closed high-utility itemsets (CHUIs) will not only increase the time and memory consumption but also make it difficult for users to analyze the results. To address this problem, this paper proposes an efficient algorithm called FCHUIM, which is used to mine a concise representation called the frequent closed high-utility itemset (FCHUI). FCHUIM is based on a total summary list structure for storing and retrieving utility lists without repeatedly scanning the database. In addition, the proposed algorithm uses an effective upper bound on the utility of items to efficiently reduce the search space. Furthermore, a precheck method and a nested list structure are also introduced in this work to quickly discover FCHUIs. To test the performance of FCHUIM, we conduct extensive experiments on real-life and synthetic databases. We also select two state-of-the-art algorithms to compare with FCHUIM: CHUI-Miner and CLS-Miner. The results show that FCHUIM performs well on databases, whether the databases are dense or sparse.

show abstract

Incremental mining of weighted maximal frequent itemsets from dynamic databases

Cited by 64 publications

References 44 publications

i-Eclat: performance enhancement of eclat via incremental approach in frequent itemset mining

i-Eclat: performance enhancement of eclat via incremental approach in frequent itemset mining

A novel single scan distributed pattern mining algorithm for frequent pattern identification

FCHUIM: Efficient Frequent and Closed High-Utility Itemsets Mining

Contact Info

Product

Resources

About