QBSO-FS: A Reinforcement Learning Based Bee Swarm Optimization Metaheuristic for Feature Selection

International Work-Conference on Artificial Neural Networks 2019 Souhila SadegLeila HamdadAmine Riad RemacheMehdi Nedjmeddine KarechKarima BenatchbaZineb Habbas

Feature selection is often used before a data mining or a machine learning task in order to build more accurate models. It is considered as a hard optimization problem and metaheuristics give very satisfactory results for such problems... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK LEADERBOARD
Feature Selection Breastcancer Breastcancer Accuracy(10-fold) 96,29 # 1
Feature Selection Congress Congress Accuracy(10-fold) 97,95 # 1
Feature Selection Diabets Diabets Accuracy(10-fold) 70,65 # 1
Feature Selection German German Accuracy(10-fold) 74,2 # 1
Feature Selection Glass identification Glass Accuracy(10-fold) 75 # 1
Feature Selection Heart-C Heart-C Accuracy(10-fold) 58,71 # 1
Feature Selection Heart-StatLog Heart-StatLog Accuracy(10-fold) 82,59 # 1
Feature Selection Hepatitis Hepatitis Accuracy(10-fold) 72,67 # 1
Feature Selection Ionosphere_class b Ionosphere Accuracy(10-fold) 96,94 # 1
Average Accuracy 95,81 # 1
Feature Selection Iris Iris Accuracy(10-fold) 97,33 # 1
Feature Selection Lung-Cancer Lung-Cancer Average Accuracy 98,25 # 1
Feature Selection Lymphography Lymphography Accuracy(10-fold) 43,33 # 1
Feature Selection Movementlibras Movementlibras Average Accuracy 92,49 # 1
Feature Selection Sonar Sonar Average Accuracy 98,22 # 1
Feature Selection Spect Spect Accuracy(10-fold) 76,67 # 1
Feature Selection Vehicule Vehicule Accuracy(10-fold) 74,47 # 1
Feature Selection Vowel Vowel Accuracy(10-fold) 99,45 # 1
Feature Selection WDBC WDBC Accuracy(10-fold) 95,61 # 1
Feature Selection Wine Wine Accuracy(10-fold) 95,56 # 1
Feature Selection Zoo Zoo Accuracy(10-fold) 100 # 1