Big Data based medical data classification using oppositional Gray Wolf Optimization with kernel ridge regression
| Autor: | K. Shankar, S. Venkata Lakshmi, Sujatha Krishamoorthy, C. Sharon Roji Priya, N. Krishnaraj, Vandna Dahiya |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Computational complexity theory
business.industry ved/biology Computer science media_common.quotation_subject ved/biology.organism_classification_rank.species Big data Data classification Particle swarm optimization Machine learning computer.software_genre Gray wolf Quality (business) Artificial intelligence business computer Biomedicine Selection (genetic algorithm) media_common |
| DOI: | 10.1016/b978-0-12-820203-6.00004-7 |
| Popis: | The classification of medical data is an important data mining issue that has been discussed for nearly a decade and has attracted numerous researchers around the world. Selection procedures provide the pathologist with valuable information for diagnosing and treating diseases. With the development of big data in the biomedicine and healthcare industry, carefully analyze the benefits of clinical data in early diagnosis, patient care and community service. However, the accuracy of the analysis decreases if the quality of the clinical data is incomplete. In addition, many regions have unique characteristics of some regional diseases that may weaken the outbreak forecast. In this study, we develop machine learning algorithms to effectively predict the outbreak of chronic disease in general communities. In this paper, the oppositional firefly (OFF) technique is proposed to select the most optimal properties in large data-based clinical datasets and oppositional Gray Wolf Optimization with Kernel Ridge Regression (OGWOKRR) compared to the OFF algorithm. The literature in this area shows that OFF performs better than particle swarm optimization (PSO), although its computational complexity is higher than PSO. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|