Comparative study between metaheuristic algorithms for internet of things wireless nodes localization

International Journal of Electrical and Computer Engineering (IJECE)
Vol. 12, No. 1, February 2022, pp. 660~668
ISSN: 2088-8708, DOI: 10.11591/ijece.v12i1.pp660-668  660
Journal homepage: http://ijece.iaescore.com
Comparative study between metaheuristic algorithms for
internet of things wireless nodes localization
Rana Jassim Mohammed1
, Enas Abbas Abed2
, Mostafa Mahmoud Elgayar3
1
Department of Computer Science, University of Diyala, Baquba, Iraq
2
Department of Computer Engineering, University of Diyala, Baquba, Iraq
3
Department of Information Technology, Mansoura University, Mansoura, Egypt
Article Info ABSTRACT
Article history:
Received Jan 4, 2021
Revised Jul 15, 2021
Accepted Aug 4, 2021
Wireless networks are currently used in a wide range of healthcare, military,
or environmental applications. Wireless networks contain many nodes and
sensors that have many limitations, including limited power, limited
processing, and narrow range. Therefore, determining the coordinates of the
location of a node of the unknown location at a low cost and a limited
treatment is one of the most important challenges facing this field. There are
many meta-heuristic algorithms that help in identifying unknown nodes for
some known nodes. In this manuscript, hybrid metaheuristic optimization
algorithms such as grey wolf optimization and salp swarm algorithm are
used to solve localization problem of internet of things (IoT) sensors.
Several experiments are conducted on every meta-heuristic optimization
algorithm to compare them with the proposed method. The proposed
algorithm achieved high accuracy with low error rate (0.001) and low power
consumption.
Keywords:
Bacteria foraging algorithm
Biogeography-based
optimization
Butterfly optimization algorithm
Grey wolf optimization
Particle swarm optimization
Salp swarm algorithm
Wireless sensor network
This is an open access article under the CC BY-SA license.
Corresponding Author:
Mostafa Mahmoud Elgayar
Department of Information Technology, Mansoura University
Mansoura City, 35511, Egypt
Email: mostafa_elgayar@mans.edu.eg
1. INTRODUCTION
The internet of things (IoT) depends on powerful technologies such as wireless sensor networks
(WSN) and Radio-frequency identification (RFID), which have changed the current world in which we live
in conjunction with the tremendous development in sensor technology and cloud computing [1]-[3]. This
development led to some problems in identifying remote sensing areas and linking them together. There are
also other challenges, such as providing a safe environment for this type of wireless network, and there is
another challenge in how to create a coordinated and synchronous link between different sensing means that
perform the same task. You can learn how to create an ontology to link data and important points that
perform the same task through research [4], [5].
WSNs are small network nodes that record their surroundings collectively. WSNs are used in
several applications, such as weather, location search, location, hygiene, home self-regulation, and
transportation control. The sensor system contains a sensor segment, a conversion segment, and a power sector.
There are various types of sensor nodes. The primary type is the Prospector, which handles as Calculator. The
second type is thermal prospectors. The final third type is some of the things that are related to feelings [6], [7].
Localization is a significant problem in WSN. The positioning of a particular node position is
defined as a localization dilemma. In WSN, there will be many unlocalized nodes, densely packed in places
that may not be identified. In addition, the large number of devices in the IoT leads to problems with power

Int J Elec & Comp Eng ISSN: 2088-8708 
Comparative study between metaheuristic algorithms for … (Rana Jassim Mohammed)
661
consumption. In addition, the internet of things system is complex and dynamic. Therefore, many algorithms
of the international system have been developed to account for such complex activities involving simple people.
The global positioning system (GPS) can be used to locate the sensor nodes. The base station is
listening to GPS to find the coordinates of the sensor. But this method is expensive. An alternative approach
is communicating and listening beacon nodes [6]. In general, localization algorithms that are not affected by
GPS changes can be used in band-dependent and band-free authorizations. In distance-dependent localization
algorithms, a point-to-point distance setting or an angular line between sensor nodes is used. Under these
circumstances, the sensor nodes' settings are given with the help of a triple anchor. In contrast to area switch
location algorithms, domain-free location algorithms do not remove any information required to belong to
unknown nodes.
In the previous related works, combinations of metaheuristic methods have been utilized to resolve
the localization dilemma in WSNs. Various optimization algorithms in wireless sensor networks (WSN) such
as practical swarm optimization (PSO), salp swarm algorithm (SSA), butterfly optimization algorithm
(BOA), grey wolf optimization (GWO), bacterial foraging algorithm (BFA), artificial bee colony algorithm
(ABC), H-best particle swarm optimization (HPSO), biogeography-based optimization (BBO), genetic
algorithm (GA), and the artificial bee colony (ABC) are used to solve the localization problem. The
document's main contribution is to conduct several experiments using hybrid meta-heuristic optimization
algorithms to solve the localization problem in WSNs. Results were analyzed using many meta-heuristic
algorithms according to performance, speed, and cost. These contributions will be summarized as follows: i)
use hybrid meta-heuristic optimization algorithms to solve the localization problem. ii) solve power
limitation in IoT sensors by enhancing meta-heuristic optimization algorithm, iii) conduct several
experiments to prove the efficiency of the system used, iv) make a comparison between related works and
proposed method. Table 1 represent some of the related works.
The remaining parts of this manuscript are designed as follows: section 2 provides a brief
explanation of the various meta-heuristic algorithms. Section 3 introduces the research method and the
proposed algorithm to solve the localization problem using a hybrid of meta-heuristic algorithms. Section 4
covers the implementation of experiments and the discussion of the results. Finally, Section 5 represent the
conclusion.
Table 1. Literature review of some related works
Ref. Year Metaheuristic algorithm Localization technique Mean localize error
[8] 2009 PSO and BFA Anchor based-Range based PSO: 0.3
BFA: 0.2
[9] 2011 PSO and ABC Anchor based-Range based PSO: 25.3
ABC: 34.1
[10] 2011 DV distance and PSO Anchor based-Range based SAL: 21%
TSA: 14%
[11] 2012 PSO and HSPO Anchor based-Range based PSO: 0.184
HPSO: 0.138
[12] 2012 PSO Mobile Anchor Broadcasts Too many Results
[13] 2012 Genetic and ANN Anchor based-Range based RMSE is 0.41 meters
[14] 2012 Adaptive PSO Anchor based-Range based PSO DV-HOP: 0.38
[15] 2013 BBO and PSO Anchor based-Range based PSO: 0.33
BBO: 0.52
[16] 2014 PSO and Binary PSO Anchor based-Range based PSO: 0.109
BPSO: 0.122
[17] 2014 DV-hop based on Genetic Algorithm Anchor based-Range based DV-HOP: 8.8%
GADV: 6.5%
[18] 2015 PSO, Genetic and Firefly Algorithm (FA) Anchor based-Range based PSO: 0.1
GA: 0.4
FA: 0.8
[19] 2017 BOA and PSO Anchor based-Range based BOA: 0.21
PSO: 0.78
[20] 2017 PSO and GWO Anchor based-Range based PSO: 0.30
GWO: 0.658
[21] 2019 PSO and ABC Anchor based-Range based Too many results
2. METAHEURISTIC ALGORITHMS
This article will create a new algorithm that addresses the localization problem of different sensors
in the wireless sensor network using anchors nodes by combining several algorithms, namely PSO, GWO,
and SSA. Therefore, the pseudocodes for each algorithm are described in this section [22].

 ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 12, No. 1, February 2022: 660-668
662
2.1. Practical swarm optimization (PSO)
PSO is a computational approach that enhances a research problem by repeatedly attempting at a
given scale of quality to develop a candidate's solution concerning. It solves a difficulty by having a set of
particles and moving these particles in the search space according to easy mathematical equations on particle
position and velocity. Each particle's motion is influenced by its most prominent local location but is also
directed towards the best-known places in the search space, which are updated as other particles found more
suitable positions. The 𝑖th particle in the swarm can be denoted as 𝑝𝑖 = [𝑝𝑖1, 𝑝𝑖2, … , 𝑝𝑖𝑑] and its speed can be
denoted by vector 𝑆𝑖 = [𝑠𝑖1, 𝑠𝑖2, … , 𝑠𝑖𝑑]. Let the best location ever visited in the past by the ith particle be
denoted by 𝐿𝑖 = [𝐿𝑖1, 𝐿𝑖2, … , 𝐿𝑖𝑑]. After many times, the whole swarm is partitioned into more miniature sub-
swarm, and each sub-swarm has its own local best particle. Algorithm 1 introduces the pseudo code of PSO.
Algorithm 1. Pseudocode of PSO
1: Function Start
2: Generate initial population of m particles
3: While (t >Max_Gerneration)
4: Foreach m
5: measure fitness value
6: best_fitness = fBest
7: Current value = new_fBest
8: End Foreach_loop
9: Select m with fBest
10: Assign value = gBest
11: For each particle
12: Measure velocity
13: Set Position
14: End For_loop
15: End While_Loop
2.2. Butterfly optimization algorithm (BOA)
Arora and Anand [23] produced a metaheuristic algorithm based on a mathematical model, inspired
by nature, to find food for butterflies, and this is a good strategy for research, which is BOA. Butterflies use
sensory receptors to determine the source of their food/nectar. These sensory receptors, also called
chemoreceptors, can perceive smells and are scattered throughout a butterfly's body. Algorithm 2 introduces
the pseudo-code for BOA.
Algorithm 2. Pseudocode of BOA
1: Function Start
2: PoB = population of Butterflies
3: Set t := 0 (counter initialization)
4: While t >maximum counter do
5: Foreach x in PoB do
6: measure fitness function for x
7: End Foreach
8: Find best x
9: Foreach x in PoB do
10: n = random value from [0,1]
11: If n > t then
g = best solution
12: Move towards g
13: else
14: Move randomly
15: End If
16: Evaluate the fitness function
17: Assign and Update g
18: End Foreach
19: End While
20: Return g
21: End Function
2.3. Grey wolf optimization (GWO)
Mirjalili et al. [24] was developed a new algorithm also inspired by nature, but this algorithm
focuses on gray wolves' social behavior and this method is called GWO. The GWO method assumes the
management authority and hunting mechanism of gray wolves in nature. Four gray wolves, such as alpha,
beta, delta, and omega are adopted to assume leadership authority. Gray wolves remain in combinations of 5-
12 wolves. α, and are four gray wolf classes that follow a rigid common hierarchy. α is the authoritative wolf
between wolves who perform various decisions, attended by other yielding gray wolves. During the hunting
manner, the wolves can invest their victim in a way that can be mathematically represented as (1), (2):

663
𝐷
⃗
⃗ = |𝐶
⃗ . 𝑋𝑝
⃗⃗⃗⃗ − 𝑋(𝐿)
⃗⃗⃗⃗⃗⃗ | (1)
𝑋(𝐿+1)
⃗⃗⃗⃗⃗⃗⃗⃗⃗⃗ = |𝑋𝑝(𝐿)
⃗⃗⃗⃗⃗⃗⃗⃗ − 𝐴
⃗
⃗ . 𝐷
⃗
⃗ | (2)
The vectors coefficient named A and C can be demonstrated as (3), (4):
𝐴
⃗
⃗ = | 𝑟𝑎𝑛𝑑1
⃗⃗⃗⃗⃗⃗⃗⃗⃗⃗⃗⃗ . 2𝑎
⃗ − 𝑎
⃗ | (3)
𝐶
⃗ = 2 𝑟𝑎𝑛𝑑2
⃗⃗⃗⃗⃗⃗⃗⃗⃗⃗⃗⃗ (4)
2.4. Salp swarm algorithm (SSA)
Mirjalili et al. [25] proposed an algorithm inspired by the natural marine environment, called salp, to
solve the improvement problems with single or multiple goals. This work presents a new optimization
algorithm called the salp swarm algorithm (SSA) and the salp swarm multipurpose algorithm (MSSA), which
breeds crowds when navigating and foraging in the ocean. These two algorithms are examined on numerous
numerical optimization functions to control and confirm their effective operations in determining optimal
solutions to optimization difficulties. Figure 1 represents the SSA flowchart.
Figure 1. Flow chart of SSA
The mathematical function results show that the SSA algorithm can efficiently optimize the first
random solutions and concentrate on the better. To find out the leader's position, we suggest (5), and it can
also determine and update the leader's position [25]:
𝑥𝑗
1
= {
𝐹𝑗 + 𝑐1 ((𝑢𝑏𝑗 − 𝑙𝑏𝑗)𝑐2 + 𝑙𝑏𝑗) 𝑐3 ≥ 0
𝐹𝑗 − 𝑐1 ((𝑢𝑏𝑗 − 𝑙𝑏𝑗)𝑐2 + 𝑙𝑏𝑗) 𝑐3 < 0
(5)

