Classification of ECG signal using FFT based improved Alexnet classifier

Arun Kumar M.; Arvind Chakrapani

doi:10.1371/journal.pone.0274225

Peer Review History

Original SubmissionJune 14, 2022
27 Jun 2022 Decision Letter - Mohamed Hammad, Editor PONE-D-22-16995Classification of ECG Signal using FFT based Improved Alexnet ClassifierPLOS ONE Dear Dr. M, Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process. Please submit your revised manuscript by Aug 11 2022 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file. Please include the following items when submitting your revised manuscript: A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'. A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'. An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'. If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter. If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols. We look forward to receiving your revised manuscript. Kind regards, Mohamed Hammad, Ph.D. Academic Editor PLOS ONE Journal Requirements: When submitting your revision, we need you to address these additional requirements. 1. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and https://journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf 2. Please note that PLOS ONE has specific guidelines on code sharing for submissions in which author-generated code underpins the findings in the manuscript. In these cases, all author-generated code must be made available without restrictions upon publication of the work. Please review our guidelines at https://journals.plos.org/plosone/s/materials-and-software-sharing#loc-sharing-code and ensure that your code is shared in a way that follows best practice and facilitates reproducibility and reuse. 3. In your Data Availability statement, you have not specified where the minimal data set underlying the results described in your manuscript can be found. PLOS defines a study's minimal data set as the underlying data used to reach the conclusions drawn in the manuscript and any additional data required to replicate the reported study findings in their entirety. All PLOS journals require that the minimal data set be made fully available. For more information about our data policy, please see http://journals.plos.org/plosone/s/data-availability. "Upon re-submitting your revised manuscript, please upload your study’s minimal underlying data set as either Supporting Information files or to a stable, public repository and include the relevant URLs, DOIs, or accession numbers within your revised cover letter. For a list of acceptable repositories, please see http://journals.plos.org/plosone/s/data-availability#loc-recommended-repositories. Any potentially identifying patient information must be fully anonymized. Important: If there are ethical or legal restrictions to sharing your data publicly, please explain these restrictions in detail. Please see our guidelines for more information on what we consider unacceptable restrictions to publicly sharing data: http://journals.plos.org/plosone/s/data-availability#loc-unacceptable-data-access-restrictions. Note that it is not acceptable for the authors to be the sole named individuals responsible for ensuring data access. We will update your Data Availability statement to reflect the information you provide in your cover letter. 4. PLOS requires an ORCID iD for the corresponding author in Editorial Manager on papers submitted after December 6th, 2016. Please ensure that you have an ORCID iD and that it is validated in Editorial Manager. To do this, go to ‘Update my Information’ (in the upper left-hand corner of the main menu), and click on the Fetch/Validate link next to the ORCID field. This will take you to the ORCID site and allow you to create a new iD or authenticate a pre-existing iD in Editorial Manager. Please see the following video for instructions on linking an ORCID iD to your Editorial Manager account: https://www.youtube.com/watch?v=_xcclfuvtxQ 5. Please ensure that you refer to Figure 16 in your text as, if accepted, production will need this reference to link the reader to the figure. Additional Editor Comments: When updating your manuscript, you should elaborate on your points and clarify with references, examples, data, etc. Also, note that if a reviewer suggested references, you should only add those that are relevant to your work if you feel they strengthen your article. [Note: HTML markup is below. Please do not edit.] Reviewers' comments: Reviewer's Responses to Questions Comments to the Author 1. Is the manuscript technically sound, and do the data support the conclusions? The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented. Reviewer #1: No Reviewer #2: Yes Reviewer #3: No ******** 2. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: No Reviewer #2: Yes Reviewer #3: No ****** 3. Have the authors made all data underlying the findings in their manuscript fully available? The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified. Reviewer #1: Yes Reviewer #2: Yes Reviewer #3: Yes ****** 4. Is the manuscript presented in an intelligible fashion and written in standard English? PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here. Reviewer #1: No Reviewer #2: Yes Reviewer #3: No ****** 5. Review Comments to the Author Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters) Reviewer #1: Manuscript is well written and formatted but less novelty in the work. Kindly follow AAMI standard in classification. The detailed review comments are attached in word file. Comparison of the proposed word with existing literature work needs to be included in the results section. Reviewer #2: The authors performed good research onthe convolutional neural network technique to analyse ECG signal using improved FFT based AlexNet classifier. However, justification is required for the following comments, 1. Highlight the problem statement in the introduction section. 2. What are the merits of the proposed algorithm over traditional algorithms compared in the research work? 3. The related work section needs to be strengthened. I recommend the authors to discuss a few more recent research works. 4. In table 1, what are PVC, APC, and RBBB? 5. What is the modification done in AlexNet architecture for stating it as improved AlexNet? 6. The introduction is too long, please remove the repeated idea. No need to explain much in detail. More explanation should be about the novelty of the proposed method. 7. In section 3.4, FFT is used for feature extraction. How the extraction was done and what are the extracted features?Include the expression for the same corresponding to the proposed architecture. Reviewer #3: Summary: The authors propose an improved AlexNet based on FFT. Results seem to back the technique. My comments: 1. The manuscript in its current form is ambiguous, confusing and unclear. 2. Narrations are incoherent. 3. Many sentences are presented as if they were section headings. 4. There are repetitions of the same sentences throughout the manuscript. 5. Figures are barely visible and sometimes (Figure 4) tend not to depict what the authors are stating in the text. 6. Some figures tend to explain things better than how the authors narrate things, which again goes towards the disadvantage of the authors. 7. In the manuscript, authors write “The AlexNet architecture is depicted in Figure 5” and then the caption of Figure 5 reads, “Architecture of the improved AlexNet model”. I wonder whether Figure 5 is original AlexNet or the authors’ improved version. 8. Acronyms have not been properly introduced. 9. Algorithms/pseudo-codes have not been presented wherever needed. 10. Data distributions/dataset analyses have not been provided. 11. Authors claim to propose AlexNet based on FFT in the Abstract, which is wrong. AlexNet is already a CNN and the authors are proposing to use FFT for feature extraction of ECG signals, and later use AlexNet for classification. Or rather, they are improving AlexNet architecture as the authors claim. Again, the language needs to be sorted out here. 12. Then, authors write in Section 3.4, Paragraph 2, “Fast Fourier transform technology has successfully extracted feature components from ECG data, such as PQRST signals”. If FFT has done it successfully, what exactly are the authors accomplishing in the current manuscript? 13. The authors write in Section 3.5, last Paragraph, “Each ECG image is transmitted to the improved AlexNet in this stage”. Which stage are the authors referring to here? Again, one can see the issue with the language. My conclusion: My main problem with this manuscript is the way it has been presented. The language is all over the place and is found to be naïve at many places as well. The results might seem to be good, however, since the paper is hard to understand and follow, they might not account to much. This, unfortunately, does not qualify the standards of Plos One. The authors need to reorganise the manuscript, revisit the language and seek professional assistance to improve on the above-mentioned shortcomings. Having said that, I believe the idea and the technique presented in the manuscript are intriguing and it appears the results back the technique. Therefore, the authors should revisit the whole manuscript and overcome the shortcomings and resubmit to Plos One. However, as things stand at the moment, my decision is of rejection. ****** 6. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files. If you choose “no”, your identity will remain anonymous but your review may still be made public. Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy. Reviewer #1: Yes: Allam Jaya Prakash Reviewer #2: Yes: Anandakumar H Reviewer #3: No ******** [NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.] While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org. Please note that Supporting Information files do not need this step. Attachments Attachment Submitted filename: Review_PLOS2.docx https://doi.org/10.1371/journal.pone.0274225.r001
Revision 1
