Submit to this Journal Review for this Journal Propose a Special Issue

Article Menu

Share Help Cite Discuss in SciProfiles

Open AccessArticle

Peer-Review Record

A Compact Bat Algorithm for Unequal Clustering in Wireless Sensor Networks

Appl. Sci. 2019, 9(10), 1973; https://doi.org/10.3390/app9101973

by Trong-The Nguyen^1,2,3

, Jeng-Shyang Pan^1,4,5,* and Thi-Kien Dao^1,3,*

Reviewer 1: Anonymous

Reviewer 2: Anonymous

Appl. Sci. 2019, 9(10), 1973; https://doi.org/10.3390/app9101973

Submission received: 6 April 2019 / Revised: 2 May 2019 / Accepted: 7 May 2019 / Published: 14 May 2019

(This article belongs to the Section Computing and Artificial Intelligence)

Round 1

Reviewer 1 Report

Here are more focused comments on the work entitled "A Compact Bat Algorithm for Unequal Clustering in Wireless Sensor Networks"

The comparison between cBA and cPSO algorithms does not seem decisive, because of the proximity of their efficiency (see Tables 3 for example).
The proposed results, in particular in Table 6, do not present any vision of application.

Clustering algorithms have gained more importance, in increasing the life time of the WSN, because of their approach in cluster head selection and data aggregation.
An important missing point in this work concerns the study of essential parameters in the WSNs such as the efficient use of energy, the lifetime of the network and the environmental conditions.

It would also be interesting for the authors to compare their algorithm more seriously with two important clustering protocols, namely LEACH and LEACH C.

For all these reasons, I consider that this work lacks originality and offers no realistic application.

Author Response

The authors would like to thank the reviewers for their constructive criticism, useful comments, and new insights. The suggested revisions have been addressed and embedded in the revised manuscript. As indicated in our revision notes included below, we have incorporated responses to all comments and suggestions made by reviewers. For details, please refer to the responses as follows: reviewers’ comments are in italic Times New Roman fonts; authors’ responses are in Times New Roman fonts while changes in the revised manuscript and this document are marked with green color. Proofreading changes are noted in red.

Reviewer#1 (Full comment):

Here are more focused comments on the work entitled "A Compact Bat Algorithm for Unequal Clustering in Wireless Sensor Networks"

1) The comparison between cBA and cPSO algorithms does not seem decisive, because of the proximity of their efficiency (see Tables 3 for example).

2) The proposed results, in particular in Table 6, do not present any vision of application.

3) Clustering algorithms have gained more importance, in increasing the life time of the WSN, because of their approach in cluster head selection and data aggregation. An important missing point in this work concerns the study of essential parameters in the WSNs such as the efficient use of energy, the lifetime of the network and the environmental conditions.

4) It would also be interesting for the authors to compare their algorithm more seriously with two important clustering protocols, namely LEACH and LEACH C.

---------------------------------------------------------------------------

Reviewer#1:

1) The comparison between cBA and cPSO algorithms does not seem decisive, because of the proximity of their efficiency (see Tables 4 for example).

Authors’ response:

The authors much appreciate the constructive criticism of the Reviewer#1. We completely agree that the comparison between cBA and cPSO algorithms does not seem decisive, because of the proximity of their efficiency (see Tables 4 for example).

PSO is a popular metaheuristic algorithm, and its applications have been successful in many fields. PSO also has evolved with some versions included cPSO. However, the comparison cBA with cPSO, and the other algorithms are conducted in our manuscript that said the proposed cBA is like the evolution of different algorithms based on a theorem of "No free lunch"; said that there is no meta-heuristic algorithm best suited for solving all optimization problems.

In the revised manuscript, we modified Section 1 and added motivation based on the law of No free lunch.

Furthermore, one of our motivations in doing this paper based on a theorem of "No free lunch" said that there is no meta-heuristic algorithm best suited for solving all optimization problems [19]. It means that one algorithm might obtain excellent results on a given set of challenges but underperform on an alternative set of the issues. The other our motivations in this paper are to consider the relative points of strength of different algorithms based on the types and properties of the problem.