 ISSN: 2088-8708
664
where 𝑥𝑗
1
shows the position of the first salp (leader) and 𝑐1, 𝑐2, and 𝑐3 are random numbers. As shown in (5)
shows that the leader only updates its position with respect to the food source.
𝑐1 = 2𝑒
− (
4𝑙
𝐿
)
2
(6)
Where L = max of iterations.
𝑥𝑗
𝑖
=
1
2
𝑎 𝑡2
+ 𝑣0𝑡 (7)
Considering 𝑣0 = 0, this equation can be expressed as (8):
𝑥𝑗
𝑖
=
1
2
(𝑥𝑗
𝑖
+ 𝑥𝑗
𝑖−1
) (8)
3. PROPOSED METHOD
Our method's principal objective is locating target IoT sensor nodes using nature-inspired methods
such as GWO, and SSA. Also, we need to estimate the greatest density of target nodes using precise
information about anchor or beacon nodes' position. The proposed algorithms are produced in algorithm 3
and algorithm 4, respectively.
Algorithm 3. Hybrid method (SSA and GWO)
Input: itmax, GWO population X, SSA
population Y, Size M, learning factors
C1,C2
Output: optimal solution
1: Function Start
2: for i=1 : M
3: for =1 : R
4: initialize SSA population Y
5: compute fitness for each agent
6: chaotic sequence Generation
7: End for (j)
8: End for (i)
9: for t = 1 : itmax
10:for i=1 : M
11: for j=1 : R
12: compute 𝒙𝒋
𝟏
, 𝑫𝜶
⃗⃗⃗⃗⃗ , 𝑫𝜷
⃗⃗⃗⃗⃗ , 𝑫𝜹
⃗⃗⃗⃗⃗
13: compute 𝒘𝟏, 𝒘𝟐, 𝒘𝟑
14: compute 𝒙𝒊𝒃𝒆𝒔𝒕
15: update position and velocity
16: End for (j)
17: End for (i)
18: Compute value of fitness function and
19: Update values of 𝜶, 𝜷, 𝜹
Algorithm 4. Proposed method
Input: Unknown Nodes, Anchor Nodes and
Communication Range (R)
Output: Localized Nodes and Error Rates
1: Procedure Start
2: Randomly Initialize target nodes with
unknown position
3: Randomly Initialize anchor nodes with
known position
4: For each anchor node (i) with R do
5: Calculate the distance from target
node
(x,y)and anchor nodes within R
𝒅𝒊 = √(𝒙 − 𝒙𝒊)𝟐 + (𝒚 − 𝒚𝒊)𝟐
6: Calculate Objective Function
𝒇(𝒙, 𝒚) = 𝒎𝒊𝒏 ∑ (√(𝒙 − 𝒙𝒊)𝟐 + (𝒚 − 𝒚𝒊)𝟐)𝟐
𝑴
𝒊=𝟏
7: Calculate Localization Error
𝑬𝒍 =
𝟏
𝑵𝒍
∑ √(𝒙𝒊 − 𝑿𝒊)𝟐 + (𝒚𝒊 − 𝒀𝒊)𝟐
𝒍
𝒊=𝟏
8: If all Target Node get localized
9: Break
10: Else
11: Continue
12:End For
4. RESULTS AND DISCUSSION
4.1. Environmental parameters
All the measurements of experiments for the three algorithms (PSO, BOA, and proposed algorithm)
are implemented using R2019b version of MATLAB on a platform of Windows 10 operating system, Intel
Core i7 CPU, and RAM 16 GB. The factors’ values of the environment area are displayed in Table 2.
Table 2. Environmental parameters
Factors Values
Target nodes (i)
∑ 𝑖 ∗ 2
4
𝑖=1
5
Anchor or beacon nodes (b) 𝑡𝑎𝑟𝑔𝑒𝑡 𝑛𝑜𝑑𝑒𝑠/4
Range of Node transmission (R) 30 m
Environment Area (A) 100 m*100 m
Iteration Numbers (t) 100

