The Swarm Intelligence Algorithms for Optimization in Diagnosis the Diseases: A survey

Document Type : Original Article

Authors

1 Faculty of Computers and Information, Kafr El Sheikh university

2 Faculty of Computers and Artificial Intelligence, Helwan University

Abstract

There are many diseases that require early detection for rapid diagnosis, treatment, and recovery, and delays in diagnosis lead to other risks. Recently, researchers turned to use artificial intelligence to discover many diseases with high speed and accuracy, especially machine learning, CNN, and the use of optimization algorithms to choose the necessary features in order to make a simple training model for the classification stage. As most data sets consist of noisy and repetitive features in all application areas, this slows down the performance of the classifier and may even reduce the classification accuracy because the search space becomes huge and also affects the runtime of the classification. This review provided a comprehensive review of Particle Swarm Optimization (PSO), Artificial Bee Colony (ABC), and Grey Wolf Optimization (GWO), and their uses in diagnosing different diseases will be addressed such as skin cancer, adrenal gland tumors, diabetes, and coronary heart and others. Also, the different procedures that researchers have taken to improve the accuracy and speed of diagnosis, the changes they have made to these algorithms, hybrids to these algorithms, and proposed future trends in every search. The base of this study is to help new researchers get an overview of swarm intelligence algorithms and their role in diagnosing the diseases and brighten their horizons towards the future direction in this field.

Keywords

Full Text

 

 

Files

Share

How to cite

Statistics