Reference:

[19] D. H. Wolpert and W. G. Macready, “No free lunch theorems for optimization,” IEEE Trans. Evol. Comput., vol. 1, no. 1, pp. 67–82, 1997.

Moreover,

-------------------------------------------

Reviewer#1:
2) The proposed results, in particular in Table 7, do not present any vision of application.

Authors’ response:

We would like to sincerely thank Reviewer#1 for careful reading of the manuscript. The authors much appreciate the constructive comment of the Reviewer#1.

Our manuscript proposed cBA focusing on dealing with Unequal clustering problem in WSN. For overview a whole picture the of the clustering formation issue in WSN, we have implemented both the equal clustering and unequal clustering for further emphasizing our focus unequal clustering issue one.

Table 7 shows the comparison of averaged outcomes and running time of cBA with the oBA, PSO-TVAC, and PSO-TVIW methods for equal clustering formation.

-------------------------------------------------------------

Reviewer#1:
3) Clustering algorithms have gained more importance, in increasing the life time of the WSN, because of their approach in cluster head selection and data aggregation. An important missing point in this work concerns the study of essential parameters in the WSNs such as the efficient use of energy, the lifetime of the network and the environmental conditions.

Authors’ response:

We are thankful to Reviewer#1 much for careful reading of the manuscript and meaningful insights on the flaws of our original paper. However, we would like to explain in detail about this issue as follows.

One of the solutions to both the equal and unequal clustering issues is to optimize the objective function as in Eq.(22).

This equation is a multi-objective function for the equal clustering formation that included functions f1 as in Eq.(19) and f2 as in Eq.(21). The f1(x) is for optimizing the selection CHs based on energy residual, and the f2(x) is for optimizing the factor related distances that affected the energy consumption of sensor nodes.

For the unequal clustering problem is also to use the objective function in Eq.(22); however, two parameters should be adjusted, e.g., the distance of CHs to Base station (BS) refers to Eq.(23), and loudness of Bat algorithm refers to Eq.(25).

-----------------------------------------------------

Reviewer#1:
4) It would also be interesting for the authors to compare their algorithm more seriously with two important clustering protocols, namely LEACH and LEACH C.

Authors’ response:

We want to thank sincerely Reviewer#1 for this suggestion. The authors much appreciate the constructive comment of the Reviewer#1.

We have considered adding suggested comparison with LEACH-C. We would like to explain in detail about this issue. Low-Energy Adaptive Clustering Hierarchy (LEACH) [22] is a clustering protocol that is to select sensor nodes randomly as CHs based on probability as a "threshold" parameter. LEACH-Centralized (LEACH-C) [23] based on LEACH with Base station (BS) uses a specific method to select the CH and divide the nodes to clusters which can offer more optimization; it means network lifetime longer than LEACH. The setting parameters for two added approaches for the sensor node and WNS refer to subsections 5.2 and 5.3. The obtained outcomes of the approaches are compared with each other in Figure 7.

Figure 7 shows a comparison of the advanced cBA-WSN with other methods, e.g., PSO-TVAC, PSO-TVIW, the Low-Energy Adaptive Clustering Hierarchy (LEACH) [22], and LEACH-Centralized (LEACH-C) [23] approaches regarding the number of nodes alive. LEACH is a clustering protocol that is to select sensor nodes randomly as CHs based on probability as a "threshold" parameter. LEACH-C is another version based on LEACH with Base station (BS) uses a specific method to select the CH and divide the nodes to clusters which can offer more optimization; it means network lifetime longer than LEACH.

Reference:

[22] W. B. Heinzelman, A. P. Chandrakasan, and H. Balakrishnan, “An application-specific protocol architecture for wireless microsensor networks,” IEEE Trans. Wirel. Commun., vol. 1, no. 4, pp. 660–670, 2002.

[23] W. B. Heinzelman, “Application-specific protocol architectures for wireless networks.” Massachusetts Institute of Technology, 2000.

------------------------------

Author Response File: Author Response.pdf

Reviewer 2 Report

This paper presented a new optimization algorithm which enhanced the existing Bat Algorithm (cBA) to reduce energy consumption.

The new algorithm has been applied in a real case study to find a solution for the Unequal clustering problem in Wireless Sensor Networks (WSN)

This topic is very interesting and it is studied by the authors with a rigorous approach

In addition, it fits well the main goal \ topics of the journal.

It will be interesting to investigate the potential of the algorithm in other real cases.

However, in order to show the contribution of this paper more clearly, the authors should provide a comparison to other analogs existing approaches published in the literature, and explain better the advantages of the proposal, anticipating briefly the outcomes reported in Section 4 and 5.

Moreover, the authors should specify their contribution to extend a previous work of the same authors on "compact Bat algorithm. (This work is referenced by [2] in the article.)

Finally, in order to enhance the quality of the paper, these following comments should be addressed by the authors:

-) Introduction should better clarify the goal of the paper

-) The English of the paper should be improved; Authors should also check typos (e.g. "forawd" at row 204)

-) It is not clear why the authors report in subsection 2.2 (which is a subsection of the section Related Work) a series of formulas. Are these formulas derived from another study?

In addition, all these formulas should be better explained (in general all the formulas that appear in the article).

Without further explanations, it is hard to check these formulas, even the methodological approach seems correct.

-) The sentences in the rows from 175 to 181 are not clear; thus, it is jeopardized the possibility for the readers to understand the key features of CBat compared to Bat.

-) At row 294, the references should be reported for algorithms rcGA, cDE, and cPSO.

-) The authors should verifiy the numbers referring to the figures add tables (e.g. table 4 at row 295 and figues 12, 13 and 14 at row 306)

-) The authors should enhance the explanation of Table 3 (rows 295-300)

-) At row 311, likely it is better to write "In designing and deploying sensor networks, prolonging the lifetime is a core demand. "

Author Response

Authors’ response:

We appreciate this suggestion made by Reviewer#2.

The authors pasted and attached the response as follows

Reviewer#2:

1) This topic is very interesting and it is studied by the authors with a rigorous approach

In addition, it fits well the main goal \ topics of the journal.

It will be interesting to investigate the potential of the algorithm in other real cases.

Authors’ response:

We would like to sincerely thank Reviewer#2 for careful reading of our manuscript and the constructive comments.

The authors greatly appreciate the positive comments about the topic and applicability of the manuscript.

----------------------------------------------------------

Reviewer#2:

2) In order to show the contribution of this paper more clearly, the authors should provide a comparison to other analogs existing approaches published in the literature, and explain better the advantages of the proposal, anticipating briefly the outcomes reported in Section 4 and 5.

Moreover, the authors should specify their contribution to extending a previous work of the same authors on "compact Bat algorithm. (This work is referenced by [2] in the article.)

Authors’ response:

We appreciate this suggestion made by Reviewer#2. The authors checked the entire section and explained in more detail the necessary paragraphs about contribution and originality:

The contributions to extending a previous work (of the same authors), on "compact Bat algorithm" [2] are explained as follows. Our previous work "compact Bat algorithm" [2] is a version of Bat algorithm for the numerical optimization. It was proposed based on sampling the probability for representing the solution of a swarm agent search. However, its application is not flexible.

Our manuscript is extended compact BA that has some contributions:

1. A parameter ω is used as a weight to control the probability of sampling of generating a new solution that is sampling points toward the left or right size (Subsection 3.2, line 222-227 in the manuscript).

2. A new application of the proposed cBA for the unequal clustering formation in WSN (Section 5 in the document).

3. Extensive testing is not only for the monomial problems but also for multimodal global optimization problems through series selected benchmark functions (Section 4 in the manuscript).

4. Comprehensive comparison with the other version of Bat algorithm, the compact algorithms in the literature, and the clustering approach in WSN (Sections 4 and 5 in the manuscript).

In the revised manuscript, we modified section 1 and added motivation

Section 1 (Introduction)

Furthermore, one of our motivations in this paper based on a theorem of "No free lunch" said that there is no meta-heuristic algorithm best suited for solving all optimization problems [19]. It means that one algorithm might obtain excellent results on a given set of challenges but underperform on an alternative set of the issues. The other our motivations in this paper are to consider the relative points of strength of different algorithms based on the types and properties of the problem.

In this paper, we extend our previous work of compact Bat algorithm (cBA)[2] for the unequal clustering of Wireless sensor networks (uWSN) problems. Extending work aims to deal with the issues of saving variable memory and selecting parameters according to the unequal clustering problem of WSNs. The logic behind extending work includes an added weight to control the probability of sampling for perturbation vector, a set of tests for benchmark functions, a solution to unequal clustering problem, and extensive comparison with the other compact algorithms in the literature. A real-valued prototype vector is maintained the probabilistic operations to generate each candidate for the solution of optimization cBA. The proposed cBA is extensively evaluated on several continues multimodal functions as well as the unequal clustering of Wireless sensor networks (uWSN) problems.

Moreover, in Section 5 (for Clustering in WSNs problem) is revised as follows:

Figure 7. Comparison of advanced cBA-WSN for the number of nodes alive of WSNs with PSO-TVAC, PSO-TVIW, LEACH, and LEACH-C approaches

Figure 7 shows a comparison of the advanced cBA-WSN with other methods, e.g.PSO-TVAC, PSO-TVIW, the Low-Energy Adaptive Clustering Hierarchy (LEACH) [22], and LEACH-Centralized (LEACH-C) [23] approaches regarding the number of nodes alive. LEACH is a clustering protocol that is to select sensor nodes randomly as CHs based on probability as a "threshold" parameter. LEACH-C is another version based on LEACH with Base station (BS) uses a specMỏific method to select the CH and divide the nodes to clusters which can offer more optimization; it means network lifetime longer than LEACH. Observably, it is clear that the number of alive nodes of the proposed cBA-WSN is the longest. It means that the resulting figure of the proposed cBA-WSN for the testing functions and clustering problem in WSN is better than the other methods in the comparisons.

-------------------------------------------------------------------.

Reviewer#2:

3) Finally, in order to enhance the quality of the paper, these following comments should be addressed by the authors:

-) Introduction should better clarify the goal of the paper

-) The English of the paper should be improved; Authors should also check typos (e.g. "forawd" at row 204)

Authors’ response:

We are thankful to Reviewer#2 for the suggestion. The authors checked the entire text for possible grammar and syntax errors. Found errors are corrected, and the changes are marked with red color in the revised manuscript.

In the revised manuscript, we modified section 1 and added motivation

Section 1 (Introduction)

An example of the changes marked with red:

Table 4 depicts the comparison the outcomes of the proposed algorithm with the other compact algorithms such as cPSO [30], cDE[31], and rcGA[32] for 10 test functions.

--------------------------------------------------------

Reviewer#2:

3) ..

-) It is not clear why the authors report in subsection 2.2 (which is a subsection of the section Related Work) a series of formulas. Are these formulas derived from another study?

In addition, all these formulas should be better explained (in general all the formulas that appear in the article).

Without further explanations, it is hard to check these formulas, even the methodological approach seems correct.

Authors’ response:

The authors much appreciate the constructive comment of the Reviewer#2. A series of formulas is related to the energy consumption of sensor nodes that affected to performance of entire WSN. Yes, these formulas derived from our previous work [16].

In the manuscript, subsection 2.2 of Energy Consumption Model was further explained.

2.2. Energy Consumption in WSNs model

Unequal Clustering in WSN with hundreds or thousand sensor nodes is an efficient way of organizing such a vast number of nodes, uniformly distributed load and eliminating hotspot problem [24]. In contrast, equal clustering, the size of the cluster is the same throughout the network. Admittedly, in unequal clustering, the cluster size is determined based on the length to BS. The cluster size is smaller when the distance to BS is shorter, and the size increases as the distance to BS increases.

The wireless radio transceiver in WSN depends on the various parameters, e.g., distances, energy consumption. The definition related to the power consumed, and ranges of the nodes referred to in [16] [24]. The distance between the transmitter and receiver obeyed on the attenuated trans-receiving power decreased exponentially with the increasing distance. A threshold separated the free space model and the multipath model.

References:

16] T.-T. Nguyen, T.-K. Dao, M.-F. Horng, and C.-S. Shieh, “An Energy-based Cluster Head Selection Algorithm to Support Long-lifetime in Wireless Sensor Networks,” J. Netw. Intell., vol. 1, no. 1, pp. 23–37, 2016.

----------------------------------------------------------------

Reviewer#2:

3) ..

-) The sentences in the rows from 175 to 181 are not clear; thus, it is jeopardized the possibility for the readers to understand the key features of cBat compared to Bat.

Authors’ response:

We want to thank Reviewer#2 for this insight. Following the reviewer’s suggestion, we tried to clarify the paragraphs.

In the revised manuscript, we modified the paragraph.

A real-valued prototype vector is used to maintain sampling probabilistic for generating components of a candidating solution randomly. This vector operates distributedly based on the estimated distribution algorithm (EDA)[26]. Because of a few new generating candidates stored in remembrance, it is not all of the population of solutions stored in memory. The likelihood of the estimated distribution would trend driving new candidate forward to the fitness function.

---------------------------------------------------------------------------

Reviewer#2:

3) ..

-) At row 294, the references should be reported for algorithms rcGA, cDE, and cPSO.

-) At row 311, likely it is better to write "In designing and deploying sensor networks, prolonging the lifetime is a core demand. "

Authors’ response:

We appreciate the suggestion of Reviewer# 2. The authors added citations of the rcGA [32], cDE[31], and cPSO[30] algorithms.

In the revised manuscript:

Table 4 depicts the comparison the outcomes of the proposed algorithm with the other compact algorithms such as cPSO [30], cDE[31], and rcGA[32] for 10 test functions. Apparently, cBA outperforms its competitors regarding convergence. The best results in among them for each function highlighted in rows. The performance of compared ratio r is set for each pair of comparisons of cBA with the cPSO, cDE, and rcGA respectively. The symbol of ‘+’, ‘- ‘and ‘~’ mean the ‘better,' ‘worse,' and ‘approximation’ of the deviation of the outcomes respectively. If the averaged outcomes obtained of 25 runs for the optimized function of cBA is the better than the cPSO, cDE, and rcGA, then r is set symbol ‘+.' The same with symbols “~” and “-” for the worse, and approximation are applied to the cases respectively. It would be seen that almost the highlighted cases of testing functions belong to the proposed cBA. It said that the proposed approach outperforms the other methods in this table. According to Figure 4, the curve of the cBA displays a comparatively better in convergence behavior on the selected test functions.

References:

[30] F. Neri, E. Mininno, and G. Iacca, “Compact particle swarm optimization,” Inf. Sci. (Ny)., vol. 239, pp. 96–121, 2013.

[31] E. Mininno, F. Neri, F. Cupertino, and D. Naso, “Compact differential evolution,” IEEE Trans. Evol. Comput., vol. 15, no. 1, pp. 32–54, 2011.

[32] G. R. Harik, F. G. Lobo, and D. E. Goldberg, “The compact genetic algorithm,” IEEE Trans. Evol. Comput., vol. 3, no. 4, pp. 287–297, 1999.

5. Experiments for Clustering in WSNs problem

In designing and deploying sensor networks, prolonging the lifetime is a core demand.

------------------------------------------------

Review #2

-) The authors should verifiy the numbers referring to the figures add tables (e.g. table 4 at row 295 and figues 12, 13 and 14 at row 306)

Authors’ response:

We would like to sincerely thank Reviewer#2 for careful reading of our manuscript and the constructive comments.