665
4.2. Experimental results
Many experiments are conducted through this paper. PSO algorithm is implemented with 7, 13 and
19 anchors and with 25, 50 and 75 target nodes as shown in Figure 2. Also, BOA algorithm is implemented
with 7, 13 and 19 anchors and with 25, 50 and 75 target nodes as shown in Figure 3. Finally, proposed hybrid
algorithm is implemented with 7, 13 and 19 anchors and with 25, 50 and 75 target nodes as shown in Figure 4.
(a) (b) (c)
Figure 2. Experiment 1 using PSO: (a) results of 7 anchors and 25 target nodes, (b) results of 13 anchors and
50 target nodes, (c) results of 19 anchors and 75 target nodes
(a) (b) (c)
Figure 3. Experiment 2 using BOA: (a) results of 7 anchors and 25 target nodes, (b) results of 13 anchors and
50 target nodes, (c) results of 19 anchors and 75 target nodes
(a) (b) (c)
Figure 4. Experiment 3 using proposed GWO and SSA: (a) results of 7 anchors and 25 target nodes,
(b) results of 13 anchors and 50 target nodes, (c) results of 19 anchors and 75 target nodes

 ISSN: 2088-8708
666
The results of the above experiments using 7, 13, 19, 25 anchors and 25, 50, 75 and 100 target nodes
are displayed in Table 3. Error of localized node in meter (EL(m)), Time in seconds (Ts) and number of
localized nodes (NL) are displayed also in Table 3. We found form Table 3 that the proposed algorithm
achieved highest NL and lowest EL than other related works.
4.3. Comparison between proposed algorithm and other related works
According to the results shown in Tables 3 and 4, we found that the proposed method using the
hybrid optimization algorithms (SSA and GWO) achieved higher accuracy and lowest error than other related
works. Also, we found that the proposed method achieved low error rate with high number of localized
nodes. The error rate (m) and time consumption (s) between proposed method and other related works are
represented in Figures 5 and 6 respectively.
Table 3. Results of applying the various localization algorithms where E=Error, T=Time and N=number of
localized nodes
Target nodes Anchor nodes PSO BOA Proposed Algorithm
EL(m) T(s) NL EL(m) T(s) NL EL(m) T(s) NL
25 7 0.25 0.4 19 0.1 0.3 22 0.04 0.3 24
50 13 0.08 0.7 46 0.02 0.6 49 0.001 0.5 50
75 19 0.04 0.9 72 0.01 0.8 74 0.001 0.6 75
100 25 0.1 1.3 91 0.05 0.9 95 0.01 0.7 99
Table 4. Comparison between proposed method and other related works
Reference Method Type Error (m)
[18] PSO, Genetic and firefly algorithm (FA) Anchor based-Range based PSO: 0.1
GA: 0.4
FA: 0.8
[19] BOA and PSO Anchor based-Range based BOA: 0.21
PSO: 0.78
[20] PSO and GWO Anchor based-Range based PSO: 0.30
GWO: 0.658
Proposed Method SSA and GWO Anchor based-Range based 0.01
A labeled for Anchors and T labeled for Target A labeled for Anchors and T labeled for Target
Figure 5. Error chart in meters for each localization
algorithm in different experiments
Figure 6. Time chart in seconds for each localization
algorithm in different experiments
0.25
0.08
0.04
0.1
0.1
0.02
0.01
0.05
0.04
0.001
0.001
0.01
7 A A ND 25
T
1 3 A A ND
50 T
19 A A ND
75 T
25 A A ND
100 T
ERROR (M)
PSO BOA Proposed
0
0.2
0.4
0.6
0.8
1
1.2
1.4
7 A A ND
25 T
13 A A ND
50 T
19 A A ND
75 T
25 A A ND
1 0 0 T
TIME (S)
PSO BOA Proposed

667
5. CONCLUSION
In this article, hybrid localization algorithm based on dynamics inspired algorithms (SSA, and
GWO) has been proposed and treats node location as an optimization dilemma. The suggested method has
been performed and verified in different WSN deployments using various target nodes and beacon nodes.
Besides, the proposed algorithm was assessed and compared with known optimization methods, namely PSO
and BOA, concerning localization accuracy, computing time and the number of local nodes. The proposed
method achieved high accuracy with lower error rate (0.001) and localized high number of IoT nodes.
REFERENCES
[1] R. Sharma, S. Prakash, and P. Roy, “Methodology, applications, and challenges of WSN-IoT,” 2020 International Conference on
Electrical and Electronics Engineering (ICE3), 2020, pp. 502-507, doi: 10.1109/ICE348803.2020.9122891.
[2] Z. Vatansever, M. Brandt-Pearce, and N. Bezzo, “Localization in optical wireless sensor networks for IoT applications,” ICC
2019 - 2019 IEEE International Conference on Communications (ICC), 2019, pp. 1-6, doi: 10.1109/ICC.2019.8761909.
[3] P. Beuchat, H. Hesse, A. Domahidi, and J. Lygeros, “Optimization based self-localization for IoT wireless sensor networks,”
2018 IEEE 4th World Forum on Internet of Things (WF-IoT), 2018, pp. 712-717, doi: 10.1109/WF-IoT.2018.8355120.
[4] N. A. Hikal and M. M. El-Gayar, “Enhancing IoT botnets attack detection using machine learning-IDS and ensemble data
preprocessing technique,” Internet of Things-Applications and Future, vol. 114, pp. 89-102, 2020, doi: 10.1007/978-981-15-3075-
3_6.
[5] M. M. El-Gayar, N. E. Mekky, A. Atwan, and H. Soliman, “Enhanced search engine using proposed framework and ranking
algorithm based on semantic relations,” IEEE Access, vol. 7, pp. 139337-139349, 2019, doi: 10.1109/ACCESS.2019.2941937.
[6] N. A. Lafta and S. S. Hreshee, “Wireless sensor network’s localization based on multiple signal classification algorithm,”
International Journal of Electrical and Computer Engineering (IJECE), vol. 11, no. 1, pp. 498-507, 2021, doi:
10.11591/ijece.v11i1.pp498-507.
[7] B. Mostafa, C. Saad, and H. Abderrahmane, “Firefly algorithm solution to improving threshold distributed energy efficient
clustering algorithm for heterogeneous wireless sensor networks,” IAES International Journal of Artificial Intelligence (IJ-AI),
vol. 6, no. 3, pp. 91-99, 2017, doi: 10.11591/ijai.v6.i3.pp91-99.
[8] R. V. Kulkarni, G. K. Venayagamoorthy, and M. X. Cheng, “Bio-inspired node localization in wireless sensor networks,” 2009
IEEE International Conference on Systems, Man and Cybernetics, 2009, pp. 205-210, doi: 10.1109/ICSMC.2009.5346107.
[9] D. Lavanya and S. K. Udgata, “Swarm intelligence based localization in wireless sensor networks,” International Workshop on
Multi-disciplinary Trends in Artificial Intelligence, vol. 7080, 2011, pp. 317-328, doi: 10.1007/978-3-642-25725-4_28.
[10] P. H. Namin and M. A. Tinati, “Node localization using particle swarm optimization,” 2011 Seventh International Conference on
Intelligent Sensors, Sensor Networks and Information Processing, 2011, pp. 288-293, doi: 10.1109/ISSNIP.2011.6146558.
[11] A. Kumar, A. Khosla, J. S. Saini, and S. Singh, “Meta-heuristic range based node localization algorithm for wireless sensor
networks,” 2012 International Conference on Localization and GNSS, 2012, pp. 1-7, doi: 10.1109/ICL-GNSS.2012.6253135.
[12] H. Bao, B. Zhang, C. Li, and Z. Yao, “Mobile anchor assisted particle swarm optimization (PSO) based localization algorithms
for wireless sensor networks,” Wireless Communications And Mobile Computing, vol. 12, no. 15, pp. 1313-1325, 201, doi:
10.1002/wcm.1056.
[13] S. H. Chagas, J. B. Martins, and L. L. De Oliveira, “An approach to localization scheme of wireless sensor networks based on
artificial neural networks and Genetic Algorithms,” 10th IEEE International NEWCAS Conference, 2012, pp. 137-140, doi:
10.1109/NEWCAS.2012.6328975.
[14] Y. Gao, W. S. Zhao, C. Jing, and W. Z. Ren, “WSN node localization algorithm based on adaptive particle swarm optimization,”
Applied Mechanics and Materials, vol. 143-144, pp. 302-306, 2012, doi: 10.4028/www.scientific.net/AMM.143-144.302.
[15] S. Singh, S. Shivangna, and E. Mittal, “Range based wireless sensor node localization using PSO and BBO and its variants,” 2013
International Conference on Communication Systems and Network Technologies, 2013, pp. 309-315, doi:
10.1109/CSNT.2013.72.
[16] I. F. M. Zain and S. Y. Shin, “Distributed localization for wireless sensor networks using binary particle swarm optimization
(BPSO),” 2014 IEEE 79th Vehicular Technology Conference (VTC Spring), 2014, pp. 1-5, doi:
10.1109/VTCSpring.2014.7022886.
[17] B. Peng and L. Li, “An improved localization algorithm based on genetic algorithm in wireless sensor networks,” Cognitive
Neurodynamics, vol. 9, no. 2, pp. 249-256, 2015, doi: 10.1007/s11571-014-9324-y.
[18] D. Chandirasekaran and T. Jayabarathi, “A case study of bio-optimization techniques for wireless sensor network in node location
awareness,” Indian Journal of Science and Technology, vol. 8, no. 31, pp. 1-9, Nov. 2015, doi: 10.17485/ijst/2015/v8i31/67726.
[19] S. Arora and S. Singh, “Node localization in wireless sensor networks using butterfly optimization algorithm,” Arabian Journal for
Science and Engineering, vol. 42, no. 8, pp. 3325-3335, 2017, doi: 10.1007/s13369-017-2471-9.
[20] R. Rajakumar, J. Amudhavel, P. Dhavachelvan, and T. Vengattaraman, “GWO-LPWSN: Grey wolf optimization algorithm for
node localization problem in wireless sensor networks,” Journal of Computer Networks and Communications, vol. 2017, 2017,
Art. no. 7348141, doi: 10.1155/2017/7348141.
[21] K. P. Lakshmishree and M. B. Nirmala, “Localization in wireless sensor networks with optimization and security schemes-a
review,” 2018 Second International Conference on Intelligent Computing and Control Systems (ICICCS), 2019, pp. 1428-1433,
doi: 10.1109/ICCONS.2018.8663162.
[22] V. Annepu and A. Rajesh, “Implementation of self adaptive mutation factor and cross-over probability based differential
evolution algorithm for node localization in wireless sensor networks,” Evolutionary Intelligence, vol. 12, no. 3, pp. 469-478,
2019, doi: 10.1007/s12065-019-00239-0.
[23] S. Arora and P. Anand, “Binary butterfly optimization approaches for feature selection,” Expert Systems with Applications,
vol. 116, pp. 147-160, 2019, doi: 10.1016/j.eswa.2018.08.051.
[24] S. Mirjalili, S. M. Mirjalili, and A. Lewis, “Grey wolf optimizer,” Advances in Engineering Software, vol. 69, pp. 46-61, 2014,
doi: 10.1016/j.advengsoft.2013.12.007.
[25] S. Mirjalili, A. H. Gandomi, S. Z. Mirjalili, S. Saremi, H. Faris, and S. M. Mirjalili, “Salp swarm algorithm: A bio-inspired
optimizer for engineering design problems,” Advances in Engineering Software, vol. 114, pp. 163-191, 2017, doi:
10.1016/j.advengsoft.2017.07.002.

 ISSN: 2088-8708
668
BIOGRAPHIES OF AUTHORS
Rana Jassim Mohammed University of Diyala. Rana J. Mohammed received her
B.E. degree in Computer Science from the University of Diyala in 2006, her M.Sc. degree
Computer Science from University of Diyala in 2019. She is currently a lecturer in Diyala
University, Iraq. Her current research interests cover pre-processing security and
authentication in mobile. She can be contacted at email: ad.ranamohammed@uodiyala.edu.iq.
Enas Abbas Abed University of Diyala. Enas A. Abed received her B.E. degree
in Computer Engineering from the University of Diyala in 2005, her M.Sc. degree in
Information System from Egypt/Banha University in 2018. She is currently a lecturer in Diyala
University, Iraq. Her current research interests Information Retrieval, image processing, and
Artificial intelligence. She can be contacted at email: sc_enasabed@uodiyala.edu.iq.
Mostafa Mahmoud Elgayar received the B.Sc., M.Sc., and Ph.D. degrees in
information technology from Mansoura University, Mansoura, Egypt, in 2010, 2013 and 2019,
respectively. Since 2013, he has been a Teaching Assistant with the Faculty of Computer and
Information Science, Mansoura University. His research interests include wireless sensor
network, semantic web, algorithms, big data, security, and pattern recognition. He can be
contacted at email: mostafa_elgayar@mans.edu.eg.

Comparative study between metaheuristic algorithms for internet of things wireless nodes localization

More Related Content

What's hot (19)

Similar to Comparative study between metaheuristic algorithms for internet of things wireless nodes localization (20)

More from IJECEIAES (20)

Recently uploaded (20)

Comparative study between metaheuristic algorithms for internet of things wireless nodes localization