All reviews of published articles are made public. This includes manuscript files, peer review comments, author rebuttals and revised materials. Note: This was optional for articles submitted before 13 February 2023.
Peer reviewers are encouraged (but not required) to provide their names to the authors when submitting their peer review. If they agree to provide their name, then their personal profile page will reflect a public acknowledgment that they performed a review (even if the article is rejected). If the article is accepted, then reviewers who provided their name will be associated with the article itself.
Dear Authors the review process is now finished. All Reviewers are positive on your manuscript therefore i am pleased to forward your manuscript with a positive recommendation.
Article is overall well written and contains interesting and revealing content. Authors have used professional English and included accurate literature references. Proofs are clear and does not contain any visible errors.
Authors have replied to all given critique and have given clear responses.
All findings are well documented, clear to read and does not contain any visible errors.
This article is well made and contains valuable knowledge. It's easy to read.
Check fig. 3,4,6 axis descriptions are truncated.
I have no more critical comments.
In my opinion it is ok.
OK
The authors followed my suggestions so I have no further objections.
Dear Authors, Reviewers suggest changes to your paper by solving important issues. Please revise it and return to us with revisions for further processing.
[# PeerJ Staff Note: Please ensure that all review comments are addressed in a rebuttal letter and any edits or clarifications mentioned in the letter are also inserted into the revised manuscript where appropriate. It is a common mistake to address reviewer questions in the rebuttal letter but not in the revised manuscript. If a reviewer raised a question then your readers will probably have the same question so you should ensure that the manuscript can stand alone without the rebuttal letter. Directions on how to prepare a rebuttal letter can be found at: https://peerj.com/benefits/academic-rebuttal-letters/ #]
This article shows an interesting solution that fits into the current needs of the healthcare system around the World. Authors have created a well performing CNN model recognizing, in a very short time, Chronic Obstructive Pulmonary Disease (COPD). Because of that it could help the doctors, especially in overpopulated areas, to diagnose, with higher accuracy, more patients in the same time, which could potentially lead to faster treatment and less health complications.
The article is well and clearly written and provides all used resources, however some minor changes are required.
After analyzing your code I can see that in your work you have used Adam optimization algorithm, however it is not mentioned in your article. As we know there are many different training algorithms and because of that I have a question:
- Why have you chosen such algorithm? Were there any experiments carried out with other algorithms like NAdam, RMSprop, etc.? And how does they compare with each other (training times, accuracy, ...)
You have mentioned that other systems takes a very long time to train and predict. How does it perform in your case? Is it faster than other methods with similar results? What is the device requirenment to run the network with reasonable predicting times and to train the model?
All findings are well documented, clear to read and does not contain any major errors.
This article is well made and contains valuable knowledge. It's easy to read.
Table VII should be corrected: the headers are large, axis descriptions illegible.
Table VIII explain word abbreviations Se Sp
Fig 3-6 no axes description.
Fig 3-fig 11 are large and not clear
More precisely explain and describe the feature extraction methods between input analogic signal, spectrogram and input to your neural network.
More precisely explain how the architecture of convolutional neural networks looks like (convolutional, pooling). Can you show some examples of each operation?
Authors shows interesting applied of CNN for detection of chronic obstructive pulmonary disease, but numer of examples form experiments is small, so give more examples for other types of images
Explain where the presented method can be used in practice.
How this method can be improved and developed in the future?
Authors can extend the bibliography to include articles: Bio-inspired voice evaluation mechanism, DecomVQANet: Decomposing visual question answering deep network via tensor decomposition and regression
All text and materials provided via this peer-review history page are made available under a Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.