Comparison of Frontal-Temporal Channels in Epilepsy Seizure Prediction Based on EEMD-ReliefF and DNN
Round 1
Reviewer 1 Report
Dr. Aníbal Romney and Vidya Manian realized a very interesting and innovative comparative analysis of frontal-temporal channels in epilepsy seizure prediction based on EEMD-ReliefF and DNN. I consider the manuscript already satisfying, and I only suggest minor revisions:
1) Table 1 is unnecessary, and its content could be placed through the main text.
2) Minor English revisions and typos correction should be realized.
Author Response
REVIEWER 1: 1) Table 1 is unnecessary, and its content could be placed through the main text. RESPONSE: Table 1 has been removed and contents were placed in main text.
REVIEWER 1: 2) Minor English revisions and typos correction should be realized. RESPONSE: We have proofread the manuscript and made the corresponding corrections of grammar and typos.
|
Reviewer 2 Report
The paper “Comparison of frontal-temporal channels in epilepsy seizure prediction based on EEMD-ReliefF and DNN” focuses on implementation a deep neural network (DNN) to perform prediction and early detection of seizures on specific patient EEG recordings.
The work is interesting and in general it is well written. In general the study is correct, well organized and with a good analyses of results. However, it needs extensions and improvements across all of its aspects:
- a) The introduction includes a small literature review. In this regards, I suggest author to create a new section “Literature review” and examine related recent works. I recommend to read and to quote:
Pulmonary Tumor Detection by virtue of GLCM (2019). G Kanagaraj & P Suresh Kumar.
Stochastic recurrent wavelet neural network with EEMD method on energy price prediction (2020). Jingmiao Li & Jun Wang.
Identifying Industrial Productivity Factors with Artificial Neural Networks (2020). A. M. Gutiérrez-Ruiz et al.
Forecasting neural network model with novel CID learning rate and EEMD algorithms on energy market (2018). Zhongpei Cen & Jun Wang.
These papers will provide a much more complete view of the methodology used and they help justify the choice of neural network methodology. Therefore it is essential to cite (at least) these references.
- b) The authors need to be more strict in the statistical methodology. An elementary statistical card is missing (sample size justification, average, variance, representativity, …)
- c) Order of the sections. The order established by the authors is not usual. I recommend:
- Introduction
- Literature review
- Materials and Methods
- Results
- Discussion and Conclusion.
References
After its need rewriting.
My opinion is: Accept the article but with major corrections.
Author Response
REVIEWER 2:
- a) The introduction includes a small literature review. In this regards, I suggest author to create a new section “Literature review” and examine related recent works. I recommend to read andto quote:
Pulmonary Tumor Detection by virtue of GLCM (2019). G Kanagaraj & P Suresh Kumar.Stochastic recurrent wavelet neural network with EEMD method on energy price prediction(2020). Jingmiao Li & Jun Wang.
Identifying Industrial Productivity Factors with Artificial Neural Networks (2020). A. M. GutiérrezRuiz et al.
Forecasting neural network model with novel CID learning rate and EEMD algorithms on energy market (2018). Zhongpei Cen & Jun Wang.
These papers will provide a much more complete view of the methodology used and they help justify the choice of neural network methodology. Therefore it is essential to cite (at least) these references.
RESPONSE:
A new section Literature review is created. Recent related studies has been added, including three paper recommendations. Added references [29][30][31][32][33].
- Literature Review. See pages 2-4.
REVIEWER 2:
- b) The authors need to be more strict in the statistical methodology. An elementary statistical card is missing (sample size justification, average, variance, representatively, …)
RESPONSE:
Statistical analysis were included in the following sections:
- Materials and Method
3.4. Statistical Analysis and Validation. See page 7.
- Results
4.5. Statistical Significance. See page 11.
REVIEWER 2:
- c) Order of the sections. The order established by the authors is not usual. I recommend:
- Introduction
- Literature review
- Materials and Methods
- Results
- Discussion and Conclusion.
References
RESPONSE: The sections orders has been changed.
- Introduction
- Literature review
- Materials and Methods
- Results
- Discussion and Conclusion.
References
Round 2
Reviewer 2 Report
Dears Authors,
Thank you for the new version, all my suggestions were accepted and followed.
But, some references are incomplete:
[31] Pulmonary Tumor Detection by virtue of GLCM (2019). G Kanagaraj & P Suresh Kumar.Stochastic recurrent wavelet neural network with EEMD method on energy price prediction(2020). Jingmiao Li & Jun Wang. J Sci Ind Res (Journal of Scientific & Industrial Research)
[32] Identifying Industrial Productivity Factors with Artificial Neural Networks (2020). A. M. Gutiérrez-Ruiz et al. J Sci Ind Res (Journal of Scientific & Industrial Research)
You need to check this (required).
I hope my comments will be useful for your future work.
Author Response
Response to Reviewer 2 Comment (ROUND 2)
|
REVIEWER 2: Thank you for the new version, all my suggestions were accepted and followed. But, some references are incomplete: [31] Pulmonary Tumor Detection by virtue of GLCM (2019). G Kanagaraj & P Suresh Kumar.Stochastic recurrent wavelet neural network with EEMD method on energy price prediction(2020). Jingmiao Li & Jun Wang. J Sci Ind Res (Journal of Scientific & Industrial Research) [32] Identifying Industrial Productivity Factors with Artificial Neural Networks (2020). A. M. GutiérrezRuiz et al. J Sci Ind Res (Journal of Scientific & Industrial Research)
RESPONSE: The references [31], [32] are now complete.
[31] G. Kanagaraj and S. Kumar, “Pulmonary Tumor Detection by virtue of GLCM,” Journal of Scientific & Industrial Research, Vol. 79, February 2020, pp. 132–134, 2020. [32] A. Manuel Gutiérrez-Ruiz, L. Valcarce-Ruiz, R. Becerra-Vicario, and D. Ruíz-Palomo, “Identifying Industrial Productivity Factors with Artificial Neural Networks,” Journal of Scientific & Industrial Research, Vol. 79, June 2020, pp. 534–536, 2020.
|