Deep Learning Model of Sleep EEG Signal by Using Bidirectional Recurrent Neural Network Encoding and Decoding

Round 1

Reviewer 1 Report

Authors presents a deep learning model of sleep EEG signal using bidirectional recurrent neural network (BiRNN) encoding and decoding. 

The input signal was denoised using the wavelet threshold method. The feature extraction in the time and frequency domains was realized using a convolutional neural network to expand the scope of feature extraction and preserve the original EEG feature information to the maximum extent possible. The model was cross-validated using Fpz-Cz single-channel EEG signals from the Sleep-EDF dataset for nights, and the results demonstrated that the proposed model can achieve a high recognition rate and stability.

This is an interesting work, however, I have few questions and remarks:

1. The comparison with previous works must be more precise in order to highlight the real contribution of this work.

2. Method section is well presented illustrating the main contribution. 

3. Results section must be extended by integrating more results and discussion.

Concluding, the paper has potential to be appreciated by the readers and the above comment are formulated such that to enhance its impact.

 

 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

The following corrections are required:

i) The meaning of attention and concatenation needs to be specified in the flow chart of the proposed model in figure2.

ii)The relations, functions, and components of figure 4 need to be elaborated.

iii)  Specify the meaning of Fpz-Cz, Fpz-Oz, Pz-Oz EEG signals.

(iv) Need to mention the labels of the x-axis and y-axis in figure6.

 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf