Constrained Big Data Mining in an Edge Computing Environment

High volumes of wide varieties of valuable data of different veracity can be easily generated or collected at a high velocity from various big data applications and services. A rich source of these big data is the Internet of Things (IoT), which can be viewed as a network of sensors, mobile devices, wearable devices, and other “things” that are capable to operate within the existing Internet infrastructure. As a popular data science task, frequent pattern mining aims to discover implicit, previously unknown and potentially useful information and valuable knowledge—in terms of sets of frequently co-occurring items—embedded in these big data. Existing frequent pattern mining algorithms mostly run serially on a single local computer or in distributed and parallel environments on computer clusters, grids, or clouds. Many of these algorithms return large numbers of frequent patterns, of which only some may be of interest to the user. In this paper, we present a constrained big data mining algorithm that (i) focuses the mining to those frequent patterns that are interested to the users and (ii) runs in an edge computing environment, in which computation is performed at edges of the computing network.