2 Aug 2022 Author Response Reviewer #1: 1. Kindly write the abstract in a concise and succinct manner, there is no requirement of background basic study in the abstract. The first three to four lines can shift to the introduction. Based on the suggestion, the abstract is revised and a few lines were shifted to the introduction section. The following modification is carried out and included in the revised manuscript. Cardiovascular disease is currently a severe hazard to life and health, and its incidence is increasing year after year. As a result, it is critical to concentrate on cardiovascular disease diagnosis and prevention. An electrocardiogram (ECG) is the most popular non-invasive screening test to identify a specific cardiac issue. It keeps track of the heart's function throughout time. 2. Use convolutional neural network short term in abstract. In the abstract, Convolutional Neural Network is replaced by “CNN” 3. Why authors are concentrated on only four beats, any specific reason? Right Bundle Branch Block (RBBB), Premature Atrial Contraction (PAC), and Premature Ventricular Contraction (PVC) are some of the significant heartbeat problems investigated in the research paper. These four beats are the major types for ECG analysis. 4. Better to use any customized network not transfer learning Thanks to the reviewer for the suggestion. In this research, improved AlexNet along with FFT is used to process ECG signals. Transfer learning can also be adapted to process EEG signals rather than ECG signals using the same network architecture. 5. Figure 2 is copied from the internet Figure 2 is a common picture of the ECG signal used to represent the P, Q, R, and S factors. 6. I didn’t find any comparison of the proposed method with existing literature In the literature section, the following statements were introduced as per the suggestion. There are numerous accounts of ECG beat classification using a variety of techniques, including artificial neural networks (ANN), self-organizing maps (SOM), support vector machine (SVM) classifiers, soft independent modeling of class analogy (SIMCA), deep learning, and complex support vector machines (CSVM), decision trees, and convolution neural network (CNN). SVM exhibits poor behavior in the face of class instabilities, but methods of handling have been developed, including hierarchical SVM or SVM weighted by each class. The drawback is that, in very large problems, it may not always be possible to find an optimization, and the training algorithm is not guaranteed to achieve a global optimization. Due to the high computational cost during the test phase, the KNN-k nearest neighbor method (KNN) has limited application in real-world scenarios. Decision Tree is not commonly used because it can only handle a limited number of features and the rule-based approach performs the worst. The results of the existing method are compared with the proposed method. 7. Write specific author contribution Major contribution: • Numerous algorithms have been used in research, including random forests and decision tree ensembles as well as the non-linear classifier Support Vector Machine (SVM). Manual feature extraction is necessary for this algorithm. In this research neural networks are used to address the issue in medical diagnostics. This increases the effectiveness of training techniques, makes it possible for the algorithm to be used "end-to-end," and makes it simpler for a wider range of people if large datasets are available. 8. MIT-BIH full form missed The full form of MIT-BIH is Massachusetts Institute of Technology-Beth Israel Hospital. In the revised manuscript, the full form is provided. 9. Please remove unnecessary capitalizations in the manuscript Unnecessary capitalizations are removed in the revised manuscript. 10. Please mention important major contributions only The goal of this research is to develop a deep learning-based method to detect arrhythmias automatically without the use of manual feature identification. 11. Quality of the images are very poor, and not visible also The quality of the images is enhanced in the revised manuscript. 12. As per my knowledge authors are used Python for implementation, but network diagram missed? Instead of the network diagram, the visualization of the AlexNet is provided in Figure 5. 13. Needs to include ROC curves, and precision-recall curves The above ROC curve plot is included in the revised manuscript. 14. Grammatically needs to recheck again The revised manuscript is checked with Grammar correction using a grammar correcting tool. 15. Needs to recheck the structure of the paper as Introduction, Literature, and Motivation, Contributions of the proposed work, Database, Proposed methodology, Experimental results, Discussion, Conclusion + Future scope. The structure of the paper is reframed as per the comments. 16. Needs to include ablation study (If possible) Ablation was carried out wherever possible 17. Conclusions also needs to re-write again The conclusion section is rewritten again with appropriateness and the future work is also included. 