Table 3.

Summary of nature-inspired algorithms.

Nature-Inspired Algorithms	Application Domains
GA	Bandwidth utilization, computational resources and data dependencies [79]. GA algorithm was applied to decoupled data and computational services on the cloud.
Simulated Annealing (SA) and Whale Optimization Algorithm (WOA)	SA algorithm-based big data optimization technique, which uses WOA to design different feature selection [80]. SA algorithm helps to improve the classification accuracy and selects the most useful attributes for classification tasks.
PSO	Time series prediction, remote sensing image registration [81].
SA algorithm based on feature selection	SAFS technique for big data learning and computer vision. SAFS algorithm removes variables and tightens a sparse constraint, to reduce the problem size that makes it mainly fit for big data learning [82].
Artificial Bee Colony (ABC)	ABC algorithm-based clustering approach for big data, which identifies the best cluster and performs the optimization for different dataset sizes. ABC algorithm minimizes the execution time and improves the accuracy of clustering when implemented on a map/reduce-based Hadoop environment. ABC algorithm has been applied in training neural networks for pattern recognition [83].
Firefly Swarm Optimization (FSO)	FSO algorithm-based hybrid (FSOH) approach for big data optimization, which focused on six multi-objective problems to reduce the execution cost but it has high computational time complexity [84]. Heart disease prediction, image processing (segmentation of brain tissues, multilevel color image thresholding), clustering and classification (protein complex identification, hyper-spectral image classification [81].
Grey Wolf Optimization algorithm (GWO)	Feature selection, community detection, iris recognition [81].
Cat Swarm Optimization (CSO)	CSO algorithm-based approach for big data classification to select features in a text classification experiment for big data [85]. CSO algorithm uses the term frequency-inverse document frequency to improve the accuracy of feature selection.
Ant Colony Optimization (ACO)	For mobile big data to select optimal features to resolve decisions, which aids to manage big data of social networks (tweets and posts) effectively [86]. Predictive control for nonlinear processes, anomaly detection, treating missing values in big data sets, medical image de-noising, hyper-spectral image classification [81].
Improved ACO algorithm (IACO)	Big data analytical approach for management of medical data such as patient data, operation data, which helps doctors to retrieve the required data in little time [87].
Shuffled Frog Leaping (SFL)	Selection of the feature in high-dimensional biomedical data. SFL algorithm maximizes the predictive accuracy by exploring the space of possible subsets to obtain the set of features and reduces the irrelevant features [88].
Bacterial Foraging Optimization (BFO) algorithm	Classify the informative and affective content from the medical weblogs. The “MAYO” clinic data were used to evaluate the accuracy to retrieve the relevant information from the medical dataset [89].
Kestrel-based Search Algorithm (KSA)	KSA was applied as a parameter tuning algorithm to improve on the accuracy of feature selection in high-dimensional bioinformatics datasets [76].
Lion Optimization Algorithm (LOA) Lion cooperation characteristic	Data clustering, extracting liver from the abdominal CT images [81].
Whale Optimization Algorithm	Feature selection and currently proposed for diagnosing and predicting COVID-19 cases [16].
Flock by leader	For local proximity in an artificial virtual space [90], data clustering.