Distributed Fuzzy Cognitive Maps a Scalable Framework for Big Data Modelling

Abstract

In the era of digital transformation, big data analytics has become crucial for newlinederiving insights and making informed decisions across various domains. newlineHowever, the sheer volume, velocity, and variety of big data pose significant newlinechallenges to traditional data processing methodologies, particularly in terms of newlinescalability and interpretability. This study addresses these critical gaps by newlineinvestigating the potential of Distributed Fuzzy Cognitive Maps (FCMs) in newlinetackling key challenges in big data analytics, including feature reduction, newlinedistributed classification, large-scale network processing, and temporal data newlineanalysis. newlineCurrent approaches in big data analytics often struggle with the trade-off newlinebetween computational efficiency and model interpretability, especially when newlinedealing with complex, high-dimensional datasets. Moreover, existing methods newlinefrequently fall short in providing scalable solutions that can adapt to the newlineever-increasing size of datasets while maintaining analytical depth. This research newlineaims to bridge these gaps by developing novel FCM-based techniques that offer newlineboth scalability and interpretability. newline