摘要
The ongoing growth of the Internet of Things and machine learning technology have provided increased motivation for the development of smart healthcare. In this study, a disease diagnosis system is proposed for remote identification and early prediction in smart healthcare environments. The originality of this study resides in the innovative implementation of ensuing modules to improve diagnostic accuracy of the system. First, fuzzy clustering based on the forest optimization algorithm is employed to detect outliers and a self-organizing fuzzy logic classifier is applied to supplement missing data in electronic medical records (EMRs). A feature selection technique using the battle royale optimization algorithm is then developed to remove redundant information and identify optimal EMR features. The refined and fused data are further classified using an eigenvalue-based machine learning algorithm to determine whether a patient exhibits a certain disease. Simulation experiments are conducted with widely used heart disease and diabetes datasets to evaluate the performance of the proposed system, using accuracy, precision, recall, and F-measure as evaluation metrics.
| 源语言 | 英语 |
|---|---|
| 期刊论文编号 | 111123 |
| 期刊 | Applied Soft Computing |
| 卷 | 151 |
| DOI | |
| 出版状态 | 已出版 - 1月 2024 |
| 已对外发布 | 是 |
联合国可持续发展目标
此成果有助于实现下列可持续发展目标:
-
可持续发展目标 3 良好健康与福祉
学术指纹
探究 'A disease diagnosis system for smart healthcare based on fuzzy clustering and battle royale optimization' 的科研主题。它们共同构成独一无二的学术指纹。引用此
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver