An evolutionary framework based microarray gene selection and classification approach using binary shuffled frog leaping algorithm
| Autor: | Rasmita Rautray, Rajashree Dash, Rasmita Dash |
|---|---|
| Rok vydání: | 2022 |
| Předmět: |
General Computer Science
Computer science business.industry Binary number Particle swarm optimization 020206 networking & telecommunications 02 engineering and technology Machine learning computer.software_genre Support vector machine Set (abstract data type) ComputingMethodologies_PATTERNRECOGNITION Differential evolution Genetic algorithm 0202 electrical engineering electronic engineering information engineering Gene chip analysis 020201 artificial intelligence & image processing Artificial intelligence business Metaheuristic computer |
| Zdroj: | Journal of King Saud University - Computer and Information Sciences. 34:880-891 |
| ISSN: | 1319-1578 |
| DOI: | 10.1016/j.jksuci.2019.04.002 |
| Popis: | Since last few years, microarray technology has got tremendous application in many bio-medical researches. However, in order to efficiently recognize and apply this technology into the bio-medical areas is still very difficult and expensive. There are many metaheuristic approaches has been developed with different biological interpretation. Despite the existence of several approaches, there is always a requirement of development of more robust and efficient approach. In this work a new metaheuristic approach is proposed implementing binary shuffled frog leaping algorithm (BSFLA) for gene selection. To obtain an optimal gene subset, 20 different combination of gene subset is extracted from the original dataset. Out of which the optimal gene subset is identified implementing KNN classifier. Superiority of these gene set is shown using few other classifiers such as ANN and SVM. The model performance is also compared with few other metaheuristic approaches such as particle swarm optimization, differential evolution and genetic algorithm. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|