A novel tool (FP-KC) for handle the three main dimensions reduction and association rule mining

This work attempt to developing the FP-Growth data mining algorithm through use several knowledge constructions to build up a novel tool called Frequency Pattern-Knowledge Constructions (FP-KC) to find the association rules and to satisfy the goal of dimension reduction methods is using the correlation structure among the predicator variables by reduction the main three dimensions (features, samples and value of features). FP-KC attempts to combine between the features of principle component analysis and frequency pattern growth. This done using the three criteria (Eigenvalue, cumulative variability and Scree plot). There are many reasons for developing the FP-Growth data mining algorithm in build up a novel algorithm FP-KC to find the association rules: (a) the size of an FP-tree is typically smaller than the size of the uncompressed data because many records in dataset often share a few items in common.(b) Given the best result, if all the records have the same set of items, and this point always satisfy in the scientific dataset. (c) FP-growth is an efficient algorithm because it illustrates how a compact representation of the transaction data set helps to efficiently generate frequent item sets. (d) The run-time performance of FP-growth depends on the compaction factor of the data set. The performance of FP-KC test using five huge databases including (Primate splice-junction gene sequences, Diabetes, DNA, GIS and Watermarking). The confidence´ degree of the all association rules yield by FP-KC is equal to 95%.