Education 4.0: Teaching the Basics of KNN, LDA and Simple Perceptron Algorithms for Binary Classification Problems
Round 1
Reviewer 1 Report
Dear authors,
Your article proposal tries to highlight the comparative analysis of the educational phenomenon Education 4.0 through unsupervised learning algorithms.
A general consideration to this proposal:
I do not understand why the three methods were described in detail if you do not make a theoretical contribution to these methods of supervised and unsupervised analysis.
I will review the aspects I found on the lines.
1) Between lines 43-45 we have two lines inspired by the following resource .. please reformulate.
because the source is from here and you didn't quote
https://ieeexplore.ieee.org/document/8869509
That's how it was in its original form
i) virtual collaboration, (ii) resilience, (iii) social intelligence, (iv) novel and adaptive thinking, (v) load cognition management, (vi) sense making, (vii) new media literacy, (viii) design mind set , (ix) transdisciplinary approach and (x) computational skills.
If you consider it important, put it in quotation marks and indicate this bibliographic resource
Guillermo Sandoval Benítez, Ricardo Mendez Hernandez, David Barragan Prieto, "University - Industry: a successful collaboration experience", Intelligent Engineering and Management (ICIEM) 2020 International Conference on, pp. 498-503, 2020.
2) Paragraph 2.1
The k-nn method was discovered by Evelyn Fix and Joseph Hodges in 1951,
Fix, Evelyn; Hodges, Joseph L. (1951). Discriminatory Analysis. Nonparametric Discrimination: Consistency Properties (PDF). USAF School of Aviation Medicine, Randolph Field, Texas.
https://apps.dtic.mil/dtic/tr/fulltext/u2/a800276.pdf
Ulerior was developed by Thomas Cover in 1967
T. Cover and P. Hart, "Nearest neighbor pattern classification," in IEEE Transactions on Information Theory, vol. 13, no. 1, pp. 21-27, January 1967, doi: 10.1109 / TIT.1967.1053964.
The algorithm on line 170 will not belong to you. Why not indicate the source where it came from.
3) Paragraph 2.2
The concept of Linear discriminant analysis has its roots in Fisher's 1936 work
Fisher, R. A. (1936). "The Use of Multiple Measurements in Taxonomic Problems" (PDF). Annals of Eugenics. 7 (2): 179–188. doi: 10.1111 / j.1469-1809.1936.tb02137.x. hdl: 2440/15227.
The algorithm on lines 223 will also not belong.
4) Paragraph 2.3
Perceptron originated in the laboratories of Cornell Aeronautical in 1957 by:
Rosenblatt, Frank (1957). "The Perceptron — a perceiving and recognizing automaton." Report 85-460-1. Cornell Aeronautical Laboratory.
In line 264 the algorithm does not belong to you, please indicate the source.
4) Paragraph 2.3
Perceptron originated in the laboratories of Cornell Aeronautical in 1957
Rosenblatt, Frank (1957). "The Perceptron — a perceiving and recognizing automaton." Report 85-460-1. Cornell Aeronautical Laboratory.
In line 264 the algorithm does not belong to you, please indicate the source.
In Table 1, at the LDA with Disadvantages intersection you wrote twice
Linear decision boundaries
5) In fact, your article starts from line 265 with the case study.
6) We consider useful the delimitation between state of the art and your contribution to science.
7) The article proposal requires major changes and structuring of the concepts/methods used, respectively a brief presentation of the case study, emphasizing the limitations of the research.
Best Regards
Author Response
“Education 4.0: Teaching the basics of KNN, LDA and Simple Perceptron algorithms for binary classification problems”
Dear Reviewers,
We have submitted the revised manuscript “Education 4.0: Teaching the basics of KNN, LDA and Simple Perceptron algorithms for binary classification problems” for publication consideration in the Journal: Future Internet Special Issue - Education 4.0 in the Transformation of Universities: Educational and Research Applications.
We would like to thank the reviewers for their meticulous reading of this manuscript and for the comments' valuable suggestions, which assist to improve this manuscript. The paper has been revised based on their suggestions and comments, with the hope this revision has improved the paper to a level of their satisfaction. Reviewer’s comments are enumerated followed by our response in orange.
Thank you for your consideration of this manuscript.
Sincerely,
Diego López Bernal.
Reviewer 1:
Dear authors,
Your article proposal tries to highlight the comparative analysis of the educational phenomenon Education 4.0 through unsupervised learning algorithms.
A general consideration to this proposal:
I do not understand why the three methods were described in detail if you do not make a theoretical contribution to these methods of supervised and unsupervised analysis.
Thank you very much for your time and comments on our manuscript. To clarify, the article proposal has the objective of serving as educational material for students and teachers that are interested in learning through the Education 4.0 framework. This can be seen from line 86 to line 104. Thus, the methods have to be described in detail so that the paper can be useful as support or introductory material for machine learning lessons.
1) Between lines 43-45 we have two lines inspired by the following resource .. please reformulate. Because the source is from here and you didn't quote
https://ieeexplore.ieee.org/document/8869509
That's how it was in its original form
- i) virtual collaboration, (ii) resilience, (iii) social intelligence, (iv) novel and adaptive thinking, (v) load cognition management, (vi) sense making, (vii) new media literacy, (viii) design mind set , (ix) transdisciplinary approach and (x) computational skills.
If you consider it important, put it in quotation marks and indicate this bibliographic resource
Guillermo Sandoval Benítez, Ricardo Mendez Hernandez, David Barragan Prieto, "University - Industry: a successful collaboration experience", Intelligent Engineering and Management (ICIEM) 2020 International Conference on, pp. 498-503, 2020.
Thank you for your remark. We have checked the source that you mention; however, we did not find the original form in that paper. Moreover, we looked over more works about this topic and it seems that the first one to describe those competencies was the one cited in our work:
Ramirez-Mendoza, R. A., Morales-Menendez, R., Iqbal, H., & Parra-Saldivar, R. (2018). Engineering Education 4.0: — proposal for a new Curricula. 2018 IEEE Global Engineering Education Conference (EDUCON). doi:10.1109/educon.2018.8363376
Also, in this reference, the competencies were not written in the same way as in our work, thus it seems to be unnecessary to use quotation marks.
2) Paragraph 2.1
The k-nn method was discovered by Evelyn Fix and Joseph Hodges in 1951,
Fix, Evelyn; Hodges, Joseph L. (1951). Discriminatory Analysis. Nonparametric Discrimination: Consistency Properties (PDF). USAF School of Aviation Medicine, Randolph Field, Texas.
https://apps.dtic.mil/dtic/tr/fulltext/u2/a800276.pdf
Ulerior was developed by Thomas Cover in 1967
- Cover and P. Hart, "Nearest neighbor pattern classification," in IEEE Transactions on Information Theory, vol. 13, no. 1, pp. 21-27, January 1967, doi: 10.1109 / TIT.1967.1053964.
The algorithm on line 170 will not belong to you. Why not indicate the source where it came from.
Thank you for your comment. We added the references to the original works for KNN algorithm development and also indicated that the pseudo-code provided is an interpretation of these works.
3) Paragraph 2.2
The concept of Linear discriminant analysis has its roots in Fisher's 1936 work
Fisher, R. A. (1936). "The Use of Multiple Measurements in Taxonomic Problems" (PDF). Annals of Eugenics. 7 (2): 179–188. doi: 10.1111 / j.1469-1809.1936.tb02137.x. hdl: 2440/15227.
The algorithm on lines 223 will also not belong.
We appreciate your remark. Just as in your previous comment, we added a reference to Fisher's original work, while also mentioning that the provided pseudo-code is based on it.
4) Paragraph 2.3
Perceptron originated in the laboratories of Cornell Aeronautical in 1957
Rosenblatt, Frank (1957). "The Perceptron — a perceiving and recognizing automaton." Report 85-460-1. Cornell Aeronautical Laboratory.
In line 264 the algorithm does not belong to you, please indicate the source.
In Table 1, at the LDA with Disadvantages intersection you wrote twice
Linear decision boundaries
We are grateful for your remark. We added a reference to the original work of the Perceptron at the beginning of this section. Moreover, we clarify that the pseudo-code is based on this same work. Additionally, we corrected the mistake in Table 1 and eliminated the repetition of “linear decision boundaries” as a disadvantage of the LDA algorithm.
5) In fact, your article starts from line 265 with the case study.
Thank you for your comment. As mentioned earlier, the detailed description of the given algorithms, previous to the analysis of the case study, was necessary in order to fulfill the main objective of the article, which is to serve as educational material under the Education 4.0 framework.
6) We consider useful the delimitation between state of the art and your contribution to science.
We appreciate your comment. This has been addressed by specifying in the introduction that “at the time of writing this paper, we have not found other work that provides an introduction to these algorithms and that explains how to apply them over real-life situations under the Education 4.0 framework.”
