A Deep Swarm-Optimized Model for Leveraging Industrial Data Analytics in Cognitive Manufacturing

To compete in the current data-driven economy, it is essential that industrial manufacturers leverage real-time tangible information assets and embrace big data technologies. Data classification one of most proverbial analytical techniques within cognitively capable manufacturing industries for finding patterns structured unstructured at plant, enterprise, industry levels. This article presents a cognition-driven analytics model, CNN-WSADT, using three soft computing techniques, namely, deep learning [convolution neural network (CNN)], machine [decision tree (DT)], swarm intelligence [wolf search algorithm (WSA)]. The proposed swarm-optimized classifier feature-boosted DT, which learns features convolution net an optimal feature set built metaheuristic WSA. performance CNN-WSADT studied on two benchmark datasets experimental results depict cognition model outperforms other considered algorithms terms accuracy.