See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/344248191

Crow Search Algorithm: Theory, Recent advances, and Applications

Article  in  IEEE Access · September 2020

DOI: 10.1109/ACCESS.2020.3024108

CITATIONS READS

0 136

7 authors, including:

Abdelazim G. Hussien Mingjing Wang

Fayoum University Southeast University (China)
10 PUBLICATIONS   155 CITATIONS    38 PUBLICATIONS   504 CITATIONS   

SEE PROFILE SEE PROFILE

Guoxi Liang Ahmed Alsanad

Wenzhou Polytechnic, China, Wenzhou King Saud University
7 PUBLICATIONS   6 CITATIONS    24 PUBLICATIONS   92 CITATIONS   

SEE PROFILE SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Harris hawks optimization (HHO): Algorithm and applications View project

Machine learning for medical diagnosis View project

All content following this page was uploaded by Abdelazim G. Hussien on 15 September 2020.

The user has requested enhancement of the downloaded file.

 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3024108, IEEE Access

Date of publication xxxx 00, 0000, date of current version xxxx 00, 0000.
Digital Object Identifier

Crow Search Algorithm: Theory, Recent

Advances, and Applications
ABDELAZIM G. HUSSIEN1 , MOHAMED AMIN2 , MINGJING WANG3 , GUOXI LIANG4 , AHMED
ALSANAD5 , ABDU GUMAEI5 AND HUILING CHEN6
1
Faculty of Science, Fayoum University, Fayoum, Egypt
2
Faculty of Science, Menoufia University, Menoufia, Egypt
3
Institute of Research and Development, Duy Tan University, Da Nang 550000, Vietnam
4
Department of Information Technology, Wenzhou Polytechnic, Wenzhou 325035, China
5
STC’s Artificial Intelligence Chair, Department of Information Systems, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi
Arabia
6
College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou 325035, China
Corresponding author: Guoxi Liang (guoxiliang2017@gmail.com), Ahmed Alsanad (aasanad@ksu.edu.sa), and Huiling Chen
(chenhuiling.jlu@gmail.com)
The authors are grateful to the Deanship of Scientific Research, King Saud University for funding through Vice Deanship of Scientific
Research Chairs. Basic scientific research project of Wenzhou under grant No. G20190020, Key scientific research project of Wenzhou
Polytechnic under grant No. WZY2019004, Service technology innovation project of Wenzhou science and technology association under
grant No.2019KXCX-RH07.
We also acknowledge the efforts of Ali Asghar Heidari (http://aliasgharheidari.com) during preparation and revision of this research

ABSTRACT In this paper, a comprehensive overview of the Crow Search Algorithm (CSA) is introduced
with detailed discussions, which is intended to keep researchers interested in swarm intelligence algorithms
and optimization problems. CSA is a new swarm intelligence algorithm recently developed, which simulates
crow behavior in storing excess food and retrieving it when needed. In the optimization theory, the crow is
the searcher, the surrounding environment is the search space, and randomly storing the location of food
is a feasible solution. Among all food locations, the location where the most food is stored is considered
to be the global optimal solution, and the objective function is the amount of food. By simulating the
intelligent behavior of crows, CSA tries to find optimal solutions to various optimization problems. It has
gained a considerable interest worldwide since its advantages like simple implementation, a few numbers
of parameters, flexibility, etc. This survey introduces a comprehensive variant of CSA, including hybrid,
modified, and multi-objective versions. Furthermore, based on the analyzed papers published in the literature
by some publishers such as IEEE, Elsevier, and Springer, the comprehensive application scenarios of CSA
such as power, computer science, machine learning, civil engineering have also been reviewed. Finally, the
advantages and disadvantages of CSA have been discussed by conducting some comparative experiments
with other similar published peers.

INDEX TERMS Crow Search Algorithm; CSA; Swarm Intelligence; Meta-heuristics; Optimization;
Nature-inspired algorithms

I. INTRODUCTION NP problems and finding the optimal/near-optimal solution

in real-time [188]. These algorithms become very popular
Nowadays, optimization can be considered as one of the most
since their advantages like easy in implementation, avoiding
important and hottest research topics [1]–[9]. It is inside the
local optima, and flexible and versatile [191]. They can be
core processes of every aspect and can be found in almost
considered as a black box, and can solve different problem
all fields such as engineering, science, energy, computer, etc.
types: single/multi-objective, constrained or unconstrained,
[10]–[19]. Since the complexity increasing of the real-world
and continuous/discrete.
scientific and engineering problem, optimization becomes a
Generally speaking, MA can be categorized into two ma-
big challenge in soft computing. Traditional methods of math-
jor classes: single-based / individual-based algorithms and
ematics sometimes fail to solve and address them [183], [187].
population-based. Examples of single-based algorithms are
Metaheuristics Algorithm (MA) is very good at solving these

VOLUME 4, 2016 1

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3024108, IEEE Access

Author et al.: Preparation of Papers for IEEE TRANSACTIONS and JOURNALS

Tabu Search (TS) [22], Guided Local Search (GLS), and Pat- [34], Chicken Swarm Optimization (CSO) [35], Grey Wolf
tern Search (PS) whereas Particle Swarm Optimization (PSO) Optimizer (GWO) [36], Social Spider Algorithm (SSA) [37],
[23], Differential Search Algorithm (DSA) [24] and Grey Ant Lion Optimizer (ALO) [38], Moth-Flame Optimization
Wolf Optimizer (GWO) [36] are examples of population-based (MFO) [39], Elephant Herding (EH) Optimization [40], Multi-
algorithms. Verse Optimizer (MVO) [41], Whale Optimization Algorithm
Crow Search Algorithm (CSA) is a recent algorithm devel- (WOA) [42], Dragonfly Algorithm (DA) [43], Sine Cosine
oped by Alireza Askarzadeh in 2016, which simulates the Algorithm (SCA) [44], Kidney-Inspired Algorithm [45], Spot-
crow behavior in storing their food and retrieving it when ted Hyena Optimizer (SHO) [46], Grasshopper Optimization
they need it. Since its appearance, CSA has been widely used Algorithm (GOA) [47], Salp Swarm Algorithm (SSA) [48],
and applied to different optimization problem such as chem- Thermal Exchange Optimization [56], Squirrel Search Algo-
ical engineering [86], medical [87], power energy [88], fea- rithm [58], Henry Gas Solubility Optimization (HGSO) [59],
ture selection [89], and image processing [90]. Harris Hawks Optimization (HHO) [60], Nuclear Reaction
Reviews/survey papers are critical as they present and discuss Optimization (NRO) [61].
recent and up-to-date works. In literature, there are enormous In literature, there are many metaheuristics algorithms clas-
reviews that concern with MA such as Grey Wolf Optimizer sification. For example, authors in [62] have divided MAs to
[91], Firefly Algorithm [92], Gravitational Search Algorithm two categories (evolutionary & Swarm Intelligence) where
[93], Krill Herd Algorithm [93]. in [63] authors have divided them to three different classes
To the best of our knowledge, there is no study in litera- (Swarm Intelligence, Evolutionary Intelligence, and Physical
ture covers or lists all CSA aspects, variants, and applica- & Chemical algorithm). In [59], Hashim et al. classified them
tions. This review article aims to carry a comprehensive study in to four groups (Swarm Intelligence (SI), Bio-Inspired Al-
for all CSA aspects, how scientists/researchers are motivated gorithms (BIAs), Natural Science-based Algorithms (NSAs),
to use this algorithm to solve different real-world optimiza- and Natural Phenomena-based Algorithm (NPAs)). No unique
tion problems. Also, This review collects and summarizes standard criterion is existed to classify MA. Here, we classify
all modifications and variants of CSA to overcome its draw- them into the following four categories:
backs. • Evolutionary Algorithms: in this category, algorithms
are inspired by natural evolution; examples of this cate-
The main contributions of this paper can be listed below: gory are shown in Table 1.
• A comprehensive review to CSA has been done. • Swarm Intelligence (SIs): these algorithms are inspired
• All modifications to the original CSA has been high- by the behavior of insects, birds, animals, bacteria, and
lighted. fish as algorithms in Table 2.
• All applications and fields that employed CSA have been • Physics-based algorithm: in this category, algorithms in-
summarized and presented. spired by physical laws or chemical phenomena. Exam-
• Advantages and disadvantages of CSA have been dis- ples of these are given in Table 3.
cussed. • Human-Inspired algorithm: the last category contains
• Number of challenges/ideas as a future work have been algorithms inspired by human being behavior as in Table
suggested. 4.
This paper is organized as follows: Section 2 presents a liter-
ature review to MA whereas Section 3 disuses inspiration & III. CROW SEARCH ALGORITHM
mathematical model of CSA. Section 4 presents all variants In this section, we discuss the mathematical model of CSA
and modifications of CSA and Section 5 summarizes and and its research status/trend
highlights all applications that use CSA. An assessment and
evaluation to CSA is presented in section 6 whereas Section A. STANDARD CROW SEARCH ALGORITHM
7 concludes the paper and adds some suggestions that can be A new population-based algorithm called Crow Search Al-
handled in future work. gorithm (CSA) was proposed by Askarzadeh, which simu-
lates the hiding of food behavior of crow [95]. Crow is an
II. METAHEURISTICS intelligent bird that can remember faces and warn its species
In literature, enormous types of optimization algorithms has in danger. One of the most evidence of their cleverness is
been proposed in the last decades such as Genetic Algorithm hiding food and remember its location. Moreover, the explo-
(GA) [20], Simulated Annealing (SA) [21], Tabu Search (TS) ration and exploitation of CSA can be learned from Figure 1.
[22], Particle Swarm Optimization [23], Differential Search Overall, the pseudocode of CSA can be modeled as shown in
Algorithm (DSA) [24], Harmony Search (HS) [25], Cat Swarm Algorithm 1, Figure 2 is the flowchart of CSA, and its main
Optimization (CSO) [26], Firefly Algorithm (FA) [27], Cuckoo phases can be shown as follows:
Search (CS) [28], Gravitational Search Algorithm (GSA) [29], 1) Initializing crows swarm in d-dimensional randomly.
Virus Optimization Algorithm (VOA) [30], Bat Algorithm 2) A fitness function is used to evaluate each crow, and
(BA) [31], Ant Colony Optimization (ACO) [32], Flower Pol- its value is put as an initial memory value. Each crow
lination Algorithm (FPA) [33], Krill Herd (KH) Algorithm stores its hiding place in its memory variable mi .
2 VOLUME 4, 2016

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3024108, IEEE Access

Author et al.: Preparation of Papers for IEEE TRANSACTIONS and JOURNALS

x(i,iter ) Crow i

New position of
crow i

Crow j
Origin (a) f1<1 m(i,iter )

x(i,iter ) Crow i

Crow j
m(i,iter )

New position of
Origin
crow i
(b) f1>1
FIGURE 1: Exploration and exploitation of CSA

Start Update positions using Eq. (1)

Initialize pop-size, termination

Check solution boundaries
condition, and CSA Parameters: Fl, Ap

Randomly generate crows position Evaluate fitness No

Initialize crows memory Initialize crows memory

Evaluate fitness Terminate condition

Yes

Return best position

End

FIGURE 2: Flowchart of CSA

VOLUME 4, 2016 3

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3024108, IEEE Access

Author et al.: Preparation of Papers for IEEE TRANSACTIONS and JOURNALS

TABLE 1: Examples of evolutionary algorithms.

No. Algorithm Abb. Authors Year
1 Genetic algorithms [20] GA Holland 1975
2 Evolutionary programming [64] EP Fogel et al. 1966
3 Evolution strategy [65] ES Rechenberg 1973
4 Tabu search [22] TS Glover 1986
6 Differential evolution [66] DE Storn and Price 1997
7 Differential search algorithm [24] DS Civicioglu 2011
8 Synergistic fibroblast optimization [73] SFO Dhivyaprabha et al. 2019
9 Physarum-inspired computational PCM Chen et al. 2020
model [74]

TABLE 2: Examples of sawarm intelligence algorithms.

No. Algorithm Abb. Authors Year
1 Ant colony optimization [32] ACO Dorigo 1992
2 Particle swarm algorithm [23] PSO Kennedy and Eberhart 1995
3 Artificial fish swarm algorithm [67] AFSA Li et al. 2002
4 Bacterial foraging optimization algorithm [68] BFOA Passino 2002
5 Glowworm swarm optimization [69] Krishnanand and Ghose 2005
6 Cat swarm optimization [26] CSA Chu et al. 2006
7 Artificial bee colony [70], [71] ABC Karaboga and Basturk 2007
8 Cuckoo search [28] CS Yang and Deb 2009
9 Bat algorithm [31] BA Yang 2010
10 Firefly algorithm [27] FA Yang 2010
11 Krill herd algorithm [34] KH Gandomi and Alavi 2012
12 Dolphin echolocation [72] Kaveh and Farhoudi 2013
13 Chicken swarm optimization [35] CSO Meng et al. 2014
14 Grey wolf optimizer [36] GWO Mirjalili et al. 2014
15 Ant lion optimizer [38] ALO Mirjalili 2015
16 Dragonfly algorithm [43] DA Mirjalili 2015
17 Whale optimization algorithm [42] WOA Mirjalili and Lewis 2016
18 Grasshopper optimization algorithm [47] GOA Saremi et al. 2017
19 Butterfly-inspired algorithm [75] BOA Qi et al. 2017
20 Salp swarm algorithm [48] SSA Mirjalili et al. 2017
21 Equilibrium optimizer [49] EO Faramarzi et al. 2019
22 Bald eagle search [50] BES Alsattar et al. 2019
23 Harris hawks optimization [51] HHO Heidari et al. 2019
24 Nuclear reaction optimization [52] NRO Wei et al. 2019
25 Slime mould algorithm [53] SMA Li et al. 2020
26 Border collie optimization [54] BCO Dutta et al. 2020

TABLE 3: Examples of physics-based algorithms.

No. Algorithm Abb. Authors Year
1 Simulated annealing [21] SA Kirkpatrick et al. 1983
2 Harmony search [25] HS Geem et al. 2001
3 Gravitational search algorithm [29] GSA Rashedi et al. 2009
4 Big bang–big crunch optimization [76] BBCB Erol and Eksin 2005
5 River formation dynamics [77] RFD Rabanal et al. 2007
6 Ray optimization [78] RO Kaveh and Khayatazad 2012
7 Mine blast algorithm [79] MBA Sadollaha et al. 2013
8 Lightning search algorithm [80] LSA Shareef et al. 2015
9 Sine cosine algorithm [44] SCA Mirjalilia 2016
10 Multi-verse optimizer [41] MVO Mirjalili et al. 2016
11 Thermal exchange optimization [56] TEO Kaveh and Dadras 2017
12 Henry gas solubility optimization [57] HGSO Hashim et al. 2019

TABLE 4: Examples of human related algorithms.

No. Algorithm Abb. Authors Year
1 Human-inspired algorithm [81] HIA Zhang et al. 2009
2 Social emotional optimization [82] SEOA Xu et al. 2010
3 Brain storm optimization [83] BSO Shi 2011
4 Teaching–learning-based optimization [84] TLBO Rao et al. 2011
5 Volleyball premier league algorithm [85] VPL Moghdani and Salimifard 2018
6 Gaining-sharing knowledge [55] GSKMohammed
2019
et al.

4 VOLUME 4, 2016

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3024108, IEEE Access

Author et al.: Preparation of Papers for IEEE TRANSACTIONS and JOURNALS

TABLE 5: The top 10 journals with the largest number of the papers on CSA.
Rank Journals Number of papers
1 Applied Soft Computing Journal 24
2 Neural Computing And Applications 15
3 IEEE Access 14
4 Advances In Intelligent Systems And Computing 13
5 Expert Systems With Applications 12
6 Soft Computing 11
6 Studies In Computational Intelligence 11
8 Applied Intelligence 7
8 Swarm And Evolutionary Computation 7
9 Applied Mathematical Modelling 6
9 Engineering Applications Of Artificial Intelligence 6

3) Crow updates its position by selecting a random an- B. CROW SEARCH ALGORITHM RESEARCH TRENDS
other crow, i.e xj and generating a random value. if CSA has gained huge attention from all researchers and sci-
this value is greater than Awareness Probability ‘AP’, entists all over the world. According to Google Scholar 1 558
then crow xi will follow xj to know mj times (accessed in 23rd May 2020): 375 in journals, 138 in
4) Crow updates its position by selecting a random other conferences, 38 in book chapters, and 4 in review papers.Table
crow i.e xj and following it to know mj . Then new xj 5 shows the top 10 journals with the highest paper numbers
is calculated as follows: dealing with CSA. Also, Figure 3 shows the number of pub-
 lications per different publisher such as Elsevier, Springer,

 xi,iter + ri × IEEE, and others, whereas Figure 4 shows the number of
 f li,iter ×


publications per year.
xi,iter+1 = (mj,iter − xi,iter ) rj ≥ APj,iter




a random position otherwise

IV. DIFFERENT METHODS OF CROW SEARCH
(1)
ALGORITHM
where APj,iter refers to crow j awareness probability,
In the section, CSA variants have been divided to 3 classes:
iter refers to iteration number, ri , rj refers to random
modified CSA, hybrid CSA, and multi-objective CSA.
numbers, f li,iter is the crow i flight length to denote
crow j memory.
A. MODIFIED CSA
5) Updating memory
I this section, we discuss all modified versions of CSA such

 xi,iter+1 f (xi,iter+1 ) ≤ f (mi,iter ) as binary version, Opposition-based learning-based, Levy flight-
mi,iter+1 = based, etc.
mi,iter otherwise

(2) 1) Binary CSA
Souza et al. [96] proposed a binary version of CSA called
BCSA in which a V-shape transfer function was used to con-
Algorithm 1 CSA: Crow Search Algorithm.
vert the continuous values to discrete ones. Laabadi et al.
Input: n Number of crows in the population. [164] did another work. They developed a binary version of
itermax Maximum number of iteration. CSA to solve the 2D bin packing problem.
Output: Optimal crow position
Initialize position of crows. 2) Modified CSA
Initialize crows’ memory In [97], Coelho et al. [98] tried to propose a modified CSA by
while iter < itermax do using Gaussian distribution and diversity information of the
for crowi belong to crows do population. Also, Gupta et al. tried to extract usability fea-
choose a random crow. tures by proposing a novel approach of CSA called modified
determine a value of awareness probability AP CSA (MCSA) in which a particular selected feature number
Update xi,iter+1 using Eq.(1) is generated and applied to the life cycle of software develop-
end for ment by using usability factors hierarchical model. Moham-
Check solution boundaries. madi and Abdi in [99] enhanced the classical version of CSA
Calculate the fitness of each crow by performing two modifications 1) Introducing a priority-
Update crows’ memory using Eq.(2) based technique which shows how each crow will choose
end while
1 (https://scholar.google.co.uk/scholar?hl=en&as_sdt=0%2C5&q=A+
novel+metaheuristic+method+for+solving+constrained+engineering+
optimization+problems%3A+Crow+search+algorithm&btnG=)

VOLUME 4, 2016 5

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3024108, IEEE Access

Author et al.: Preparation of Papers for IEEE TRANSACTIONS and JOURNALS

FIGURE 3: Number of publications of CSA per publisher

Number of publications per year

NUMBER OF WOTKS

300
200 208
4 134
100 66
74
0
2016
2017
2018
2019
2020
YEAR

FIGURE 4: Number of publications of CSA per Year

another crow to move towards its position. 2) Introducing rithm was tested on two different models: a simple structure
a method to determine the sufficient flight length amount. (beam) and a complex structure. In [103], Majhi et al. tried
The authors applied it to economic load dispatch. Likewise, to prevent SCA from getting trapped into local optima by
another enhancement to CSA has done by Cuevas et al. [100] developing another enhanced version of CSA with the use
by modifying two CSA parameters, namely: awareness prob- of opposition learning strategy and mutation operator. They
ability and random perturbation. They argued that these mod- tested their algorithm which named OBL-SCA-MO by using
ifications would affect the diversity of the population and CEC2017 and used it to design fractional order PID (FOPID).
also improve the convergence speed. In [101], authors added Another enhancement called CCSA was proposed in [104] by
local search and niching methods to enhance the searching Zamani et al. by using three strategies, namely:neighborhood-
capabilities of CSA. based local search, non-neighborhood based search, and wan-
dering around search.
3) Lévy flight & Opposition-based CSA
Wu et al. [102] introduced a novel approach of CSA named
CCSA, in which an Lévy flight was used. The novel algo-
6 VOLUME 4, 2016

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3024108, IEEE Access

Author et al.: Preparation of Papers for IEEE TRANSACTIONS and JOURNALS

4) Enhanced CSA B. HYBRID CSA

A new version called ECSA was developed by Javidi et al.
In literature, CSA has been hybridized with many other MA
[105]. In this version, the authors tried to improve the per-
and machine learning to combine and benefit from the strength
formance of the original CSA in handling problems of struc-
of both. In [115], a novel hybrid algorithm called GWOCSA,
tural optimization by adding three enhancements: 1) replac-
which combined GWO with CSA. To test the hybrid algo-
ing each variable of violated decision with its corresponding
rithm, the authors used 23 benchmark functions, and the re-
variable. 2) suggesting a free-fly mechanism. 3) introduc-
sults were compared with GWO, augmented GWO (AGWO),
ing the upper bound strategy. Likewise, Bhullar et al. [106]
and Enhanced GWO (EGWO). GWOCSA was also applied
proposed another version of CSA by 1) adding an archive
to solve the feature selection problem. Davoodkhani et al.
component to use crow experience. 2) formulating a non-
also hybridized GWO and CSA [116] in which the hybrid
hideout position. 3) exploiting the 1/5th of exploitation by
algorithm (hGWO-CSA) was used to maximize photovoltaic
using awareness probability. In [107], the authors proposed a
power point tracking. Another hybrid algorithm was proposed
version called ICSA by restructuring two properties of CSA:
by Pratiwi [117], which combined cat swarm optimization
awareness probability and a random perturbation and adding
with CSA. The novel algorithm was applied to the vehicle
a dynamic probability.
routing problem. The same hybrid algorithm was done by
Kumar [118] and was applied to the economic emission dis-
5) Improved CSA patch problem. Pamir et al. [119]. has combined the BA and
CSA. The proposed algorithm, which is called BCSA, was
Another effort to enhance the original CSA to be able to employed in smart grid applications. Likewise, Xue et al.
solve high dimensional optimization tasks is shown in [108] [120] tried to solve the flow shop scheduling problem us-
where three operators have been added to a balance between ing a novel algorithm named CPO, which is a hybridiza-
exploration and exploitation. These factors are Lévy flight, tion between CSA and PSO. Another CSA version was em-
experience factor, and adaptive adjustment factor. In [109], ployed in the vehicle routing problem in which CSA has been
Zhang and Huang added an inertia weight factor and used hybridized with ACO [121]. Also, Mahesh and Vijayachitra
the Roulette wheel as a selection scheme. Likewise, Díaz et in [122] proposed a new version of CSA called DECSA in
al. [110] developed another improvement to CSA and applied which dolphin echolocation and CSA were hybridized to-
the new version to solve energy optimization problems. Also, gether to classify energy-aware routing. Pasandideh and Khalilpourazar
in [111], Gupta et al. introduced an improved CSA version in [123], [124] developed a hybrid algorithm SCCSA in which
called optimized CSA (OCSA). They tested their novel algo- SCA was combined with CSA. Their novel algorithm was
rithm using 20 datasets and compared OCSA with the orig- compared with original SCA, DA, GSA, CS, and PSOGSO.
inal CSA and chaotic CSA. Moghaddam et al. [112] used Allaoui et al. [125], combined CSA with a local search method
GA operators: crossover and mutation and employed it in to accelerate the searching process to solve the fragment as-
CSA to increase its performance and prevent it from getting sembly of DNA problems that follow the OLC model. Like-
stuck into sub-optimal regions. Fallah et al. [113] introduced wise, Anter and Ali integrated the CSA with the Fuzzy C-
an improved CSA (ICSA) in which each crow must choose means algorithm and chaos theory and applied it to medical
a random crow as a leader. In [114], Sahoo and Padhy re- problems [126]. Also, Nawaz–Enscore–Ham (NEH) strategy
placed random movement and ‘AP’ with Lévy flight and Dy- was used to generate CSA population [127]. Also, in [172]
namic AP (DAP). Likewise, Anter et al. [89] used CSA with the authors developed a hybrid algorithm that combined WOA
a fast fuzzy c-mean to identify crops. CSA also has been with CSA called CrowWhale to solve energy trust routing
improved by Han et al. [163] by using a spiral search mecha- (ETR). In [173], Farh et al. introduced (CSA-PSO), which
nism. Their new algorithm, which called ISCSA, is enhanced hybridized CSA with PSO. The authors tried to find the op-
using weight coefficient, optimal guidance position, spiral timal size and allocation of distributed generation. Another
search, Gaussian variation, and random perturbation. They version called Crow Search Mating - based Lion Algorithm
tested their algorithm using 23 benchmark functions and four (CSM-LA) was developed by Gaddala and Raju [174] to solve
different engineering problems. Rizk-Allah et al. [176] has unified power quality conditions (UPQC). Another hybrid
designed another chaotic CSA for the fractional optimiza- version between the CSA, lion algorithm, and AFL called
tion problem. Likewise, the Space Transform Search (STS) crow-FAL was developed by Rodrigues [175] and was ap-
method has been combined with CSA to improve the per- plied to intrusion detection. In [179], Huang et al. developed
formance of the original algorithm [177]. The authors used a hybrid version of CSA called HCSA in which CSA was
the CEC 2017 benchmark to test their method. To solve truss integrated with Nawaz-Enscore-Ham (NEH). The novel algo-
sizing optimization, Ozbasaran and Yildirim developed mod- rithm has been applied to the flow shop scheduling problem.
ified CSA called CSAM [178]. Overall, literature reviews on And, literature reviews on hybrid CSA algorithms can be
variants and modified CSA algorithms can be summarized in shown in Table 7.
Table 6.

VOLUME 4, 2016 7

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3024108, IEEE Access

Author et al.: Preparation of Papers for IEEE TRANSACTIONS and JOURNALS

C. MULTI-OBJECTIVE CSA
In many areas, the process starts with the modeling and de-
sign of objective functions for searching for feasible solu-
tions, which cannot necessarily be an optimal value [182],
[184]–[186]. One of the most challenging characteristics in
solving the real-world problem is the multi-objective fitness
function. Many variants of multi-objective CSA have been
developed in the literature. Nobahari and Bighashdel in [129]
developed a multi-objective version called MOCSA. They
also added a chasing operator to improve the convergence
speed. They compared their results with ten multi-objective
algorithms using 13 unconstrained functions. Also, in [130],
Hinojosa et al. proposed another multi-objective CSA version
hybridized with chaos theory. The authors tested MOCCSA
using different datasets, and they argued that the proposed
algorithm achieved better results than the Multi-Objective
Dragonfly Algorithm (MODA) and Multi-Objective Particle
Swarm Optimization (MOPSO). Likewise, a multi-objective
crow and fruit fly optimization algorithm has been developed
by Ramgouda and Chandraprakash [131]. Rizk-Allah et al.
[132] developed an orthogonal opposition-based version of
CSA known as M2O-CSA. In their algorithm, two crows se-
lected randomly to undergo crossover. Then, the orthogonal
array was founded to have nine solutions (individuals). John
and Rodrigues [133] developed a version called MOTCO,
which refers to the Multi-objective Taylor Crow Optimiza-
tion algorithm. They used it in clustering aware wireless sen-
sor network. Totally, some summary of literature review on
variants and modified Multi-objective CSA algorithms are
displayed in Table 8.

8 VOLUME 4, 2016

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
 VOLUME 4, 2016
TABLE 6: Summary of literature review on variants and modified CSA algorithms.
No. Modification Ref. Parameters. Test Benchmark fun. Authors Journal Remarks
Name /Conf.
1 Standard N =50, itermax = 13 unconstrained Alireza Computers This algorithm has designed to
Crow search [95] 500 , f l=2, AP =0.1 benchmark function Askarzadeh and solve unconstrained problems such
algorithm & 6 constrained Structures as Three-bar truss, Pressure vessel,
engineering design etc
problems
2 modified N =23, itermax = A private dataset 2 Gupta et al. Neural Authors proved that MCSA algo-
CSA [98] 10 , f l=2, AP =0.1 Computing rithm can find the most important
and feature that can be obtained using
Applications various models.
3 Oppositional N =30, IEE CEC 2017 Majhi et al. Evolving 2 operators are added to improve
CSA with [103] itermax =1000, Systems CSA performance of: oppositional
mutation AP = 0.1, and f l = 2 learning & mutation operator.
operator
4 modified N =100, 4 unconstrained func. Mohammadi Applied Soft improves CSA by using an inno-
Author et al.: Preparation of Papers for IEEE TRANSACTIONS and JOURNALS

crow search [99] itermax =100, AP = & five different well- and Abdi Computing vative crows selection & adaptive
algorithm 0.1, and f l = 2, 1.9 known ELD flight length adjustment
(MCSA)
5 Conscious N =200, CEC 2017 & 4 engi- Zamani et al. Applied Soft CCSA uses 3 strategies NLS, NGS,
neighborhood- [104] itermax =1500 neering design prob- Computing and WAS
based CSA lems
6 Enhanced N = 70, f l = 3 and 4 popular benchmark Javidi et al. Applied Soft Three modifications were made 1)
10.1109/ACCESS.2020.3024108, IEEE Access

crow search [105] AP =0.1 structures Computing each decision variable was replaced
algorithm by corresponding one. 2) a free-fly
mechanism 3) the personal upper
bound strategy.
7 Improved 15 unconstrained f l = 2, AP =0.1, Jain et al. Journal of CSA is improved by adding expe-
crow search [108] function itermax =40000 Intelligent rience factor, adaptive adjustment
algorithm & Fuzzy operator and Lévy flight
Systems
8 Enhanced N =10,AP = [0.05, 2], 23 unconstrained Bhullar et al. Soft (1) archive component addition
crow search [106] f l= [0.5, 2.5] functions Computing (2) of non-hideout formulation (3)
algorithm Rechenberg’s 1/5th rule is exploited
(4) awareness probability is regu-
lated.

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI

9
 10
TABLE 7: Summary of literature review on hybrid CSA algorithms.
No. Modification Ref. Parameters. Test Benchmark fun. Authors Journal Remarks
Name /Conf.
1 Hybrid N =50, itermax =300 23 unconstrained ARORA et IEEE Access hybrid GWO with CSA called
algorithm [115] , f l=2, AP =0.1 benchmark function al. GWOCSA is introduced to find
based on & 21 datasets global optima efficiently.
grey wolf
optimization
and crow
search
algorithm
2 Hybrid crow N =20, f l=2, 12 dataset PFSP Wu et al. ICESS2018 CPO combines CSA and PSO
particle opti- [120] AP =0.05 to solve permutation flow shop
mization scheduling problems
3 DECSA f l=2, AP =0.1 Mahesh et al. Neural a hybrid dolphin echolocation and
[122] Computing crow search optimization
and
Applications
4 Sine–cosine itermax =1000 , 28 unconstrained Khalilpourazari Neural SCCSA is hybrid algorithm com-
crow search [124] f l=2, AP =0.1 benchmark function Computing bines CSA and SCA.
algorithm and
10.1109/ACCESS.2020.3024108, IEEE Access

Applications
5 hybrid rough N =50, itermax =500 IEEE CEC 2005, Aboul Ella Journal of RCSA combines CSA with rough
crow search [128] , f l changes dynami- IEEE CEC 2010 and Hassanien et Ambient searching scheme (RSS) in solving
algorithm cally, AP =0.1 4 engineering design al. Intelligence engineering optimization problems
problems and
Humanized
Computing
6 CFCSA N =10, itermax =10 , 10 dataset Anter and Soft hybrid crow search optimization al-
[126] f l=2, AP =0.1 Ali Computing gorithm integrated with chaos the-
ory and fuzzy c-means

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI

VOLUME 4, 2016
Author et al.: Preparation of Papers for IEEE TRANSACTIONS and JOURNALS
 VOLUME 4, 2016
TABLE 8: Summary of literature review on variants and modified Multi-Objective CSA algorithms.
No. Modification Ref. Parameters. Test Benchmark fun. Authors Journal Remarks
Name /Conf.
1 Multi- N =600 900 4290, 13 multi-objective Nobahari & CSIEC2017 Multi-Objective CSA (MOCSA).
objective [129] f l=2, AP =0.3, 0.22, functions Bighashdel
CSA 0.2
2 Multi- N =100, f l=2, CEC 2009 Hinojosa et Neural 2 versions Multi-Objective Crow
objective [130] AP =0.1 al. Computing Search Algorithm (MOCSA) &
Author et al.: Preparation of Papers for IEEE TRANSACTIONS and JOURNALS

chaotic and Multi-Objective Chaotic Crow

crow search Applications Search Algorithm (MOCCSA)
algorithm have been proposed.
3 Multi- N =100, ZDT test suits Rizk-Allah Neural multi-objective orthogonal
objective [132] maxiter =200, et al. Computing opposition-based crow search
orthogonal f l=2, AP =0.1 and algorithm (M2O-CSA) is proposed
opposition- Applications for solving large-scale multi-
10.1109/ACCESS.2020.3024108, IEEE Access

based CSA objective optimization problems.

4 Multi- f l=2, AP =0.1 The simulation is car- John & Ro- Mobile Multi-Objective Taylor Crow Op-
objective [133] ried out by consider- drigues Networks timization (MOTCO) algorithm is
taylor crow ing 50 nodes and 100 and proposed which is a combination of
optimization nodes Applications the Taylor series and the CSA

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI

11
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3024108, IEEE Access

Author et al.: Preparation of Papers for IEEE TRANSACTIONS and JOURNALS

V. APPLICATION(OPTIMIZATION & ENGINEERING) 8, 16, and 32). They argued that CSA achieved better re-
CSA has been successfully applied to different application sults than PSO, DE, GWO, MFO, and CS in terms of PSNR,
domains, as shown in Figure 5. SSIM, and FSIM metrics. Oliva et al. [147] used CSA to
find the optimal cost of cross-entropy in image segmenta-
A. POWER ENGINEERING tion. They tested their model in multi-dimensional spaces.
In this subsection, all CSA applications related to power en- Thomas and Rangachar [148] used CSA to recognize faces in
gineering have been discussed. low-resolution images by combining Gabor filter + wavelet +
texture (GWTM). Fred et al. [87] proposed the fuzzy-CSA
1) Optimal power flow algorithm and applied it to the segmentation of medical im-
In [88], Saha et al. used CSA to solve the optimal power ages. They compared it with ABC, FA, and SA.
flow problem. Authors used IEEE 30 bus to validate the ef-
3) Neural network & Support vector machine
fectiveness of CSA and compared it with DSA [134],MOHS
[135], TLBO [136], QoTLBO [136]. Also, Fathy and Ab- Chithra and Jagatheeswari [149] Combined CSA with Sup-
delaziz [137] tried to solve single-objective OPF for electric port Vector Machine (SVM), neural network, and fraction
power. They argued that the results obtained from CSA are theory to classify tuberculosis patients. They mentioned that
significant when applied to the IEEE 30-bus system and IEEE their combination increased the speed of computation and
118 bus system. Similar work was done in [138] by Naresh, decreased time and cost spent on test samples. Also, in [150],
Reddy, and Reddy. Chakravarthy and Rajaguru integrated their modified version
of CSA with a neural network to detect lung cancer. Like-
2) Load dispatch & Unit commitment
wise, More and Ingle [151] introduced a dragonfly-crow al-
gorithm called D-Crow hybridized with Support Vector Re-
Economic Load Dispatch Problem (ELDP) is the problem of
gression (SVR). They applied it to Virtual Machine Migra-
finding the minimum scheduling outputs of the generating
tion (VMM).
units’ outputs. In [99], Mohammadi and Abdi used a modi-
fied version of CSA to solve ELDP. To proof the applicability
4) Cloud
of their novel algorithm, they used five different test sys-
Satpathy et al. [152] used CSA in order to propose a resource-
tems. Also, Kumar et al. [139] used CSA to solve constrained
aware to consolidate a substantial Virtual Machine (VM) num-
nonconvex ELDP with prohibited operation zones. Sheta has
bers on minimal in the cloud data center. They proposed two
done similar works in [140] and Spea in [141]. In [142],
different technique CSA-based travel salesman problem (TSPCS)
Habachi et al. tried to solve unit commitment problems and
and Greedy Crow Search (GCS). The same problem has been
economic dispatch using CSA based on the eagle strategy.
handled by Satpathy et al. [153] where a 2-tier VM placement
algorithm has been proposed. First, a queuing structure to
B. COMPUTER SCIENCE
schedule VMs, whereas the second (CSAVMP) CSA-based
In this subsection, all CSA applications related to computer VM problem was developed to reduce the consumption of
science have been discussed. power at data centers. Likewise, In [154], authors enhanced
cloud task scheduling by using CSA. They proved that the
1) Feature selection CSA-based system has better results than Min-Min and an
Feature selection (FS) can be defined as the process of se- ant algorithm. In [155], George and Sumathi proposed the
lecting the most critical dataset and removing irrelevant ones Crow Lion Algorithm (C-lion) and applied it in privacy pro-
[143], [144]. If it is a wrapper method, it is often related tection on the cloud using the dyadic product. Also, Firefly
to the neural networks in its application part [189], [190]. Crow Search Algorithm (FF-CSA) is developed in [156] by
In [96], Souza et al. used a binary version of CSA called Malleswaran and Kasireddi to produce efficient task schedul-
BCSA, which has the V-shape to solve the FS problem. The ing in the cloud environment. Another attempt has been made
authors used six different datasets and compared their re- by Kumar and Vimala [157], which combined an integrated
sults with BBA, BPSO, SFS, and SBS. Also, Allahverdipoor Fractional Dragonfly Algorithm (C-FDLA) to achieve load
and Gharehchopogh in [145] combined K-nearest neighbor balance in cloud environments. The latter approach was per-
with CSA to solve the FS problem in classifying text docu- formed by Makhdoom and Askarzadeh [158], which tried to
ments. Likewise, Anter and Ali [126] hybridized CSA with optimize the photovoltaic / diesel generator operation with
chaos theory and c-means to solve medical diagnosis prob- pumped hydro storage by a modified version of CSA.
lems. Sayed et al. [146] used CSA with chaos theory to solve
the FS problem. C. CIVIL ENGINEERING
Recently, many works have been proposed to solve struc-
2) Image processing tural optimization problems using different MAs. In [105],
In [90], the authors used CSA to estimate multilevel thresh- authors employed their new version of CSA in finding the
old optimal values of image based on Kapur’s entropy. They design of the optimum structure. Also, Lin et al. [159] used
tested their model on different values of thresholds (2, 4, modified CSA with a fuzzy concept to control adjacent con-
12 VOLUME 4, 2016

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3024108, IEEE Access

Author et al.: Preparation of Papers for IEEE TRANSACTIONS and JOURNALS

FIGURE 5: Distribution of CSA related papers in many application, as reported by Scopus.

nected building by magnetorheological dampers concerning Banadkooki et al. [165] employed CSA to optimize the oper-
soil–structure interaction ation of the reservoir and minimize water in irrigation. They
compared their results with PSO, Shark Algorithm (SA), GA,
D. CHEMICAL ENGINEERING & QSAR and Weed Algorithm (WA).
Abdallah and Algmal [86] used an improved binary version
of CSA in order to classify skin sensitization potential based 2) Aircraft maintenance check
on quantitative structure-activity relationship (QSAR) model
Siswanto et al. [166] used CSA in order to check aircraft
E. CONTROL ENGINEERING maintenance and airworthiness program. To validate their model,
Kumar et al. [160] used CSA to find the static VAR com- they compared CSA with PSO and hybrid PSO with a greedy
pensator (SVC) optimal dynamic control assisted Single Ma- randomized adaptive search (PSO-GRASP).
chine Infinite Bus (SMIB). Also, in [161], authors applied
the island-based CSA in solving optimal control problems: 3) Wireless sensor network
parallel reaction, continuous stirred tank reactor, batch reac- Gupta et al. [167] used CSA to detect fault that may accrue
tor consecutive reaction, nonlinear constrained mathematical in the wireless sensor network, which may lead to system
system, nonlinear continuous stirred tank reactor, and non- failure.
linear crane container problems. In [162], the hybrid CSA
with a pattern search algorithm has been applied in studies of
4) Privacy preservation in health care
a multi-area LFC system using the FOPID-PDN controller.
Likewise, Majhi et al. [103] applied their improved version of Health care information privacy and security is one of the
CSA, which called OBL-CSA-MO in the FOPID controller most critical requirements for pharmacological or health prac-
design. titioners [168]. Mandala and Rao [169] used CSA with the
probability of adaptive awareness to improve the preservation
F. OTHER APPLICATIONS of medical data in the health care sector. Their improved CSA
1) Water management (AAP-CSA) was compared with PSO, GA, DE, and original
Optimal management in water and energy is needed as many CSA.
countries suffering from a lack of water & energy resources.
VOLUME 4, 2016 13

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3024108, IEEE Access

Author et al.: Preparation of Papers for IEEE TRANSACTIONS and JOURNALS

5) Travelling salesman problem need to be addressed in the future. Several areas that may be
Azezan et al. [170] tried to solve the common Traveling Sales- handled in the future is list below:
man Problem (TSP) using the CSA. They used ten datasets • No work in the literature studied the tuning parameters
from TSPLIB and compared them with ACO and SA. They of CSA.
argued that CSA’s performance is the best. • No work in the literature has been introduced to adapt
CSA to work in dynamic & Multi-objective dynamic
6) Stock index price movement prediction problems.
Future prediction of stock index price is critical for investors • CSA can be hybridized with many other algorithms.
who plan to increase profit and researchers who wish to ex- • No work in the literature has been introduced to adapt
tract complex stock market data over time series data. Dash et CSA to work in a noisy optimization problem.
al. [171] used TOPSIS and CSA to predict stock index price • CSA needs more theoretical studies.
movement.
REFERENCES
VI. ASSESSMENT AND EVALUATION OF CSA [1] Zhao, X., et al., Feature selection based on improved ant colony op-
In this section, CSA analysis and evaluation has been dis- timization for online detection of foreign fiber in cotton. Applied Soft
Computing, 2014. 24: p. 585-596.
cussed first, then a comparison between CSA and other meta- [2] Wang, M. and H. Chen, Chaotic multi-swarm whale optimizer boosted
heurstics algorithm have been performed and discussed. support vector machine for medical diagnosis. Applied Soft Computing,
2020. 88: p. 105946.
[3] Zhao, X., et al., Chaos enhanced grey wolf optimization wrapped ELM
A. CSA EVALUATION & ANALYSIS for diagnosis of paraquat-poisoned patients. Computational biology and
CSA has many advantages: easy in implementation and sim- chemistry, 2019. 78: p. 481-490.
ple inspiration. Moreover, CSA has a fewer number of pa- [4] Xu, X. and H.-L. Chen, Adaptive computational chemotaxis based on field
in bacterial foraging optimization. Soft Computing, 2014. 18(4): p. 797-
rameters. However, CSA has many drawbacks like all other 807.
MA, as according to No Free Lunch (NFL), CSA has not [5] Shen, L., et al., Evolving support vector machines using fruit fly optimiza-
the ability to solve all optimization problems. Furthermore, tion for medical data classification. Knowledge-Based Systems, 2016. 96:
p. 61-75.
CSA does not perform well in high dimensional & complex [6] Wang, M., et al., Toward an optimal kernel extreme learning machine using
problems. Furthermore, the ability to control the parameters a chaotic moth-flame optimization strategy with applications in medical
of CSA is deficient. diagnoses. Neurocomputing, 2017. 267: p. 69-84.
[7] Xu, Y., et al., Enhanced Moth-flame optimizer with mutation strategy for
global optimization. Information Sciences, 2019. 492: p. 181-203.
B. RESULTS AND COMPARISONS [8] hen, H., et al., An enhanced Bacterial Foraging Optimization and its
To show the effectiveness and the power of CSA. A compar- application for training kernel extreme learning machine. Applied Soft
Computing, 2020. 86: p. 105884.
ison among many MA has been made including Grey Wolf [9] 1. Sun, Y., G.G. Yen, and Z. Yi, IGD Indicator-Based Evolutionary
Optimization, Particle Swarm Optimization, Sine Cosine Al- Algorithm for Many-Objective Optimization Problems. IEEE Transactions
gorithm, Bat Algorithm, Firefly Algorithm, Moth-Flame Op- on Evolutionary Computation, 2019. 23(2): p. 173-187.
[10] Sun, Y., et al., Evolving Deep Convolutional Neural Networks for Image
timization, Whale Optimization Algorithm, Invasive Weed Classification. IEEE Transactions on Evolutionary Computation, 2020.
Optimization (IWO) [180] , and Electromagnetism like Mech- 24(2): p. 394-407.
anism Algorithm (EM) [181]. As seen in Table 9, CSA has [11] Sun, Y., et al., Automatically Designing CNN Architectures Using the
Genetic Algorithm for Image Classification. IEEE Transactions on Cyber-
achieved promising and better results in approximately all netics, 2020: p. 1-15.
functions. As shown in Figure 6, a statistical test called the [12] Chen, H., et al., A balanced whale optimization algorithm for constrained
Friedman test is used to assess and evaluate CSA results. As engineering design problems. Applied Mathematical Modelling, 2019. 71:
p. 45-59.
shown, we can observe that CSA has ranked first. Figure 7 [13] Luo, J., et al., Multi-strategy boosted mutative whale-inspired optimization
shows the convergence curves for some representative func- approaches. Applied Mathematical Modelling, 2019. 73: p. 109-123.
tions in which we can observe the dominant speed of CSA [14] Yu, H., et al., Chaos-enhanced synchronized bat optimizer. Applied Math-
ematical Modelling, 2020. 77: p. 1201-1215.
convergence. [15] Chen, H., M. Wang, and X. Zhao, A multi-strategy enhanced sine cosine
algorithm for global optimization and constrained practical engineering
VII. CONCLUSION & FUTURE WORK problems. Applied Mathematics and Computation, 2020. 369: p. 124872
(https://doi.org/10.1016/j.amc.2019.124872).
Crow Search Algorithm (CSA) is a recently developed al- [16] Zhang, X., et al., Gaussian mutational chaotic fruit fly-built optimization
gorithm that simulates the behavior of crows in storing and and feature selection. Expert Systems with Applications, 2020. 141: p.
retrieving food. Researchers have given great interest and at- 112976.
[17] Deng, W., J. Xu, and H. Zhao, An Improved Ant Colony Optimization
tention to CSA due to its excellent characteristics. This paper Algorithm Based on Hybrid Strategies for Scheduling Problem. IEEE
introduces a comprehensive review of the CSA. About 135 Access, 2019. 7: p. 20281-20292.
papers have been collected and summarized. All CSA mod- [18] Deng, W., et al., A novel collaborative optimization algorithm in solving
complex optimization problems. Soft Computing, 2017. 21(15): p. 4387-
ifications have been highlighted and categorized into three 4398.
classes: variants, hybrid, and multi-objective. The limitations [19] Chen, H., et al., Multi-population differential evolution-assisted Harris
and strengths of CSA have been discussed in details. A com- hawks optimization: Framework and case studies. Future Generation Com-
puter Systems, 2020. 111: p. 175-198.
prehensive set of applications has been studied. Although, the [20] J. H. Holland, Adaptation in natural and artificial systems: an introductory
success and popularity of CSA, many areas and challenges analysis with applications to biology, control, and arti

14 VOLUME 4, 2016

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3024108, IEEE Access

Author et al.: Preparation of Papers for IEEE TRANSACTIONS and JOURNALS

TABLE 9: The average results for solving benchmark functions.

No. CSA GWO PSO SCA BA FA MFO WOA IWO EM
F1 1.99E+06 5.85E+07 8.33E+06 2.57E+08 8.57E+05 2.77E+08 1.06E+08 2.95E+07 1.10E+06 2.50E+07
F2 8.58E+03 2.01E+09 1.43E+08 1.49E+10 5.66E+05 1.55E+10 1.28E+10 3.57E+06 3.86E+06 5.29E+08
F3 8.22E+02 2.99E+04 9.48E+02 3.79E+04 4.93E+02 6.48E+04 1.02E+05 4.21E+04 1.19E+04 1.63E+04
F4 5.44E+02 6.78E+02 4.81E+02 1.43E+03 4.43E+02 1.46E+03 1.04E+03 5.78E+02 4.59E+02 6.60E+02
F5 5.20E+02 5.21E+02 5.21E+02 5.21E+02 5.21E+02 5.21E+02 5.20E+02 5.20E+02 5.21E+02 5.21E+02
F6 6.30E+02 6.14E+02 6.23E+02 6.35E+02 6.35E+02 6.34E+02 6.22E+02 6.36E+02 6.37E+02 6.25E+02
F7 7.00E+02 7.20E+02 7.02E+02 8.32E+02 7.01E+02 8.33E+02 8.30E+02 7.01E+02 7.01E+02 7.08E+02
F8 9.35E+02 8.82E+02 9.69E+02 1.05E+03 1.04E+03 1.02E+03 9.44E+02 9.77E+02 1.08E+03 8.92E+02
F9 1.05E+03 1.01E+03 1.11E+03 1.17E+03 1.18E+03 1.16E+03 1.12E+03 1.13E+03 1.30E+03 1.06E+03
F10 4.32E+03 3.21E+03 5.19E+03 6.72E+03 5.39E+03 7.54E+03 4.63E+03 4.90E+03 5.57E+03 2.74E+03
F11 4.82E+03 4.04E+03 5.73E+03 7.96E+03 5.62E+03 7.96E+03 5.45E+03 6.03E+03 5.53E+03 4.91E+03
F12 1.20E+03 1.20E+03 1.20E+03 1.20E+03 1.20E+03 1.20E+03 1.20E+03 1.20E+03 1.20E+03 1.20E+03
F13 1.30E+03 1.30E+03 1.30E+03 1.30E+03 1.30E+03 1.30E+03 1.30E+03 1.30E+03 1.30E+03 1.30E+03
F14 1.40E+03 1.40E+03 1.40E+03 1.44E+03 1.43E+03 1.40E+03 1.40E+03 1.40E+03 1.40E+03 1.40E+03
F15 1.52E+03 1.59E+03 1.52E+03 4.15E+03 1.53E+03 1.64E+04 2.21E+05 1.58E+03 1.52E+03 1.53E+03
F16 1.61E+03 1.61E+03 1.61E+03 1.61E+03 1.61E+03 1.61E+03 1.61E+03 1.61E+03 1.61E+03 1.61E+03
F17 1.54E+04 1.77E+06 2.47E+05 7.37E+06 1.12E+05 7.01E+06 2.33E+06 4.07E+06 5.56E+04 8.11E+05
F18 2.13E+03 6.78E+06 2.20E+06 1.94E+08 1.08E+05 2.79E+08 2.06E+05 7.77E+03 5.22E+04 6.08E+07
F19 1.93E+03 1.95E+03 1.92E+03 1.99E+03 1.93E+03 2.00E+03 1.96E+03 1.95E+03 1.92E+03 1.94E+03
F20 2.40E+03 1.77E+04 2.32E+03 1.51E+04 2.40E+03 2.14E+04 7.13E+04 2.42E+04 4.05E+03 2.70E+03
F21 1.23E+04 9.02E+05 1.11E+05 1.31E+06 5.87E+04 1.71E+06 3.87E+05 1.18E+06 3.45E+04 1.72E+05
F22 2.82E+03 2.57E+03 2.86E+03 2.95E+03 3.30E+03 2.99E+03 3.04E+03 2.96E+03 3.40E+03 2.85E+03
F23 2.62E+03 2.63E+03 2.62E+03 2.66E+03 2.62E+03 2.73E+03 2.67E+03 2.63E+03 2.62E+03 2.57E+03
F24 2.61E+03 2.60E+03 2.63E+03 2.60E+03 2.66E+03 2.71E+03 2.69E+03 2.61E+03 2.70E+03 2.60E+03
F25 2.71E+03 2.71E+03 2.71E+03 2.73E+03 2.73E+03 2.73E+03 2.72E+03 2.71E+03 2.73E+03 2.70E+03
F26 2.70E+03 2.74E+03 2.77E+03 2.70E+03 2.70E+03 .70E+03 2.70E+03 2.70E+03 2.79E+03 2.79E+03
F27 3.17E+03 3.34E+03 3.50E+03 3.55E+03 3.89E+03 3.80E+03 3.59E+03 3.87E+03 3.85E+03 3.63E+03
F28 6.55E+03 3.89E+03 7.07E+03 4.74E+03 5.39E+03 .24E+03 3.90E+03 5.07E+03 7.87E+03 5.67E+03
F29 1.93E+06 2.48E+06 3.39E+04 1.06E+07 3.41E+07 2.66E+06 3.66E+06 6.04E+06 6.39E+05 8.28E+06
F30 1.09E+04 5.19E+04 1.30E+04 2.62E+05 1.47E+04 1.77E+05 5.64E+04 8.67E+04 9.56E+03 1.13E+04

FIGURE 6: The average ranking results of the CSA and other peers

VOLUME 4, 2016 15

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3024108, IEEE Access

Author et al.: Preparation of Papers for IEEE TRANSACTIONS and JOURNALS

FIGURE 7: Convergence curves of the CSA and other peers

cial intelligence, MIT press, 1992. [28]

[21] S. Kirkpatrick, C. D. Gelatt, M. P. Vecchi, Optimization by simulated [29] E. Rashedi, H. Nezamabadi-Pour, S. Saryazdi, Gsa: a gravitational search
annealing, science 220 (4598) (1983) 671-680. algorithm, Information sciences 179 (13) (2009) 2232-2248.
[22] F. Glover, C. McMillan, The general employee scheduling problem. an [30] H. Wang, J. Cuevas, Y. Lai, Y. Liang, Virus optimization algorithm (voa):
integration of ms and ai, Computers & operations research 13 (5) (1986) A novel metaheuristic for solving continuous optimization problems, in:
563-573. Proceedings of 10th Asia Pacific industrial engineering & management
[23] R. Eberhart, J. Kennedy, A new optimizer using particle swarm theory, in: system conference (APIEMS), Kitakyushu, Japan, 2009, pp. 14-16.
Micro Machine and Human Science, 1995. MHS’95., Proceedings of the [31] X.-S. Yang, A new metaheuristic bat-inspired algorithm, in: Nature in-
Sixth International Symposium on, IEEE, 1995, pp. 39-43. spired cooperative strategies for optimization (NICSO 2010), Springer,
[24] P. Civicioglu, Transforming geocentric cartesian coordinates to geodetic 2010, pp. 65-74.
coordinates by using differential search algorithm, Computers & Geo- [32] M. Dorigo, M. Birattari, Ant colony optimization, in: Encyclopedia of
sciences 46 (2012) 229-247. machine learning, Springer, 2011, pp. 36-39.
[25] Z. W. Geem, J. H. Kim, G. V. Loganathan, A new heuristic optimization [33] X.-S. Yang, Flower pollination algorithm for global optimization, in:
algorithm: harmony search, simulation 76 (2) (2001) 60-68. International conference on unconventional computing and natural com-
[26] S.-C. Chu, P.-W. Tsai, J.-S. Pan, Cat swarm optimization, in: Pacific Rim putation, Springer, 2012, pp. 240-249.
International Conference on Arti [34] A. H. Gandomi, A. H. Alavi, Krill herd: a new bio-inspired optimization
cial Intelligence, Springer, 2006, pp. 854-858. algorithm, Communications in Nonlinear Science and Numerical Simula-
[27] X.-S. Yang, Nature-inspired metaheuristic algorithms, Luniver press, tion 17 (12) (2012) 4831-4845.
2010. [35] X. Meng, Y. Liu, X. Gao, H. Zhang, A new bio-inspired algorithm: chicken

16 VOLUME 4, 2016

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3024108, IEEE Access

Author et al.: Preparation of Papers for IEEE TRANSACTIONS and JOURNALS

swarm optimization, in: International conference in swarm intelligence, [61] Z. Wei, C. Huang, X. Wang, T. Han, Y. Li, Nuclear reaction optimization:
Springer, 2014, pp. 86-94. A novel and powerful physics-based algorithm for global optimization,
[36] S. Mirjalili, S. M. Mirjalili, A. Lewis, Grey wolf optimizer, Advances in IEEE Access.
engineering software 69 (2014) 46-61. [62] S. Mirjalili, Moth-flame optimization algorithm: A novel nature-inspired
[37] J. James, V. O. Li, A social spider algorithm for global optimization, heuristic paradigm, Knowledge-Based Systems 89 (2015) 228-249.
Applied Soft Computing 30 (2015) 614-627. [63] A. O. Topal, O. Altun, A novel meta-heuristic algorithm: dynamic virtual
[38] A. S. Assiri, A. G. Hussien, M. Amin, Ant lion optimization: variants, bats algorithm, Information Sciences 354 (2016) 222-235.
hybrids, and applications, IEEE Access. [64] L. J. Fogel, A. J. Owens, M. J. Walsh, Arti
[39] A. G. Hussien, M. Amin, M. Abd El Aziz, A comprehensive review of cial intelligence through simulated evolution.
moth-flame optimisation: variants, hybrids, and applications, Journal of [65] I. Rechenberg, Evolution strategy: Optimization of technical systems
Experimental & Theoretical Artificial Intelligence (2020) 1-21. according to the principles of biological evolution. frommann-holzbog,
[40] G.-G. Wang, S. Deb, L. d. S. Coelho, Elephant herding optimization, in: stuttgart, 1973, Step-Size Adaptation Based on Non-Local Use of Selec-
Computational and Business Intelligence (IS-CBI), 2015 3rd International tion Information. In Parallel Problem Solving from Nature (PPSN3).
Symposium on, IEEE, 2015, pp.1-5. [66] ] R. Storn, K. Price, Differential evolution a simple and efficient heuristic
[41] S. Mirjalili, S. M. Mirjalili, A. Hatamlou, Multi-verse optimizer: a nature- for global optimization over continuous spaces, Journal of global optimiza-
inspired algorithm for global optimization, Neural Computing and Appli- tion 11 (4) (1997) 341-359.
cations 27 (2) (2016) 495-513. [67] X. Li, A new intelligent optimization method-artificial fish school algo-
[42] A. G. Hussien, A. E. Hassanien, E. H. Houssein, M. Amin, A. T. Azar, New rithm, doctor thesis of Zhejiang University.
binary whale optimization algorithm for discrete optimization problems, [68] K. M. Passino, Biomimicry of bacterial foraging for distributed optimiza-
Engineering Optimization 52 (6) (2020) 945-959. tion and control, IEEE control systems magazine 22 (3) (2002) 52-67.
[43] S. Mirjalili, Dragonfly algorithm: a new meta-heuristic optimization tech- [69] K. Krishnanand, D. Ghose, Detection of multiple source locations using
nique for solving single-objective, discrete, and multi-objective problems, a glowworm metaphor with applications to collective robotics, in: Swarm
Neural Computing and Applications27 (4) (2016) 1053-1073. intelligence symposium, 2005. SIS 2005. Proceedings 2005 IEEE, IEEE,
[44] S. Mirjalili, Sca: a sine cosine algorithm for solving optimization prob- 2005, pp. 84-91.
lems, Knowledge-Based Systems 96 (2016) 120-133. [70] D. Karaboga, An idea based on honey bee swarm for numerical opti-
[45] N. S. Jaddi, J. Alvankarian, S. Abdullah, Kidney-inspired algorithm for mization, Tech. rep., Technical report-tr06, Erciyes university, engineering
optimization problems, Communications in Non-linear Science and Nu- faculty, computer engineering department (2005).
merical Simulation 42 (2017) 358-369. [71] D. Karaboga, B. Basturk, A powerful and efficient algorithm for numerical
[46] G. Dhiman, V. Kumar, Spotted hyena optimizer: A novel bio-inspired function optimization: arti
based metaheuristic technique for engineering applications, Advances in cial bee colony (abc) algorithm, Journal of global optimization 39 (3)
Engineering Software 114 (2017) 48-70. (2007) 459-471.
[47] S. Saremi, S. Mirjalili, A. Lewis, Grasshopper optimisation algorithm: [72] A. Kaveh, N. Farhoudi, A new optimization method: dolphin echolocation,
Theory and application, Advances in Engineering Software 105 (2017) Advances in Engineering Software 59 (2013) 53-70.
30-47. [73] T. T. Dhivyaprabha, P. Subashini, and M. Krishnaveni, “Synergistic fibrob-
[48] A. G. Hussien, A. E. Hassanien, E. H. Houssein, Swarming behaviour last optimization: A novel nature-inspired computing algorithm,” Frontiers
of salps algorithm for predicting chemical compound activities, in: 2017 Inf. Technol. Electron. Eng., vol. 19, no. 7, pp. 815–833, Jul. 2018.
Eighth International Conference on Intelligent Computing and Information [74] X. Chen, Y. Liu, X. Li, Z. Wang, S. Wang, and C. Gao, “A new evolution-
Systems (ICICIS), IEEE,2017, pp. 315-320. ary multiobjective model for traveling salesman problem,” IEEE Access,
[49] A. Faramarzi, M Heidarinejad, B Stephens, and S Mirjalili. “Equilibrium vol. 7, pp. 66964–66979, 2019
optimizer: A novel optimization algorithm.” Knowledge-Based Systems [75] X. Qi, Y. Zhu, H. Zhang, A new meta-heuristic butterfly-inspired algo-
191 (2020): 105190. rithm, Journal of Computational Science 23(2017) 226-239.
[50] Alsattar, H. A., A. A. Zaidan, and B. B. Zaidan. “Novel meta-heuristic [76] O. K. Erol, I. Eksin, A new optimization method: big bang-big crunch,
bald eagle search optimisation algorithm.” Artificial Intelligence Review Advances in Engineering Software 37 (2) (2006) 106-111.
(2019): 1-28. [77] P. Rabanal, I. Rodríguez, F. Rubio, Using river formation dynamics to de-
[51] Heidari, Ali Asghar, Seyedali Mirjalili, Hossam Faris, Ibrahim Aljarah, sign heuristic algorithms, in: International conference on unconventional
Majdi Mafarja, and Huiling Chen. “Harris hawks optimization: Algorithm computation, Springer, 2007, pp. 163-177.
and applications.” Future Generation Computer Systems 97 (2019): 849- [78] A. Kaveh, M. Khayatazad, A new meta-heuristic method: ray optimization,
872. Computers & structures 112 (2012) 283-294.
[52] Wei, Zhenglei, Changqiang Huang, Xiaofei Wang, Tong Han, and Yintong [79] A. Sadollah, A. Bahreininejad, H. Eskandar, M. Hamdi, Mine blast
Li. “Nuclear reaction optimization: A novel and powerful physics-based algorithm: A new population based algorithm for solving constrained
algorithm for global optimization.” IEEE Access 7 (2019): 66084-66109. engineering optimization problems, Applied Soft Computing 13 (5) (2013)
[53] Li, Shimin, Huiling Chen, Mingjing Wang, Ali Asghar Heidari, and 2592-2612.
Seyedali Mirjalili. ‘Slime mould algorithm: A new method for stochastic [80] A. F. Nematollahi, A. Rahiminejad, B. Vahidi, A novel physical based
optimization.” Future Generation Computer Systems (2020). meta-heuristic optimization method known as lightning attachment pro-
[54] Dutta, Tulika, Siddhartha Bhattacharyya, Sandip Dey, and Jan Platos. cedure optimization, Applied Soft Computing 59 (2017) 596-621.
“Border Collie Optimization.” IEEE Access (2020). [81] L. M. Zhang, C. Dahlmann, Y. Zhang, Human-inspired algorithms for
[55] Mohamed, Ali Wagdy, Anas A. Hadi, and Ali Khater Mohamed. “Gaining- continuous function optimization, in: 2009 IEEE international conference
sharing knowledge based algorithm for solving optimization problems: on intelligent computing and intelligent systems, Vol. 1, IEEE, 2009, pp.
A novel nature-inspired algorithm.” International Journal of Machine 318-321.
Learning and Cybernetics (2019): 1-29. [82] Y. Xu, Z. Cui, J. Zeng, Social emotional optimization algorithm for
[56] A. Kaveh, A. Dadras, A novel meta-heuristic optimization algorithm: nonlinear constrained optimization problems, in: International Conference
Thermal exchange optimization, Advances in Engineering Software 110 on Swarm, Evolutionary, and Memetic Computing, Springer, 2010, pp.
(2017) 69-84. 583-590.
[57] A. Kaveh, A. Dadras, A novel meta-heuristic optimization algorithm: [83] Y. Shi, Brain storm optimization algorithm, in: International Conference
Thermal exchange optimization, Advances in Engineering Software 110 in Swarm Intelligence, Springer, 2011, pp. 303-309.
(2017) 69-84. [84] R. V. Rao, V. J. Savsani, D. Vakharia, Teaching-learning-based opti-
[58] M. Jain, V. Singh, A. Rani, A novel nature-inspired algorithm for optimiza- mization: an optimization method for continuous non-linear large scale
tion: Squirrel search algorithm, Swarm and Evolutionary Computation problems, Information Sciences 183 (1) (2012) 1-15.
[59] F. A. Hashim, E. H. Houssein, M. S. Mabrouk, W. Al-Atabany,S. Mirjalili, [85] R. Moghdani, and S. Khodakaram “Volleyball premier league algorithm.”
Henry gas solubility based algorithm, Future Generation Computer Sys- Applied Soft Computing 64 (2018): 161-185.
tems 101 (2019) 646-667. [86] G. Y. Abdallh, Z. Y. Algamal, A qsar classi
[60] A. A. Heidari, S. Mirjalili, H. Faris, I. Aljarah, M. Mafarja, H. Chen, cation model of skin sensitization potential based on improving binary
Harris hawks optimization: Algorithm and applications, Future Generation crow search algorithm, Electronic Journal of Applied Statistical Analysis
Computer Systems 97 (2019) 849-872. 13 (1) (2020) 86-95.

VOLUME 4, 2016 17

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3024108, IEEE Access

Author et al.: Preparation of Papers for IEEE TRANSACTIONS and JOURNALS

[87] A. L. Fred, S. Kumar, P. Padmanaban, B. Gulyas, H. A. Kumar, Fuzzy- [110] P. Díaz, M. Pérez-Cisneros, E. Cuevas, O. Avalos, J. Gálvez, S. Hino-
crow search optimization for medical image segmentation, in: Applica- josa, D. Zaldivar, An improved crow search algorithm applied to energy
tions of Hybrid Metaheuristic Algorithms for Image Processing, Springer, problems, Energies 11 (3) (2018) 571.
2020, pp. 413-439. [111] D. Gupta, S. Sundaram, A. Khanna, A. E. Hassanien, V. H. C. De
[88] A. Saha, A. Bhattacharya, P. Das, A. K. Chakraborty, Crow search Albuquerque, Improved diagnosis of parkinson’s disease using optimized
algorithm for solving optimal power flow problem, in: 2017 Second crow search algorithm, Computers & Electrical Engineering 68 (2018)
International Conference on Electrical, Computer and Communication 412-424.
Technologies (ICECCT), IEEE, 2017, pp. 1-8. [112] S. Moghaddam, M. Bigdeli, M. Moradlou, P. Siano, Designing of stand-
[89] A. M. Anter, A. E. Hassenian, D. Oliva, An improved fast fuzzy c- alone hybrid pv/wind/battery system using improved crow search algo-
means using crow search optimization algorithm for crop identification rithm considering reliability index, International Journal of Energy and
in agricultural, Expert Systems with Applications 118 (2019) 340-354. Environmental Engineering 10 (4) (2019) 429-449.
[90] P. Upadhyay, J. K. Chhabra, Kapur’s entropy based optimal multilevel [113] H. Fallah, O. Kisi, S. Kim, M. Rezaie-Balf, A new optimization approach
image segmentation using crow search algorithm, Applied Soft Computing for the least-cost design of water distribution networks: Improved crow
(2019) 105522. search algorithm, Water Resources Management 33 (10) (2019) 3595-
[91] H. Faris, I. Aljarah, M. A. Al-Betar, and S. Mirjalili, “Grey wolf optimizer: 3613.
A review of recent variants and applications,” Neural Comput. Appl., vol. [114] R. M. Sahoo, S. K. Padhy, Improved crow search optimization for multi-
30, no. 2, pp. 413-435, Jul. 2018. processor task scheduling: A novel approach, in: International Conference
[92] I. Fister, I. Fister, Jr., X.-S. Yang, and J. Brest, “A comprehensive review of on Application of Robotics in Industry using Advanced Mechanisms,
firefly algorithms,” Swarm Evol. Comput., vol. 13, pp. 34-46, Dec. 2013 Springer, 2019, pp. 1-13.
[93] E. Rashedi, E. Rashedi, and H. Nezamabadi-Pour, “A comprehensive [115] S. Arora, H. Singh, M. Sharma, S. Sharma, P. Anand, A new hybrid
survey on gravitational search algorithm,” Swarm Evol. Comput., vol. 41, algorithm based on grey wolf optimization and crow search algorithm for
pp. 141-158, Aug. 2018. unconstrained function optimization and feature selection, IEEE Access 7
[94] G.-G. Wang, A. H. Gandomi, A. H. Alavi, and D. Gong, “A comprehensive (2019) 26343-26361.
review of krill herd algorithm: Variants, hybrids and applications,” Artif. [116] F. Davoodkhani, S. A. Nowdeh, A. Y. Abdelaziz, S. Mansoori, S. Nasri,
Intell. Rev., vol. 51, no. 1, pp. 119-148, Jan. 2019. M. Alijani, A new hybrid method based on gray wolf optimizer-crow
[95] A. Askarzadeh, A novel metaheuristic method for solving constrained search algorithm for maximum power point tracking of photovoltaic
engineering optimization problems: crow search algorithm, Computers & energy system, in: Modern Maximum Power Point Tracking Techniques
Structures 169 (2016) 1-12. for Photovoltaic Energy Systems, Springer, 2020, pp. 421-438.
[117] A. B. Pratiwi, A hybrid cat swarm optimization-crow search algorithm
[96] R. C. T. De Souza, L. dos Santos Coelho, C. A. De Macedo, J. Pierezan,
for vehicle routing problem with time windows, in: 2017 2nd International
A v-shaped binary crow search algorithm for FS, in: 2018 IEEE Congress
conferences on Information Technology, Information Systems and Electri-
on Evolutionary Computation (CEC), IEEE, 2018, pp. 1-8.
cal Engineering (ICITISEE), IEEE, 2017, pp. 364-368.
[97] L. dos Santos Coelho, C. Richter, V. C. Mariani, A. Askarzadeh, Modi
[118] R. Kumar, Hybrid cat swarm and crow search algorithm to solve the
ed crow search approach applied to electromagnetic optimization, in: 2016
combined economic emission dispatch model for smart grid.
IEEE Conference on Electromagnetic Field Computation (CEFC), IEEE,
[119] N. Javaid, S. M. Mohsin, A. Iqbal, A. Yasmeen, I. Ali, et al., A hybrid
2016, pp. 1-1.
bat-crow search algorithm based home energy management in smart grid,
[98] D. Gupta, J. J. Rodrigues, S. Sundaram, A. Khanna, V. Korotaev, V. H. C.
in: Conference on Complex, Intelligent, and Software Intensive Systems,
de Albuquerque, Usability feature extraction using modi
Springer, 2018, pp. 75-88.
ed crow search algorithm: a novel approach, Neural Computing and
[120] Z.-X. Wu, Z.-P. Jiang, K.-W. Huang, Y.-M. Su, A hybrid crow particle
Applications (2018) 1-11.
optimization algorithm to solve permutation flow shop scheduling prob-
[99] F. Mohammadi, H. Abdi, A modified crow search algorithm (mcsa) for
lems.
solving economic load dispatch problem, Applied Soft Computing 71
[121] K. Dhanya, S. Kanmani, G. Hanitha, S. Abirami, Hybrid crow search-ant
(2018) 51-65.
colony optimization algorithm for capacitated vehicle routing problem, in:
[100] E. Cuevas, E. B. Espejo, A. C. Enríquez, A modified crow search International Conference on Soft Computing Systems, Springer, 2018, pp.
algorithm with applications to power system problems, in: Metaheuristics 46-52.
Algorithms in Power Systems, Springer, 2019, pp. 137-166. [122] N. Mahesh, S. Vijayachitra, Decsa: hybrid dolphin echolocation and crow
[101] J. Islam, P. M. Vasant, B. M. Negash, J. Watada, A modified crow search optimization for cluster-based energy-aware routing in wsn, Neural
search algorithm with niching technique for numerical optimization, in: Computing and Applications 31 (1) (2019) 47-62.
2019 IEEE Student Conference on Research and Development (SCOReD), [123] S. H. R. Pasandideh, S. Khalilpourazari, Sine cosine crow search algo-
IEEE, 2019, pp. 170-175. rithm: a powerful hybrid meta heuristic for global optimization, arXiv
[102] H. Wu, P. Wu, K. Xu, F. Li, Finite element model updating using crow preprint arXiv:1801.08485.
search algorithm with levy flight, International Journal for Numerical [124] S. Khalilpourazari, S. H. R. Pasandideh, Sine-cosine crow search algo-
Methods in Engineering. rithm: theory and applications, Neural Computing and Applications (2019)
[103] S. K. Majhi, M. Sahoo, R. Pradhan, Oppositional crow search algorithm 1-18.
with mutation operator for global optimization and application in design- [125] M. Allaoui, B. Ahiod, M. El Yafrani, A hybrid crow search algorithm
ing fopid controller, Evolving Systems (2019) 1-26. for solving the dna fragment assembly problem, Expert Systems with
[104] H. Zamani, M. H. Nadimi-Shahraki, A. H. Gandomi, Ccsa: Conscious Applications 102 (2018) 44-56.
neighborhood-based crow search algorithm for solving global optimiza- [126] A. M. Anter, M. Ali, Feature selection strategy based on hybrid crow
tion problems, Applied Soft Computing 85 (2019) 105583. search optimization algorithm integrated with chaos theory and fuzzy c-
[105] A. Javidi, E. Salajegheh, J. Salajegheh, Enhanced crow search algorithm means algorithm for medical diagnosis problems, Soft Computing 24 (3)
for optimum design of structures, Applied Soft Computing 77 (2019) 274- (2020) 1565-1584.
289. [127] K.-W. Huang, A. S. Girsang, Z.-X. Wu, Y.-W. Chuang, A hybrid crow
[106] A. K. Bhullar, R. Kaur, S. Sondhi, Enhanced crow search algorithm for search algorithm for solving permutation flow shop scheduling problems,
avr optimization, Soft Computing (2020) 1-31. Applied Sciences 9 (7) (2019) 1353.
[107] E. Cuevas, J. Gálvez, O. Avalos, An enhanced crow search algorithm [128] A. E. Hassanien, R. M. Rizk-Allah, M. Elhoseny, A hybrid crow search
applied to energy approaches, in: Recent Metaheuristics Algorithms for algorithm based on rough searching scheme for solving engineering
Parameter Identification, Springer, 2020, pp. 27-49. optimization problems, Journal of Ambient Intelligence and Humanized
[108] M. Jain, A. Rani, V. Singh, An improved crow search algorithm for Computing (2018) 1-25.
high-dimensional problems, Journal of Intelligent & Fuzzy Systems 33 [129] H. Nobahari, A. Bighashdel, Mocsa: a multi-objective crow search algo-
(6) (2017) 3597-3614. rithm for multi-objective optimization, in: 2017 2nd Conference on Swarm
[109] Z. Shi, Q. Li, S. Zhang, X. Huang, Improved crow search algorithm Intelligence and Evolutionary Computation (CSIEC), IEEE, 2017, pp. 60-
with inertia weight factor and roulette wheel selection scheme, in: 2017 65.
10th International Symposium on Computational Intelligence and Design [130] S. Hinojosa, D. Oliva, E. Cuevas, G. Pajares, O. Avalos, J. Gálvez,
(ISCID), Vol. 1, IEEE, 2017, pp. 205-209. Improving multi-criterion optimization with chaos: a novel multi-objective

18 VOLUME 4, 2016

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3024108, IEEE Access

Author et al.: Preparation of Papers for IEEE TRANSACTIONS and JOURNALS

chaotic crow search algorithm, Neural Computing and Applications 29 (8) [152] A. Satpathy, S. K. Addya, A. K. Turuk, B. Majhi, G. Sahoo, A resource
(2018) 319-335. aware vm placement strategy in cloud data centers based on crow search
[131] P. Ramgouda, V. Chandraprakash, Constraints handling in combinatorial algorithm, in: 2017 4th International Conference on Advanced Computing
interaction testing using multi-objective crow search and fruit fly optimiza- and Communication Systems (ICACCS), IEEE, 2017, pp. 1-6.
tion, Soft Computing 23 (8) (2019) 2713-2726. [153] A. Satpathy, S. K. Addya, A. K. Turuk, B. Majhi, G. Sahoo, Crow search
[132] R. M. Rizk-Allah, A. E. Hassanien, A. Slowik, Multi-objective orthogo- based virtual machine placement strategy in cloud data centers with live
nal opposition-based crow search algorithm for large-scale multi-objective migration, Computers & Electrical Engineering 69 (2018) 334-350.
optimization, Neural Computing and Applications (2020) 1-32. [154] K. P. Kumar, K. Kousalya, Amelioration of task scheduling in cloud com-
[133] J. John, P. Rodrigues, Motco: Multi-objective taylor crow optimization puting using crow search algorithm, Neural Computing and Applications
algorithm for cluster head selection in energy aware wireless sensor (2019) 1-7.
network, Mobile Networks and Applications 24 (5) (2019) 1509-1525. [155] A. George, A. Sumathi, Dyadic product and crow lion algorithm based
[134] K. Abaci, V. Yamacli, Differential search algorithm for solving multi- coefficient generation for privacy protection on cloud, Cluster Computing
objective optimal power flow problem, International Journal of Electrical 22 (1) (2019) 1277-1288.
Power & Energy Systems 79 (2016) 1-10. [156] S. K. A. Malleswaran, B. Kasireddi, An Efficient Task Scheduling
[135] S. Sivasubramani, K. Swarup, Multi-objective harmony search algorithm Method In A Cloud Computing Environment Using Firefly Crow Search
for optimal power flow problem, International Journal of Electrical Power Algorithm (FF-CSA).
& Energy Systems 33 (3) (2011) 745-752. [157] C. A. Kumar, R. Vimala, C-fdla: Crow search with integrated fractional
[136] B. Mandal, P. K. Roy, Multi-objective optimal power flow using quasi- dragonfly algorithm for load balancing in cloud computing environments,
oppositional teaching learning based optimization, Applied Soft Comput- Journal of Circuits, Systems and Computers 28 (07) (2019) 1950115.
ing 21 (2014) 590-606. [158] S. Makhdoomi, A. Askarzadeh, Optimizing operation of a photo-
[137] A. Fathy, A. Abdelaziz, Single-objective optimal power flow for electric voltaic/diesel generator hybrid energy system with pumped hydro storage
power systems based on crow search algorithm, Archives of Electrical by a modi
Engineering 67 (1). ed crow search algorithm, Journal of Energy Storage 27 (2020) 101040.
[138] S. Naresh, M. D. Reddy, Y. K. Reddy, Optimal power flow solution using [159] X. Lin, S. Chen, W. Lin, Modified crow search algorithm based fuzzy
crow search algorithm. control of adjacent buildings connected by magnetorheological dampers
[139] A. Kumar, A. Pakhali, I. N. Trivedi, P. Jangir, Security constrained considering soil structure interaction, Journal of Vibration and Control
nonconvex economic load dispatch problems with prohibited operation (2020) 1077546320923438.
zones and ramp rates solve using crow search algorithm, in: AEPEE-2016 [160] S. Kumar, A. Kumar, G. Shankar, Crow search algorithm based optimal
conference, 2016, pp. 28-29. dynamic performance control of svc assisted smib system, in: 2018 20th
[140] A. F. Sheta, Solving the economic load dispatch problem using crow National Power Systems Conference (NPSC), IEEE, 2018, pp. 1-6.
search algorithm, in: 8th International Multi-Conference on Complexity, [161] M. S. Turgut, O. E. Turgut, D. T. Eliiyi, Island-based crow search
Informatics and Cybernetics (IMCIC 2017), 2017, pp. 95-100. algorithm for solving optimal control problems, Applied Soft Computing
[141] S. R. Spea, Solving practical economic load dispatch problem using 90 (2020) 106170.
crow search algorithm, International Journal of Electrical and Computer
[162] N. R. Babu, L. C. Saikia, D. K. Raju, Maiden application of hybrid crow
Engineering 10 (4) (2020) 3431.
search algorithm with pattern search algorithm in lfc studies of a multi-area
[142] R. Habachi, A. Touil, A. Boulal, A. Charkaoui, A. Echchatbi, Solving
system using cascade fopi-pdn controller, in: Soft Computing for Problem
economic dispatch and unit commitment problem in smart grid system
Solving 2019, Springer, 2020, pp. 337-351.
using eagle strategy based crow search algorithm, Indonesian Journal of
[163] X. Han, Q. Xu, L. Yue, Y. Dong, G. Xie, X. Xu (2020). An Improved
Electrical Engineering and Computer Science 14 (3) (2019) 1087-1096.
Crow Search Algorithm Based on Spiral Search Mechanism for Solving
[143] A. G. Hussien, E. H. Houssein, A. E. Hassanien, A binary whale opti-
Numerical and Engineering Optimization Problems. IEEE Access.
mization algorithm with hyperbolic tangent
[164] S. Laabadi, M. Naimi, H. El Amri, B. Achchab, (2020). A Binary Crow
tness function for feature selection, in: 2017 Eighth International Confer-
Search Algorithm for Solving Two-dimensional Bin Packing Problem with
ence on Intelligent Computing and Information Systems (ICICIS), IEEE,
Fixed Orientation. Procedia Computer Science, 167, 809-818.
2017, pp. 166-172.
[144] A. G. Hussien, A. E. Hassanien, E. H. Houssein, S. Bhattacharyya, M. [165] F. B. Banadkooki, J. Adamowski, V. P. Singh, M. Ehteram, H. Karami,S.
Amin, S-shaped binary whale optimization algorithm for feature selection, F. Mousavi, S. Farzin, E. S. Ahmed, (2020). Crow Algorithm for Irrigation
in: Recent trends in signal and image processing, Springer, 2019, pp. 79- Management: A Case Study. Water Resources Management, 1-25.
87. [166] N. Siswanto, A. N. Adianto, H. A. Prawira, A. Rusdiansyah, A crow
[145] A. Allahverdipour, F. Soleimanian Gharehchopogh, An improved k- search algorithm for aircraft maintenance check problem and continuous
nearest neighbor with crow search algorithm for feature selection in text airworthiness maintenance program. Jurnal Sistem dan Manajemen Indus-
documents classi tri (2019), 3(2), 115-123.
cation, Journal of Advances in Computer Research 9 (2) (2018) 37-48. [167] D. Gupta, S. Sundaram, J. J. Rodrigues, A. Khanna, An improved fault
[146] G. I. Sayed, A. E. Hassanien, A. T. Azar, Feature selection via a novel detection crow search algorithm for wireless sensor network. International
chaotic crow search algorithm, Neural computing and applications 31 (1) Journal of Communication Systems (2019), e4136.
(2019) 171-188. [168] K. Zhang, X. Liang, M. Baura, R. Lu, X. S. Shen, PHDA: A priority
[147] D. Oliva, S. Hinojosa, E. Cuevas, G. Pajares, O. Avalos, J. Gálvez, Cross based health data aggregation with privacy preservation for cloud assisted
entropy based thresholding for magnetic resonance brain images using WBANs. Information Sciences (2014), 284, 130-141.
crow search algorithm, Expert Systems with Applications 79 (2017) 164- [169] J. Mandala, M. C. S. Rao, . Privacy preservation of data using crow search
180. with adaptive awareness probability. Journal of information security and
[148] R. Thomas, M. Rangachar, Gwtm and crow search algorithm for face applications, (2019) 44, 157-169.
recognition in low-resolution images, in: 2018 International Conference [170] N. A. Azezan, H. Masran, M. F. Ramli, . Preliminary design of crow
on Advances in Computing, Communication Control and Networking search metaheuristics algorithm for travelling salesman problem. In AIP
(ICACCCN), IEEE, 2018, pp. 963-970. Conference Proceedings (Vol. 2138, No. 1, p. 040004). AIP Publishing
[149] R. Chithra, P. Jagatheeswari, Fractional crow search-based support vector LLC. (2019, August)
neural network for patient classification and severity analysis of tubercu- [171] R. Dash, S. Samal, R. Dash, R. Rautray, An integrated TOPSIS crow
losis, IET Image Processing 13 (1) (2018) 108-117. search based classifier ensemble: In application to stock index price
[150] S. Sannasi Chakravarthy, H. Rajaguru, Lung cancer detection using movement prediction. Applied Soft Computing, 85, (2019) 105784.
probabilistic neural network with modi [172] D. K. Shende, S. S. Sonavane,. CrowWhale-ETR: CrowWhale optimiza-
ed crow-search algorithm, Asian Pacific journal of cancer prevention: tion algorithm for energy and trust aware multicast routing in WSN for IoT
APJCP 20 (7) (2019) 2159. applications. Wireless Networks, (2020) 1-19.
[151] N. S. More, R. B. Ingle, Energy-aware vm migration using dragonfly- [173] H. M. Farh, A. M. Al-Shaalan, A. M. Eltamaly, A. A. Al-Shamma’A,
crow optimization and support vector regression model in cloud, Interna- A Novel Crow Search Algorithm Auto-Drive PSO for Optimal Allocation
tional Journal of Modeling, Simulation, and Scientific Computing 9 (06) and Sizing of Renewable Distributed Generation. IEEE Access, 8, (2020).
(2018) 1850050. 27807-27820.

VOLUME 4, 2016 19

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3024108, IEEE Access

Author et al.: Preparation of Papers for IEEE TRANSACTIONS and JOURNALS

[174] K. Gaddala, P. S. Raju. "Merging lion with crow search algorithm for ABDELAZIM G. HUSSIEN received his Bache-
optimal location and sizing of UPQC in distribution network." Journal of lor’s Degree in 2013 from Math & Computer Sci-
Control, Automation and Electrical Systems 31, no. 2 (2020): 377-392. ence Department, Faculty of Science, Menoufia Uni-
[175] R. Ganeshan, R., P. Rodrigues. "Crow-AFL: Crow Based Adaptive Frac- versity, Egypt and received his Master’s Degree
tional Lion Optimization Approach for the Intrusion Detection." Wireless from Menoufia University faculty of Science, Egypt
Personal Communications (2019): 1-25. in 2018. Now, he is teaching assistant at Faculty
[176] R. M. Rizk-Allah,A. E. Hassanien, S. Bhattacharyya, S. (2018). Chaotic of science, Fayoum, Egypt. He interests in meta-
crow search algorithm for fractional optimization problems. Applied Soft
heurstics, swarm intelligence, and machine learn-
Computing, 71, 1161-1175.
ing and its applications.
[177] S. K. Majhi, M. Sahoo, R. Pradhan, (2019). A space transformational
crow search algorithm for optimization problems. Evolutionary Intelli-
gence, 1-20.
[178] H. Ozbasaran, M. E. Yildirim,(2020). Truss-sizing optimization attempts
with CSA: a detailed evaluation. SOFT COMPUTING.
[179] K. W. Huang, A. S. Girsang, Z. X. Wu, Y. W. Chuang, (2019). A Hybrid
Crow Search Algorithm for Solving Permutation Flow Shop Scheduling
Problems. Applied Sciences, 9(7), 1353.
[180] A. R. Mehrabian, and C. Lucas “A novel numerical optimization algo- MOHAMED AMIN received the B.Sc. degree in
rithm inspired from weed colonization.” Ecological informatics 1, no. 4 mathematics from the Faculty of Science, Menoufia
(2006): 355-366. University, in 1983, the M.Sc. degree in computer
[181] S. Birbil, S.C. Fang, “An electromagnetism-like mechanism for global science from the Faculty of Science, Ain Shams
optimization”, Journal of Global Optimization, 25 (3) (2003), pp. 263-282 University, in 1990, and the Ph.D. degree in com-
[182] Xiong, Z., Wu, Y., Ye, C., Zhang, X. and Xu, F., “Color image chaos puter science from Gdansk University, Poland, in
encryption algorithm combining CRC and nine palace map“, Multimedia 1997. He is currently a Professor of computer sci-
Tools and Applications, 78(22) (2019), pp.31035-31055 ence and the Head of the Department of Mathe-
[183] Zeng HB, Liu XG, Wang W. “A generalized free-matrix-based integral matics and Computer Science with Menoufia Uni-
inequality for stability analysis of time-varying delay systems“, Applied
versity. He has authored or coauthored many arti-
Mathematics and Computation, 354 (2019), pp. 1-8
cles in international repute journals, such as Information Sciences, Scientific
[184] Zhang, Hongrui, Shaocheng Qu, Huan Li, Jing Luo, and Wenjun Xu. “A
Moving Shadow Elimination Method Based on Fusion of Multi-Feature.“ Reports-Nature, and others. His research interests include grammar systems
IEEE Access 8 (2020), pp.63971-63982. as a link between AI and compiler design, metaheuristic optimization algo-
[185] Xiong, Q., Zhang, X., Wang, W., Gu, Y. “A Parallel Algorithm rithms, Petri nets, reasoning dynamic fuzzy systems, cryptography, quantum
Framework for Feature Extraction of EEG Signals on MPI.“ Compu- information processing, image processing, and biometrics. He is a reviewer
tational and Mathematical Methods in Medicine (2020), pp. 1-10. doi: in many prestigious journals.
10.1155/2020/9812019
[186] Xu, W., Qu, S., Zhao, L., Zhang, H. “ An Improved Adaptive
Sliding Mode Observer for a Middle and High-Speed Rotors Track-
ing“, IEEE transactions on power electronics (2020), pp.1-10, doi:
10.1109/TPEL.2020.3000785
[187] Zeng, H., Liu, X., Wang, W., Xiao, S. “New results on stability analysis
of systems with time-varying delays using a generalized free-matrix-based MINGJING WANG Mingjing Wang is now a Ph.D.
inequality“, Journal of the Franklin Institute, 356(13) (2019), pp.7312- research intern at the School of Computer Science
7321. doi: 10.1016/j.jfranklin.2019.03.029 and Engineering, Southeast University in China.
[188] Moayedi, H. Hayati, S. “Modelling and optimization of ulti- Currently, he is also a member of the Medical Data
mate bearing capacity of strip footing near a slope by soft com- Mining and Computation Intelligence in the col-
puting methods“, Applied Soft Computing, 66 (2018), pp. 208-219
lege of computer science and artificial intelligence
https://doi.org/10.1016/j.asoc.2018.02.027
at Wenzhou University, China. His main research
[189] Moayedi, H. Rezaei, A. “An artificial neural network approach for under-
reamed piles subjected to uplift forces in dry sand“, Neural Computing and interests are advanced machine learning, evolution-
Applications, 31(2) (2019), pp. 327-336 https://doi.org/10.1007/s00521- ary computation, meta-heuristics, prediction, in-
017-2990-z formation systems, and spatial modelling.
[190] Moayedi, H., Hayati, S. . “Applicability of a CPT-based neu-
ral network solution in predicting load-settlement responses of bored
pile“, International Journal of Geomechanics,18(6) (2018), pp.06018009.
https://doi.org/10.1061/(ASCE)GM.1943-5622.0001125
[191] Weibiao Qiao, Hossein Moayedi, and Loke Kok Foong. “Nature-
inspired hybrid techniques of IWO, DA, ES, GA, and ICA, vali-
dated through a k-fold validation process predicting monthly natu-
ral gas consumption“, Energy and Buildings 217 (2020), pp.110023.
https://doi.org/10.1016/j.enbuild.2020.110023
GUOXI LIANG Guoxi Liangis currently an in-
structor in the department of information technol-
ogy, Wenzhou Polytechnic. He is pursuing the Ph.D.
degree in global company start up at Kunsan Na-
tional University, South Korea. His present research
interests center on computer vision and natural lan-
guage processing, as well as intelligent medical
diagnosis. He is also a reviewer for many journals
such as IEEE ACCESS, Entropy, Sensors. He has
published several papers in international journals
and conference proceedings, including Symmetry and ICPADS, and among
others.

20 VOLUME 4, 2016

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.3024108, IEEE Access

Author et al.: Preparation of Papers for IEEE TRANSACTIONS and JOURNALS

AHMED ALSANAD received the Ph.D. degree

in computer science from De Montfort University,
U.K., in 2013. He is currently an Associate Profes-
sor with the Information System Department and a
Chair Member of Pervasive and Mobile Comput-
ing, CCIS, King Saud University, Riyadh, Saudi
Arabia. His research interests include cloud com-
puting, health informatics, ERP, and CRM. He has
authored or coauthored more than 20 publications,
including refereed IEEE/ACM/ Springer journals,
conference papers, and book chapters.

ABDU GUMAEI received his Ph.D. degree in Com-

puter Science from King Saud University, in 2019.
He is currently an Assistant Professor at the Col-
lege of Computer and Information Sciences, King
Saud University, Riyadh, Saudi Arabia. He worked
as a lecturer and taught many courses such as pro-
gramming languages at the computer science de-
partment, Taiz University, Yemen. He has authored
and coauthored more than 40 journal and confer-
ence papers in well-reputed international journals.
He has received a patent from the UNITED STATES PATENT AND TRADE-
MARK OFFICE (USPTO), in 2013. His main areas of interest are soft-
ware engineering, image processing, computer vision, machine learning,
networks, and Internet of Things (IoT).

HUILING CHEN Huiling Chen received the Ph.D.

degree from the Department of Computer Science
and Technology, Jilin University, China. He is cur-
rently an Associate Professor with the College of
Computer Science and Artificial Intelligence, Wen-
zhou University, China. He has published more than
100 articles in international journals and confer-
ence proceedings, including Information Sciences,
Pattern Recognition, Future Generation Computer
System, Expert Systems with Applications, Knowledge-
Based Systems, Neurocomputing, PAKDD, and among others. His current
research interests include machine learning and data mining, as well as their
applications to medical diagnosis and bankruptcy prediction. He is also a
Reviewer of many journals such as Applied Soft Computing, Artificial In-
telligence in Medicine, Knowledge-Based Systems, and Future Generation
Computer System. He has been serving as an Associate Editor for IEEE
Access.

VOLUME 4, 2016 21

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
View publication stats