Cooperative co-evolution for feature selection in Big Data with random feature grouping

Journal of Big Data

Table 1 Taxonomy of FS approaches [5, 74, 75]

FS approaches	Evaluation methods	Examples of evaluator
Evaluation criteria	Filter [76]	Distributed FS using SC [77], information theory [78], T-test [79]
	Wrapper [80]	k-NN [81], SVM [82]
	Embedded [83]	LASSO [84], Gradient boosting [85]
Evolutionary computation	EA [86]	GA [87], GP [88], parallel GA [89]
	CEA [25]	CCEA [90]
	Swarm optimization [87]	PSO [87], ACO [91]
	Hybrid	mRMR-TLBOL [92], CMIM + BGA [93], TLBO + GSA [94]
	Others	ABC [95], MA [96], DE [95]
Number of objectives	Single-objective [97]	GA [87]
Number of objectives	Multi-objectives [98]	Nondominated sorting GA-II [99]

GP genetic programming, PSO particle swarm optimization, ACO ant colony optimization, TLBO teaching learning-based algorithm, GSA gravitational search algorithm, CMIM conditional mutual information maximization, BGA binary genetic algorithm, mRMR minimum redundancy maximum relevance, TLBOL TLBO with opposition-based learning, DE differential evolution, MA memetic algorithm, LCS learning classifier system, ES evolutionary strategy, ABC artificial bee colony