Espresso for Rule Mining

The Rule-based systems generate many of the redundant rules. Such rules are expensive especially in online systems. Currently, there are many of the available rule minimization techniques; however, they still suffer from many challenges in exploiting parallelism, load balancing, efficient memory usage, minimization of communication cost, efficient data, task decomposition and others. This paper introduces a new approach for minimizing association rules based on the adaptation of Espresso algorithm, used in reducing Boolean expressions. We believe that our proposed method is a simple and efficient method that supports a large number of input and output variables. The proposed method starts by the usage of binary encoding followed by the minimization. In the last step, data decoding is utilized generating the final rules. Such rule minimization could be used in many applications including the Wireless Sensor Networks collected data. For testing purposes, a car data set has been used and the results seem promising compared to the original rules