Genetically optimized Fuzzy C-means data clustering of IoMT-based biomarkers for fast affective state recognition in intelligent edge analytics

IoMT sensors such as wearables, moodables, ingestible and trackers have the potential to provide a proactive approach healthcare. But grouping, traversing selectively tapping data traffic its immediacy makes management & decision analysis pressing issue. Evidently, selection process for real-world, time-constrained health problems involves looking at multivariate time-series generated simultaneously from various wearables resulting in overload accuracy issues. Computational intelligence of edge analytics can extend predictive capability by quickly turning digital biomarker into actions remote monitoring trigger alarm during emergency incidents without relying on backend servers. pervasive generation streams levies significant issues visualization exploratory analysis. This paper presents genetically optimized Fuzzy C-means clustering technique affective state recognition edge. Clustering segregates chunks generates summarized each subject which is then avoid stagnation local optima. A multi-level convolution neural network finally used classify states baseline, stress amusement categories. The model evaluated publicly available WESAD dataset compares favorably state-of-the-art with less time complexity. It demonstrates use numerosity reduction real-time intelligent facilitates fast user.