Batch Processing for Incremental FP-tree Construction

Totad, Shashikumar G.; Geeta, R. B.; Reddy, Pvgd Prasad

doi:10.5120/910-1288

Cited by 8 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The above trees fail to take advantage of this periodical mining of frequent patterns. Working in this direction, Totad et al [20] in the year 2010, designed an algorithm, called BIT(Batch Incremental Tree), which later extended [21] in the year 2012, constructs the FP-Tree periodically and merges them instead of incrementing it after every new transaction entry. Here the nodes in the tree are sorted according to their frequency count, hence while merging, the frequency count needs to be taken into account.…”

Section: Bitmentioning

confidence: 99%

GM-Tree: An efficient frequent pattern mining technique for dynamic database

Roul

Bansal

2014

2014 9th International Conference on Industrial and Information Systems (ICIIS)

View full text Add to dashboard Cite

Since its inception, mining frequent patterns have become an imperative issue in data mining. The main problem in this area is to find out the association rule that identifies the relationships among a set of items. But the most expensive step in association rule is finding frequent itemsets and hence it draw the attention of many important research. In this paper, we propose a novel tree structure, called GM(Generate and Merge)Tree, which is a combination of prefix based incremental mining using canonical ordering and batch incrementing techniques. Our approach makes the tree structure more compact, canonically ordered of nodes and avoids sequential incrementing of transactions. It also helps to give a scalable algorithm with minimum overheads of modifying the tree structure during update operations. This algorithm is especially expected to give better results in case of extremely large transaction database in a dynamic environment. The experimental work has been carried out on two large datasets. Test results show the efficiency and effectiveness of the proposed approach by outperforming the traditional FP-Tree, CanTree(Canonical-order Tree) and BIT(Batch Incremental Tree).

show abstract

Section: Bitmentioning

confidence: 99%

GM-Tree: An efficient frequent pattern mining technique for dynamic database

Roul

Bansal

2014

2014 9th International Conference on Industrial and Information Systems (ICIIS)

View full text Add to dashboard Cite

show abstract

“…In addition, the construction of FP-Tree is carried out through offline. Since the idea of FP-Tree, there are abundant researches have been put forward such as H-Mine [13], PatriciaMine [14], FPgrowth* [15], SOTrieIT [16], AFOPF [5], AFPIM [6], EFPIM [7], CATS-Tree [8], CanTree [17], FUFP-Tree [9], CP-Tree [18], BSM [19] and BIT [11]. Due to the limitations faced by FP-Growth algorithm, the H-Mine [13], PatriciaMine [14] and FPgrowth* are proposed.…”

Section: Related Workmentioning

confidence: 99%

“…However, the construction process of CanTree is quite complicated and still questionable due to overhead cost in adjusting the tree structure when the portion of database is updated. BIT [11] algorithm merges two small …”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Fast Determination of Items Support Technique from Enhanced Tree Data Structure

Abdullah¹,

Herawan²,

Ahmad³

et al. 2014

IJSEIA

View full text Add to dashboard Cite

show abstract

“…Existing serial FIM algorithms such as FP-Growth [4] and SPO-Tree can be resource intensive when the dataset is large-scale. Parallel algorithms were developed to reduce memory use and CPU cost on each machine especially in large-scale FIM [5] [6].…”

Section: Introductionmentioning

confidence: 99%

MapReduce-based frequent itemset mining for analysis of electronic evidence

Jiang

Sun

2013

2013 8th International Workshop on Systematic Approaches to Digital Forensics Engineering (SADFE)

View full text Add to dashboard Cite

Association rules can mine the relevant evidence of computer crime from the massive data and association rules among data itemset, and further mine crime trends and connections among different crimes. They can help polices detect case and prevent crime with clues and criterions. Frequent itemset mining (FIM) plays a fundamental role in mining associations, correlations and many real-world data mining fields such as electronic evidence analysis area. FP-growth is the most famous FIM algorithm for discovering frequent patterns. As the data incrementing, the cost of time and space will be the bottleneck of FP-growth mining algorithms. One of the existing incremental frequent pattern mining algorithms called SPO-tree can perform incremental mining by a single scan for incremental mining. But how to apply this algorithm to the analysis of electronic evidence more effectively will become the focus of this paper. In the past research, little people take care of the item mined to the frequent item needing to update or inserted a little data. The past algorithms are not suit for this problem especially in forensic area. So, in this paper, we propose a novel parallelized algorithm called PISPO based on the cloud-computing framework MapReduce, which is widely used to cope with largescale data and captures both the content and state to be distributed to the changed and original of the transactions dataset to SPO-tree.

show abstract

Batch Processing for Incremental FP-tree Construction

Cited by 8 publications

References 12 publications

GM-Tree: An efficient frequent pattern mining technique for dynamic database

GM-Tree: An efficient frequent pattern mining technique for dynamic database

Fast Determination of Items Support Technique from Enhanced Tree Data Structure

MapReduce-based frequent itemset mining for analysis of electronic evidence

Contact Info

Product

Resources

About