Enhanced Associative classification based on incremental mining Algorithm (E-ACIM)
Mustafa A. Al-Fayoumi, Saudi Arabia · 2015
Several association classification algorithms have been designed to build efficient and accurate associative classifiers for large data set . Most of classification algorithms are still suffer from the huge number of the generated classification rules which takes efforts to select the best ones in order to construct the classifier. Moreover, When different data operations (adding, deleting, updating) are applied against certain training data set, the majority of current AC algorithms must scan the complete training dataset again to update the results (classifier) in order to reflect changes caused by such operations. To overcome such drawbacks, the Associative Classification based on Incremental Mining (ACIM) algorithm has been proposed to handle with incremental data without jeopardizing the classification accuracy. The main assumption of ACIM algorithm is to build a classifier when new data arrive by utilizing the old classifier without rescanning to the entire dataset. This paper introduced a modified ACIM algorithm called Enhanced ACIM (E-ACIM). This algorithm deals with the data insertion problem in associative classification context. The E-ACIM is competitive and more efficient in computational time compared with ACIM and CBA algorithms and almost provides the same accuracy for both algorithms.