Have a personal or library account? Click to login
Frequent Itemset Mining for Big Data Using Greatest Common Divisor Technique Cover

Frequent Itemset Mining for Big Data Using Greatest Common Divisor Technique

Open Access
|May 2017

Figures & Tables

Table 1

Dataset Horizontal Representation.

TIDITEMS
T1I1, I2, I3, I4, I5, I6
T2I1, I2, I4, I7
T3I1, I2, I4, I5, I6
T4I1, I2
T5I3
T6I2
T7I7
Table 2

Ignore List for Support Count 3.

I3
I5
I6
I7
I3 I5
I3 I6
I3 I7
I5 I6
I5 I7
I6 I7
I3 I5 I6
I3 I5 I7
I3 I6 I7
I5 I6 I7
Table 3

Transactions Representations.

Transaction IDItemsItems Repetition and Prime AssignmentRepetitionString ordered representationPrime Multiplication
T1I1, I2, I3, I4, I5, I6R(I1) = 4, R(I2) = 5 and
R(I4) = 3 Then
P(I1) = 3, P(I2) = 2 and P(I4) = 5
32   3   530
T2I1, I2, I4, I7
T3I1, I2, I4, I5, I6
T4I1, I2P(I1) = 3
P(I2) = 2
12   36
T5I3
T6I2P(I2) = 2122
T7I7
Table 4

Partitioning Process.

Transaction IDString RepresentationPartition Number
T12 3 7Par 1 for all transactions with string representation starting by “2”
T23 7 11Par 2 for all transactions with string representation starting by “3”
T311 19 23Par 3 for all Transaction with string representation starting by “11”
T42  23 29Par 1 for all transactions with string representation starting by “2”
T53 31 37Par 2 for all transactions with string representation starting by “3”
T611 53 59Par 3 for all transactions with string representation starting by “11”
T729 31 37Par 4 for all transactions with string representation starting by “29”
Table 5

Datasets Used For the experiment.

Dataset NameNumber of TransactionsNumber of Items
Mushroom812490
letRecog20000106
Adult4884297
Retail8814616469
Table 6

Test Results with Retail Dataset.

Time Consumed in Seconds
Support CountFP-GrowthParallel AprioriPOBPA
30%2837<0.05
40%2634<0.05
50%22.132.9<0.05
60%22.0432.3<0.05
70%21.1927<0.05
Table 7

Test Results with Mushroom Dataset.

Time Consumed in Seconds
Support CountFP-GrowthParallel AprioriPOBPA
30%59130.88
40%483.90.64
50%321.90.15
60%301.50.07
70%281.4<0.05
Table 8

Test Results with Letter Recognition.

Time Consumed in Seconds
Support CountFP-GrowthParallel AprioriPOBPA
30%2733824
40%2002314
50%179183
60%150181.2
70%110150.05
Table 9

Test Results with Adult dataset.

Time Consumed in Seconds
Support CountFP-GrowthParallel AprioriPOBPA
30%400241.8
40%328101.5
50%30080.82
60%21360.75
70%20040.5
Language: English
Submitted on: Nov 21, 2016
Accepted on: Apr 26, 2017
Published on: May 18, 2017
Published by: Ubiquity Press
In partnership with: Paradigm Publishing Services
Publication frequency: 1 issue per year

© 2017 Mohamed A. Gawwad, Mona F. Ahmed, Magda B. Fayek, published by Ubiquity Press
This work is licensed under the Creative Commons Attribution 4.0 License.