الفهرس 
AbstractOnly 14 pages are availabe for public view
 |  | from | 157 |  |  |
| | | from | 157 | | |
Abstract
Recently, the design and implementation of new healthcare frameworks have gained an interest in both industry and academia. The amalgamation between the Internet of Things, cloud, edge computing, and big data helps the proliferation of new scenarios for smart medical services and applications. Also, Deep learning is currently paying a lot of attention for its utilization with big healthcare data. To this end, the main objective of this thesis is to propose a Deep Learning H2O (DLH2O) framework for improving the performance and selection of the optimal features to predict emergency healthcare cases. The proposed DLH2O framework consists of data preprocessing layer, feature selection layer, and deep learning layer. It aims to find the optimal subset of features and minimize classification error through a proposed new variant of the Whale Optimization Algorithm (WOA) called ACP-WOA where changes have been done on the parameters a, a2, A, and C that may closely adapt both exploration and exploitation of WOA. Five experiments are performed on the dataset PhysioNet MIMIC-II to test the validity of DLH2O Framework. The results demonstrate the superiority of DLH2O and ACP-WOA compared to others in terms of time, error, and scalability. The proposed ACP-WOA is also tested on CEC2017 benchmark functions and proves its superiority over WOA in terms of accuracy. ACP-WOA is proved to be better in all 29 functions of CEC2017.