The authors verified the entire text for possible grammar and syntax errors. The changes are marked with red color in the revised manuscript.

For example:

------------------------------------------

Reviewer#2:

3) ..

-) The authors should enhance the explanation of Table 3 (rows 295-300)

Authors’ response:

We want to thank Reviewer#2 for the suggestion sincerely. The authors enhanced the explanation of Table 3 in the revised manuscript with green color.

Table 3 shows the comparison of proposed cBA with the oBA in terms of the occupied memory variables for implementing computations in running optimization. The number of variables of the two algorithms is counted for through the number of the equations used in operations optimization. Observed table 3 would clearly be seen that the number of variables of cBA use is smaller than the oBA with the same condition of computation, e.g., iterations. The number equations of oBA are four, e.g., (8),(9),(10),and (11) and the figure of cBA is eight, e.g., (8),(9),(10),(11), (15),(16), (17), and (18).

However, the real population or population size of oBA is N, and cBA is only one. With the same number of iteration and the number running time T, the stored slots of variables of oBA and cBA are 4×T×N×iteration, and 8×T×iteration respectively, where T and N are the counting run time and the number of population. It can be seen the figure of the occupied slots for oBA is higher N/2 times than that for cBA.

Table 3. Comparison of the number of variables for occupied memory slots for in the cBA and oBA

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

There is a "typo" at the end of line 45: instead of " wireless sensor work ", write " wireless sensor network".

This manuscript has been greatly improved. However, the authors must provide the following additional information about the applications of WSN's (in the introduction just before the end of line 48, and more precisely after "... single hop [16]."):

WSN's detect and measure (or monitor) a number of physical or environmental conditions such as multimedia [17, 18], infrared energy emitted from object and converts it to temperature [19], pollutant levels [20], ultrasound in medical imaging [21], vibrations [22], security and surveillance [23], agriculture [24] and many other such conditions.

[17] W. Liu, K. R. Vijayanagar, J. Kim, "Low-complexity distributed multiple description coding for wireless video sensor networks", Wireless Sensor Systems IET, vol. 3, no. 3, pp. 205-215, 2013.

[18] I. T. Almalkawi, M. G. Zapata, J. N. Al-Karaki, J. Morillo-Pozo “Wireless Multimedia Sensor Networks: current trends and future directions.” Sensors, vol. 10, no. 7, pp. 6662-717. 2010.

[19] D. Ait Aouit and A. Ouahabi, “ Monitoring crack growth using thermography”, Comptes Rendus Mécanique, Vol. 336, no. 8, pp. 677-683, 2008.

[20] D. M. Broday, Citi-Sense Project Collaborators. “Wireless Distributed Environmental Sensor Networks for Air Pollution Measurement-The Promise and the Current Reality.”, Sensors, vol.17, no.10, 2263, 2017.

[21] M. Djeddi, A. Ouahabi, H. Batatia, A. Basarab, D. Kouamé, “Discrete wavelet for multifractal texture classification: Application to medical ultrasound imaging.” In Proceedings of the 17th IEEE International Conference on Image Processing, Hong Kong, China, pp. 637–640, 26–29 September 2010.

[22] J. Medina-García, T. Sánchez-Rodríguez, J.A.G. Galán, A. Delgado, F. Gómez-Bravo, R. Jiménez, “A Wireless Sensor System for Real-Time Monitoring and Fault Detection of Motor Arrays”, Sensors , vol. 17, no.3, 469, 2017.

[23] J. Fernández-Lozano, M. Martín-Guzmán, J. Martín-Ávila, A. García-Cerezo, “A Wireless Sensor Network for Urban Traffic Characterization and Trend Monitoring.”, Sensors , vol. 15, no. 10, pp. 26143-26169, 2015.

