Empirical analyses of genetic algorithm and grey wolf optimiser to improve their efficiency with a new multi-objective weighted fitness function for feature selection in machine learning classification: the roadmap.
Azam DavahliMahboubeh ShamsiGolnoush AbaeiArash KhosraviPublished in: J. Exp. Theor. Artif. Intell. (2023)
Keyphrases
- fitness function
- genetic algorithm
- multi objective
- feature selection
- machine learning
- evolutionary algorithm
- particle swarm
- genetic algorithm ga
- genetic programming
- empirical analyses
- text classification
- evolutionary computation
- multi objective optimization
- classification accuracy
- support vector machine
- genetic operators
- optimization algorithm
- nsga ii
- feature subset
- multiple objectives
- crossover and mutation
- model selection
- particle swarm optimization
- machine learning algorithms
- crossover operator
- multi objective evolutionary algorithms
- feature space
- feature set
- decision trees
- feature extraction
- search space
- differential evolution
- evolutionary computing
- support vector
- initial population
- metaheuristic
- particle swarm optimisation
- mutation operator
- fitness evaluation
- penalty function
- feature selection algorithms
- binary particle swarm optimization
- neural network
- search capabilities
- multiobjective optimization
- objective function
- evolutionary process
- genetic search
- optimization problems
- simulated annealing
- test data generation
- mutation rate
- fuzzy logic
- knn
- premature convergence
- hybrid algorithm
- particle swarm optimization pso
- ant colony optimization
- evolutionary search
- artificial neural networks