Mining of Frequent Maximal Itemsets Using Neural Network

Abstract

The task of discovering itemsets in databases was introduced in 1993 by Agrawal and Srikant3 as large itemset mining, but it is nowadays called frequent itemset mining (FIM). This paper proposes the Mining of Frequent maximal Itemsets using the technique of Optical Neural Networks. Since optical neural network performs many optical computations in nanoseconds, the time complexity is very low as compared to other data mining techniques. The data is stored in such a way that it minimizes space complexity to a large extent as database is scanned only once and stored in the form of weight matrix as in neural networks. The frequent patterns are then mined from this weight matrix using optical inputs. This approach discovers the frequent patterns quickly and effectively mines the potential association rules. It discovers frequent patterns by using the best features of data mining, optics and neural networks. This paper focuses on how this model can be helpful in generating frequent patterns for various applications.