A Parallel Military-Dog-Based Algorithm for Clustering Big Data in Cognitive Industrial Internet of Things

With the advancement of wireless communication, Internet Things (IoT), and big data, high performance data analytic tools algorithms are required. Data clustering, a promising technique is widely used to solve IoT big-data-based problems, since it does not require labeled datasets. Recently, metaheuristic have been efficiently various clustering problems. However, handle datasets produced from devices, these algorithm fail respond within desired time due computation cost. This article presents new metaheuristic-based method problems by leveraging strength MapReduce. The proposed methods leverages searching potential military dog squad find optimal centroids MapReduce architecture optimization efficacy validated against 17 benchmark functions, results compared with five other recent algorithms, namely, bat, particle swarm optimization, artificial bee colony, multiverse whale algorithm. Furthermore, parallel version introduced using [MapReduce-based MDBO (MR-MDBO)] for industrial IoT. Moreover, MR-MDBO studied on two UCI three real IoT-based industry. F-measure six state-of-the-art methods. experimental witness that MR-MDBO-based outperforms considered in terms accuracy times.