Dual Band Antenna Design and Prediction of Resonance Frequency Using Machine Learning Approaches

Round 1

Reviewer 1 Report

This work constructs and evaluates an inset fed-microstrip patch antenna with a partial ground configuration. Here are my observations:

1-Instead of utilizing relative terms to support your findings, use absolute terms (by percentage) in the abstract and conclusion section.

2) In the abstract part, you had better show your method in step by step in order to show the core work you have done. From the current abstract, I cannot find the innovation, which is superficial to tell your method. You had better add more step details. 

3-In the introduction part, you have to reconstruct it according to the sequence of background, problem to state, existing methods with disadvantages， your method, and from which point to solve. 

4-It is required to cite any formulas that were taken from other articles.

5-In the conclusion part, you must discuss your method's drawbacks and potential future research.

Author Response

Review Response Letter

We thank the Editor and the Reviewers for their insightful and constructive comments. The revised paper has been edited to address all the issues raised by them.

Reviewer 1:

Comment 1: Instead of utilizing relative terms to support your findings, use absolute terms (by percentage) in the abstract and conclusion section.

Response:

Abstract part: The seven ML model performances are evaluated based on mean square error (MSE), mean absolute error (MAE), root mean square error (RMSE) and variance score. Among the seven ML models, the prediction result of DTR (MSE=0.71%, MAE=5.63%, RMSE=8.42%, and var score=99.68%) is superior to other ML models. In conclusion, the proposed antenna is a strong contender for operating at the entire X band and lower portion of Ku band frequencies, as evidenced by the simulation results through CST and ADS, measured and predicted results using machine learning.

Conclusion part: The predicted results show that the error performances of the Decision Tree Regression model are comparatively better than other models. The MAE, MSE, RMSE and variance scores (in percentage) of the DTR model are 5.63, 0.71, 8.42 and 99.68, respectively. The XGB model (MAE=7.03%, MSE=1.06%, RMSE=10.27% and var score=99.54%) performs better than any other learning models that are introduced in this study except DTR.

Comment 2.       In the abstract part, you had better show your method in step by step in order to show the core work you have done. From the current abstract, I cannot find the innovation, which is superficial to tell your method. You had better add more step details.

Response:

Abstract: An inset fed-microstrip patch antenna (MPA) with a partial ground structure is constructed and evaluated in this paper. This article has covered how to evaluate the suggested antenna's performance using a combination of simulation, measurement, the creation of the RLC equivalent circuit model, and the implementation of machine learning. The MPA's measured frequency range is from 7.9 GHz to 14.6 GHz, while its simulated frequency range is from 8.35 GHz to 14.25 GHz in CST Microwave Studio (CST MWS) 2018. The measured and simulated bandwidths are 6.7 GHz and 5.9 GHz, respectively. The antenna substrate is made of FR-4 Epoxy, which has a dielectric constant of 4.4 and a loss tangent of 0.02. The equivalent model of the proposed MPA is developed using Advance Design Software (ADS) to compare the resonance frequencies obtained using CST. In addition, the measured return loss of the porotype is compared with the simulated return loss observed using CST and ADS. In the end, 86 data samples are gathered through simulation using CST MWS, and seven machine learning (ML) approaches such as convolutional neural network (CNN), linear regression (LR), random forest regression (RFR), decision tree regression (DTR), Lasso regression, Ridge regression and extreme gradient boosting (XGB) regression are applied to estimate the single resonance frequency of the patch antenna. The seven ML model performances are evaluated based on mean square error (MSE), mean absolute error (MAE), root mean square error (RMSE) and variance score. Among the seven ML models, the prediction result of DTR (MSE=0.71%, MAE=5.63%, RMSE=8.42%, and var score=99.68%) is superior to other ML models. In conclusion, the proposed antenna is a strong contender for operating at the entire X band and lower portion of Ku band frequencies, as evidenced by the simulation results through CST and ADS, measured and predicted results using machine learning.

Comment 3: In the introduction part, you have to reconstruct it according to the sequence of background, problem to state, existing methods with disadvantages your method, and from which point to solve.

Response:

Yes, the findings from the comment 3, have been discussed in introduction part.

Comment 4:      It is required to cite any formulas that were taken from other articles.

Response:

Formulas have been cited from the following references number 33 and 34.

33. C. A. Balanis, Antenna theory: analysis and design. John wiley & sons, 2015.
34. P. Barthia, K. V. S. Rao, and R. S. Tomar, “Millimeter wave microstrip and printed circuit antenna,” Artech House-Boston–1991, 1991.

Review Comment 5.   In the conclusion part, you must discuss your method's drawbacks and potential future research.

Response:

CONCLUSION

This article has discussed the integration of simulation, measurement, development of the RLC equivalent circuit model, and applying machine learning to evaluate the performance of the proposed antenna. In terms of frequency, the designed antenna supports the whole X band as well as the portion of the Ku band. The prototype was built and analyzed to confirm the intended antenna's design. In addition, the RLC equivalent model of the proposed MPA found by the ADS Agilent software yields resonance frequencies nearly identical to those generated by simulation (with CST) and measurement. Furthermore, six machine learning and one deep learning (CNN) algorithm have been developed to determine the resonant frequency of the MPA. When the predicted and simulated resonant frequencies are compared, it is observed that they are almost identical. Different performance metrics such as MAE, MSE, RMSE and Variance scores are calculated to validate the prediction using learning algorithms. These metrics are obtained through the process of computing the results of the prediction. The predicted results show that the error performances of the Decision Tree Regression model are comparatively better than other models. The MAE, MSE, RMSE and variance scores (in percentage) of the DTR model are 5.63, 0.71, 8.42 and 99.68, respectively. The XGB model (MAE=7.03%, MSE=1.06%, RMSE=10.27% and var score=99.54%) performs better than any other learning models that are introduced in this study except DTR. The performance of the deep learning model (CNN) is slightly lower than the presented regression models, which may be occurred due to the inadequate number of data samples for the CNN model. Even though the proposed MPA has two resonance frequencies, we have only predicted one (9 GHz) using ML models. In addition, the designed MPA has a lower gain of 4.06 dB at 9 GHz and 3.46 dB at 13 GHz. The measured resonance frequency range (7.90 GHz to 14.6 GHz) does not quite correspond to the predicted resonance frequency range (8.35 GHz to 14.25 GHz). In the future, we will generate adequate number of data samples to achieve better results using DL models like as CNN and predict the multiple frequencies for a multiband antenna. Furthermore, we will develop the ML models to predict return loss, gain, length and width of the proposed antenna. Moreover, we will ensure the better impedance matching between the proposed MPA and the SMA connector so that the simulated and measured frequencies are completely matched. Finally, it can be concluded that the simulated, measured, and predicted results ensure the reliability of the proposed antenna in the whole X band and the part of Ku band applications.  

Author Response File: Author Response.docx

Reviewer 2 Report

Manuscript number: AWPL-07-22-1712

Manuscript Title: Dual Band Antenna Design and Prediction of Resonance Frequency Using Machine Learning Approaches

Reviewer:

Comments to the Author

In the manuscript, an inset fed-microstrip patch antenna (MPA) is constructed and evaluated with a partial ground structure. The MPA's measured frequency range is from 7.9 GHz to 14.6 26 GHz, while its simulated frequency range is from 8.35 GHz to 14.25 GHz in CST Microwave Studio (CST MWS) 2018. The antenna substrate is made, of FR-4 Epoxy, which has a dielectric constant of 28 4.4 and a loss tangent of 0.02. The equivalent model of the proposed MPA is developed using Advance Design Software (ADS) to compare the resonance frequencies obtained using CST. In addition, the measured return loss of the prototype is compared with the simulated return loss observed 31 using CST and ADS. In the end, 86 data samples are gathered through simulation using CST MWS, 32 and several machine learning approaches are applied to estimate the single resonance frequency of 33 the patch antenna.

The presented results are interesting, yet there are several parts need to improve.

The following are comments of the manuscript for further improvements.

