Next Article in Journal
A No-Reference Quality Assessment Method for Screen Content Images Based on Human Visual Perception Characteristics
Previous Article in Journal
G-Band Broad Bandwidth Extended Interaction Klystron with Traveling-Wave Output Structure
 
 
Article
Peer-Review Record

Ensemble Self-Paced Learning Based on Adaptive Mixture Weighting

Electronics 2022, 11(19), 3154; https://doi.org/10.3390/electronics11193154
by Liwen Liu 1,*, Zhong Wang 1, Jianbin Bai 1, Xiangfeng Yang 1, Yunchuan Yang 1 and Jianbo Zhou 2
Reviewer 1: Anonymous
Reviewer 2:
Reviewer 3: Anonymous
Electronics 2022, 11(19), 3154; https://doi.org/10.3390/electronics11193154
Submission received: 8 September 2022 / Revised: 20 September 2022 / Accepted: 23 September 2022 / Published: 1 October 2022
(This article belongs to the Section Computer Science & Engineering)

Round 1

Reviewer 1 Report

The article is interesting and well written. I didn't notice any flaws in the theoretical part. Generally, as it is, it is suitable for publication. Below are minor comments to the text.

-          In Figure 1, all training sets and base classifiers have the same index of 1.

-          Formula (8): What was the reason for choosing just such a formula in the proposed adaptive mixture weighting method?

Author Response

The response is attached.

Author Response File: Author Response.pdf

Reviewer 2 Report

The Research Paper stands Accepted with following Minor revisions and is subject for re-review:

1. Add in the last lines of Abstract in what %age and in what parameters the proposed methodology is better as compared to existing techniques and what is the overall analysis.

2. Proof Read the paper, and wherever et al. is written add reference number in brackets properly.

3. Add Objectives of the paper before organization of the paper.

4. Literature review is missing in the paper. It is suggested to add min 15-25 papers with proper explanation regarding what is proposed, what is the novelty and what experimental results are there. And also in the last lines, highlight what overall technical gaps are observed that led to the design of proposed methodology.

5. Add flowchart of proposed methodology.

6. Add Analysis section to the paper.

7. It is also suggested to add some Case study oriented discussion to the paper, basing some solution to the problem by using the proposed methodology.

8. Add future scope to the paper.

Author Response

The response is attached.

Author Response File: Author Response.pdf

Reviewer 3 Report

The authors present a very well structured article on Self-Paced Learning, well explained in terms of methodologies used and tests developed. 

However, there are small details that should be improved.

---------

--> Line 87: Define the acronym "ESPL" close to its meaning, i.e. "Ensemblre self-paced learning (ESPL)"

--> Line 98: Place introductory text between "2. Background" and "2.1"

--> When authors insert equations in the document, they should reference them in their explanation text. That is, when explaining the respective formula, give the equation number.

--> Line 118 "2.2 Ensemble Stacking Learning," authors should not start the subsection immediately with the image. They should put an introductory text.

--> Figure legends are: "Figure X. ", and when the authors make reference in the text they should put "Fig. 1". They should maintain coherence.

--> Figure 1", should be improved. It does not reflect well its explanation in the text. In the various steps it always contains "Training set 1" and "Base Classifier 1". Shouldn't the training number change? 

"Training set 1", "Trainig set 2, "Training set n" ??

I think this would make it more perceptible to the reader.

 

--> Line 149 "Bagging uses bootsrap", shouldn't it be "bootstrap" ?

Authors should put the bibliographic reference

 

--> Table 1. Authors should put the full name of the columns. "Insts." and "Atts."

--> Line 231: The authors say "we apply the Friedman and Nemenyi tests". They should put the reference in the text!

--> References must contain the DOI of the articles.

Author Response

The response is attached.

Author Response File: Author Response.pdf

Back to TopTop