Hybrid Optimized Aritificial Intelligence Based Techniques for Big Data Classification in Healthcare Systems
Main Article Content
Abstract
Persistent patient monitoring with smart technologies has generated a considerable amount of medical data in recent years. Conventional healthcare measurements are ineffective in extracting useful data from sensors as well as social media data, and they struggle to analyses it properly. Furthermore, typical machine learning algorithms are insufficient for processing healthcare large data in order to anticipate abnormalities. To properly store and analyze healthcare data, as well as increase classification accuracy, a unique health monitoring architecture provided by the cloud infrastructure and a big data engine is presented. This evaluation of particular healthcare data collected through IoT can assist healthcare big data analytics. The suggested Lionized Heap Optimizer (LHO) based feature extraction and selection is used to choose the best features from the huge data for the classification process.
Furthermore, the suggested Hierarchy Golden Eagle Based Self-Constructing Neural Fuzzy (HGE-SNF) technique of classification technology performs accurate data categorization. The implementation of this research is carried out by MATLAB software. Finally, the performance of the proposed model is evaluated using various indicators and compared to traditional approaches.