7) The article proposal requires major changes and structuring of the concepts/methods used, respectively a brief presentation of the case study, emphasizing the limitations of the research.
Thank you for your remark. As mentioned earlier, the main objective of this work is to be useful as educational material under the Education 4.0 framework. Hence, the paper was structured in such a way that it first gives an introduction to the presented algorithms and how they work, and then it explores their application over the proposed test bench. Moreover, section 4 describes briefly the case studies, and, from lines 395-401 (the final part of the “Final remarks” section) describes the limitations of the present research.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
Exchange in the title: Education 4.0: Teaching the BASICS of KNN, LDA and Simple Perceptron algorithms for binary classification problems
Abstract: exchange … this work by .... this study and … The end result of this work … by … The findings
In the abstract, insert some kind of implications your study entails
Please observe how to reference, use the standard of the journal [1]
The development of the article is fine and deserves publication.
The final section could be called Final Remarks and entail a strong discussion on the implications of the findings (who gains what and why after your study).
Please state also what are the next steps (what´s next?), entailing clues for further research.
There are too few references to recent articles (> 2019) on Future Internet. Please cite at least five recent articles related to your study.
Author Response
Response Letter to Review Comments
“Education 4.0: Teaching the basics of KNN, LDA and Simple Perceptron algorithms for binary classification problems”
Dear Reviewers,
We have submitted the revised manuscript “Education 4.0: Teaching the basics of KNN, LDA and Simple Perceptron algorithms for binary classification problems” for publication consideration in the Journal: Future Internet Special Issue - Education 4.0 in the Transformation of Universities: Educational and Research Applications.
We would like to thank the reviewers for their meticulous reading of this manuscript and for the comments' valuable suggestions, which assist to improve this manuscript. The paper has been revised based on their suggestions and comments, with the hope this revision has improved the paper to a level of their satisfaction. Reviewer’s comments are enumerated followed by our response in orange.
Thank you for your consideration of this manuscript.
Sincerely,
Diego López Bernal.
Reviewer 2:
1. Exchange in the title: Education 4.0: Teaching the BASICS of KNN, LDA, and Simple Perceptron algorithms for binary classification problems
Abstract: exchange … this work by .... this study and … The end result of this work … by … The findings
In the abstract, insert some kind of implications your study entails
Please observe how to reference, use the standard of the journal [1]
The development of the article is fine and deserves publication.
Thank you very much for your time and comments on our manuscript. These comments have been addressed through your suggested changes to the title and abstract wording, as well as how the references were made. Moreover, the abstract has been changed in such a way that it explains in more detail some of the main implications of this study.
2. The final section could be called Final Remarks and entail a strong discussion on the implications of the findings (who gains what and why after your study).
Please state also what are the next steps (what´s next?), entailing clues for further research.
We are grateful for your remark. This has been addressed by adding to the “Final Remarks” section a description of what the students can learn from this study and how this work can be used by teachers that are beginning to work under the Education 4.0 framework. Furthermore, we give some ideas for the possible next steps that may follow what we propose in this work, such as expanding the test bench by including more datasets or introducing more algorithms that can also be used to analyze and solve real-life problems.
3. There are too few references to recent articles (> 2019) on Future Internet. Please cite at least five recent articles related to your study.
Thank you for your comment. This has been addressed by citing the following recent articles (>2019) on Future Internet:
- Rodríguez-Abitia, G.; Bribiesca-Correa, G. Assessing Digital Transformation in Universities. Future Internet 2021,13, 52.
- Zhang, P.; Wang, R.; Shi, N. IgA Nephropathy Prediction in Children with Machine Learning Algorithms. Future Internet 2020,12, 230.
- Thapa, N.; Liu, Z.; Kc, D.B.; Gokaraju, B.; Roy, K.; others. Comparison of machine learning and deep learning models for network intrusion detection systems. Future Internet 2020, 49112, 167.
- Bressan, G.; Cisotto, G.; Müller-Putz, G.R.; Wriessnegger, S.C. Deep learning-based classification of fine hand movements from low frequency EEG. Future Internet 2021,13, 103.
- Hitimana, E.; Bajpai, G.; Musabe, R.; Sibomana, L.; Kayalvizhi, J. Implementation of IoT Framework with Data Analysis Using Deep Learning Methods for Occupancy Prediction in a Building.Future Internet 2021,13, 67.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
Dear authors,
I checked the changes you made to the article.
Respectfully,
