Efficient Generation of Association Rules from Numeric Data Using Genetic Algorithm for Smart Cities

Abstract

Machine learning plays an important role to develop smart cities by gathering real time information using several state of the art algorithms. In the recent past, association rule mining plays an important role in the discovery of accurate information from databases to satisfy the need of real time applications in smart cities ranging from healthcare to intelligent transport systems. It is used in various applications for decision making, detection and prediction etc. because of its robustness to derive associations among various attributes of datasets. This technique seems to be simple in case of categorical data but becomes quite complex in case of numeric data. In this work, we havemainly concentrated on the problem of generating association rules from numeric data in an efficientway. For accomplishing this task we have taken genetic algorithm as the base of the solution to this problem. Genetic algorithm is selected for this task because of its nature of self-improving and ability to handle large solution set. Here we have proposed genetic algorithm based association rule mining algorithm which generates random association rules on the basis of general property of datasets. The generated rule set is improved at each run of algorithm and filtered for more and more interesting and accurate rules.