Research Article
Ordered Frequent Itemsets Matrix Based On Fp-Tree Structure And Apriori Algorithm
|
International Journal of Applied Information Systems
Foundation of Computer Science (FCS), NY, USA
|
| Volume 12 - Issue 45 |
| Published: July 2024 |
| Authors: Abdulkader M. Al-Badani, Abdualmajed A. Al-Khulaidi |
10.5120/ijais2024451979
|
Abdulkader M. Al-Badani, Abdualmajed A. Al-Khulaidi . Ordered Frequent Itemsets Matrix Based On Fp-Tree Structure And Apriori Algorithm. International Journal of Applied Information Systems. 12, 45 (July 2024), 7-15. DOI=10.5120/ijais2024451979
@article{ 10.5120/ijais2024451979,
author = { Abdulkader M. Al-Badani,Abdualmajed A. Al-Khulaidi },
title = { Ordered Frequent Itemsets Matrix Based On Fp-Tree Structure And Apriori Algorithm },
journal = { International Journal of Applied Information Systems },
year = { 2024 },
volume = { 12 },
number = { 45 },
pages = { 7-15 },
doi = { 10.5120/ijais2024451979 },
publisher = { Foundation of Computer Science (FCS), NY, USA }
}
%0 Journal Article
%D 2024
%A Abdulkader M. Al-Badani
%A Abdualmajed A. Al-Khulaidi
%T Ordered Frequent Itemsets Matrix Based On Fp-Tree Structure And Apriori Algorithm%T
%J International Journal of Applied Information Systems
%V 12
%N 45
%P 7-15
%R 10.5120/ijais2024451979
%I Foundation of Computer Science (FCS), NY, USA
Abstract
Apriori and fp-growth are two well-known association rule algorithms that are well-known to data mining researchers. Nevertheless, the association rule algorithm has certain drawbacks, such as the need for large memory, lengthy dataset scans to determine the frequency of the item set, and occasionally less-than-ideal rules. To examine the rule outcomes of the three algorithms, the authors of this research compared the fp-growth, Apriori, and OFIM algorithms.In this paper, the suggest alterations to the FP-Growth algorithm's operation. By using the proposed matrix OFIM instead of the tree employed in those methods, the recommended algorithm would lower the number of often formed items and the amount of time spent mining, resulting in a considerable reduction in the amount of decision-making in large datasets. In comparison to the conventional tree-based technique, the matrix OFIM enables effective storing and retrieval of frequently occurring itemsets, leading to quicker calculation and result extraction. Furthermore, our technique significantly improves its speed in handling large datasets by limiting the amount of items that are produced often, thereby optimizing memory use.
References
No references available
Index Terms
Keywords