1.       Generally, the FR4 is the loss substrate. Why the FR4 had been chosen as the microstrip antenna?

2.       The English of the manuscript should review. There are several errors in the manuscript.

3.       Figure 3 shows the return loss vs Frequency plot of the proposed MPA. Yet there are obvious differences between the simulation and measurement results. Why?

4.       How about the radiation patterns about the proposed antenna?

5.       How about the gain of the antenna?

6.       To realization of the dual band radiation, metasurface antenna is a good choice. May be the reference about the dual band radiation antenna should be added in the reviewed manuscript. Such as DOI: 10.3390/electronics11182882  DOI:10.1002/adts.202200006   

Author Response

Review Response Letter

We thank the Editor and the Reviewers for their insightful and constructive comments. The revised paper has been edited to address all the issues raised by them.

Reviewer 2:

Comment 1: Generally, the FR4 is the loss substrate. Why the FR4 had been chosen as the microstrip antenna?

Response:

FR4 is rightly the most used material in PCB construction. Boards from FR4 are robust, water resistant, and provide sound insulation between copper layers that minimizes interference and supports good signal integrity. This research investigated the feasibility of using FR-4 substrate for microstrip antennas throughout a wide frequency range (8-12 GHz). The purpose of this investigation was to examine the FR-4 substrate is a potential option for designing an X-band microstrip antenna, aiming to achieve a high degree of agreement between simulated and measured results. Due to its inexpensive cost and widespread availability, FR-4 was selected for this research because it can be utilized for prototyping microstrip antenna.

Comment 2.       The English of the manuscript should review. There are several errors in the manuscript.

Response:

We have modified the English writing in our current manuscript. We have carefully checked the English writing via paid Grammarly software.

Comment 3: Figure 3 shows the return loss vs Frequency plot of the proposed MPA. Yet there are obvious differences between the simulation and measurement results. Why?

Response:

The following may be the reasons:

the measured return loss graph is slightly varied from simulated return loss graph. It may be occurred due the antenna is excited using a waveguide port during simulation, but practically the antenna is excited using the SMA connector. The connector loss influences the response of the antenna. In addition, the near field scattering objects, the losses due to the feed connector and the coaxial cable also affect the response on the antenna performance.

Comment 4:      How about the radiation patterns about the proposed antenna?

Response: The following statement is added in the manuscript in Figure 6.

The radiation pattern of the proposed antenna is depicted in Figure 6 which shows the main lobe direction, main lobe magnitude, side lobe level (SLL), and 3-dB beam width. At the two distinct resonance frequencies, the 3-dB beam width is 148.2 degrees for 9 GHz and 71 degrees for 13 GHz. The SLL at resonance frequency 13 GHz is -6.3 dB and at frequency 9 GHz is -10 dB.

Review Comment 5.       How about the gain of the antenna?

 Response: The following statement is added in the manuscript in Figure 7.

Gain is a measurement of the energy delivered to the main beam. The gain vs frequency curve of the proposed antenna is presented in Figure 7. From the figure, the gain of the microstrip patch antenna varies from 2.2 dB to 6.25 dB at the entire simulated frequency range. The designed antenna has a gain of 4.0614 dB at 9 GHz and 3.4589 dB at 13 GHz.

Review Comment 5.     To realization of the dual band radiation, meta surface antenna is a good choice. May be the reference about the dual band radiation antenna should be added in the reviewed manuscript. Such as DOI: 10.3390/electronics11182882 DOI:10.1002/adts.202200006

Response

Both papers have been cited in reference no 6 and 7 and following statement is added in the manuscript.

In [6-7], meta surface based dual band antennas were investigated especially for industrial, scientific, and medical (ISM) applications. When the incident angles theta and phi change from -90 to 90 and 0 to 360 degrees, the unit "1" reflection coefficient amplitude changes from 0 to 1. Genetic algorithm (GA) optimizes CFMS coding subarray distribution [6]. S₁₁ of the antenna is less than 10 dB between 2.3–2.62 GHz and 4.9–6.45 GHz. 13% and 27% impedance bandwidth. 6.8 dB at 2.45 GHz and 9.0 dB at 5.8 GHz [7]. 

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

It can be accepted.

Reviewer 2 Report

The manuscript can be accepted in this state.