Big Data Analytics Model with Deep Learning Architecture to Evaluate Live Dance Ecology Through the Internet

Abstract

Dance ecology, a burgeoning field at the intersection of dance, technology, and environmental studies, relies on real-time data analysis for understanding and optimizing dance performances. This paper proposed a novel Parallel Edge Big Data Analytics (PEBDA) framework, designed to efficiently process and analyze dance movement data in real time. The proposed PEBDA model uses parallel processing in the edge computing model for the analysis of the live dance ecology. Through the parallel processing of the edge model in the network big data analytics is implemented for the estimation of the multiple nodes in the network. The PEBDA model estimates the nodes across multiple environments for the examination of the ecology in the live dance. Finally, through parallel processing classification is performed with the deep learning model for the classification of live dance ecology in the computing platform. The proposed PEBDA framework, assesses classification accuracy, precision, recall, and F1-score. The simulation analysis expressed that Node 8 consistently outperforms others, achieving exceptional accuracy and precision levels above 0.97. These findings highlight the potential of edge computing in revolutionizing dance ecology analysis, enabling enhanced real-time monitoring, decision-making, and optimization of dance performances.