[24] A. J. Garcia-Sanchez, F. Garcia-Sanchez, J. Garcia-Haro, "Wireless sensor network deployment for integrating video-surveillance and data-monitoring in precision agriculture over distributed crops", Computers and Electronics in agriculture, vol. 75, no. 2, pp. 288-303, 2011.

Author Response

There is a "typo" at the end of line 45: instead of " wireless sensor work ", write " wireless sensor network".

Authors’ response:

We would like to sincerely thank Reviewer#1 for careful reading of the manuscript. The authors much appreciate the constructive comment of the Reviewer#1. We have considered to correct the typo and add the suggested 8 citations.

Moreover, rapid growth in the field of integrated circuits (IC) and Information Technology (IT) has led to the development of the inexpensive and tiny size of sensor nodes of Wireless sensor network (WSN). WSN is composed of a set of a vast number of sensor nodes arranged in the ad-hoc fashion to observe and interact with the physical world [15]. The sensor captures the environment's information is processed and forwarded to the Base Station (BS) via middle nodes or single hop[16]. WSN's detect and measure (or monitor) a number of physical or environmental conditions such as multimedia [17][18], infrared energy emitted from object and converts it to temperature[19], pollutant levels [20], ultrasound in medical imaging [21], vibrations [22], security and surveillance [23], agriculture [24] and many other such conditions. WSN usually is carried out in areas where people access is hard or not possible intervention.

[17] W. Liu, K. R. Vijayanagar, and J. Kim, “Low-complexity distributed multiple description coding for wireless video sensor networks,” IET Wirel. Sens. Syst., vol. 3, no. 3, pp. 205–215, 2013.

[18] I. T. Almalkawi, M. Guerrero Zapata, J. N. Al-Karaki, and J. Morillo-Pozo, “Wireless multimedia sensor networks: current trends and future directions,” Sensors, vol. 10, no. 7, pp. 6662–6717, 2010.

[19] A. A. Djedjiga and O. Abdeldjalil, “Monitoring crack growth using thermography,” Comptes Rendus. Mec., vol. 336, no. 8, pp. 677–683, 2008.

[20] D. M. Broday, “Wireless distributed environmental sensor networks for air pollution measurement—The promise and the current reality,” Sensors, vol. 17, no. 10, p. 2263, 2017.

[21] D. Meriem, O. Abdeldjalil, B. Hadj, B. Adrian, and K. Denis, “Discrete wavelet for multifractal texture classification: Application to medical ultrasound imaging,” in 2010 IEEE International Conference on Image Processing, 2010, pp. 637–640.

[22] J. Medina-García, T. Sánchez-Rodríguez, J. Galán, A. Delgado, F. Gómez-Bravo, and R. Jiménez, “A wireless sensor system for real-time monitoring and fault detection of motor arrays,” Sensors, vol. 17, no. 3, p. 469, 2017.

[23] J. J. Fernandez-Lozano, M. Martín-Guzmán, J. Martín-Ávila, and A. García-Cerezo, “A wireless sensor network for urban traffic characterization and trend monitoring,” Sensors, vol. 15, no. 10, pp. 26143–26169, 2015.

[24] A.-J. Garcia-Sanchez, F. Garcia-Sanchez, and J. Garcia-Haro, “Wireless sensor network deployment for integrating video-surveillance and data-monitoring in precision agriculture over distributed crops,” Comput. Electron. Agric., vol. 75, no. 2, pp. 288–303, 2011.

Author Response File: Author Response.pdf

Reviewer 2 Report

The authors addressed all the reviewers comments and for this reason the article can be accepted in its present forrm.

Author Response

The authors addressed all the reviewers comments and for this reason, the article can be accepted in its present form.

Authors’ response:

We would like to sincerely thank Reviewer#2 for careful reading of our manuscript and the constructive comments.

The authors greatly appreciate the positive comments about the topic and applicability of the manuscript.

Author Response File: Author Response.pdf

Article Menu

A Compact Bat Algorithm for Unequal Clustering in Wireless Sensor Networks

Further Information

Guidelines

MDPI Initiatives

Follow MDPI