18. Please cite recent scripts as below The references recommended by the reviewer are also included in the revised manuscript as follows, • Prakash, A. J., Samantray, S., Bala, C. L., & Narayana, Y. V. (2021). An Automated Diagnosis System for Cardiac Arrhythmia Classification. In Analysis of Medical Modalities for Improved Diagnosis in Modern Healthcare (pp. 301-313). CRC Press. • Prakash, A. J., & Ari, S. (2019, December). AAMI standard cardiac arrhythmia detection with random forest using mixed features. In 2019 IEEE 16th India Council International Conference (INDICON) (pp. 1-4). IEEE. • Allam, J. P., Samantray, S., & Ari, S. (2020). SpEC: A system for patient specific ECG beat classification using deep residual network. Biocybernetics and Biomedical Engineering, 40(4), 1446-1457. • Prakash, A. J., & Ari, S. (2019). A system for automatic cardiac arrhythmia recognition using electrocardiogram signal. In Bioelectronics and Medical Devices (pp. 891-911). Woodhead Publishing. • Hammad, M., Pławiak, P., Wang, K., & Acharya, U. R. (2021). ResNet‐Attention model for human authentication using ECG signals. Expert Systems, 38(6), e12547. • Tuncer, T., Dogan, S., Pławiak, P., & Acharya, U. R. (2019). Automated arrhythmia detection using novel hexadecimal local pattern and multilevel wavelet transform with ECG signals. Knowledge-Based Systems, 186, 104923. • Książek, W., Gandor, M., & Pławiak, P. (2021). Comparison of various approaches to combine logistic regression with genetic algorithms in survival prediction of hepatocellular carcinoma. Computers in Biology and Medicine, 134, 104431. Reviewer #2: The authors performed good research on the convolutional neural network technique to analyze ECG signals using improved FFT-based AlexNet classifier. However, justification is required for the following comments, 1. Highlight the problem statement in the introduction section. The problem statement is highlighted in the introduction section. 2. What are the merits of the proposed algorithm over traditional algorithms compared in the research work? Random forests and decision tree ensembles as well as the non-linear classifier Support Vector Machine (SVM) are compared in this research along with the proposed classifier. Manual feature extraction is necessary for this algorithm. In this research neural networks are used to address the issue in medical diagnostics. This increases the effectiveness of training techniques, makes it possible for the algorithm to be used "end-to-end," and makes it simpler for a wider range of people if large datasets are available. 3. The related work section needs to be strengthened. I recommend the authors discuss a few more recent research works. Recent literature related to the research work is included and cited. 4. In table 1, what are PVC, APC, and RBBB? Right Bundle Branch Block (RBBB), Premature Atrial Contraction (PAC), and Premature Ventricular Contraction (PVC) are some of the significant heartbeat problems investigated in this research. 5. What is the modification done in AlexNet architecture for stating it as improved AlexNet? Thanks to the reviewer for the suggestion. The following characteristics distinguish the improvements proposed in the paper from the traditional AlexNet network classification algorithm: • An additional convolution layer is introduced to the original AlexNet structure and the max-avg pooling technique is used to preserve the local receptive fields. This will provide more accurate image feature information. • The global average pooling (GAP) layer is substituted for the original fully connected FC layer, which significantly reduces the over-fitting effect without affecting the final features. The final result is unaffected in the absence of numerous calculations of network parameters, increasing network speed. • The LRN layer is added to the convolution layer to avoid some unnecessary numerical issues; this effectively avoids neuron saturation. The BN layer in the proposed method is used after the convolution of each layer. 6. The introduction is too long, please remove the repeated idea. No need to explain much in detail. More explanation should be about the novelty of the proposed method. The introduction section is reduced and the novelty of the proposed methodology is briefed. 7. In section 3.4, FFT is used for feature extraction. How the extraction was done and what are the extracted features? Include the expression for the same corresponding to the proposed architecture. Based on the suggestion, section 3.4 is revised. In this study, the entire segment associated with the Q, R, and S-peak, and through these deflections QRS complex and RR interval wave was identified and included in the revised manuscript. Reviewer #3 1. The manuscript in its current form is ambiguous, confusing and unclear. The manuscript is restructured clearly. 2. Narrations are incoherent. The narrations represented in the manuscript are updated. 3. Many sentences are presented as if they were section headings. All the sentences are reframed and introduced in the subsections. 4. There are repetitions of the same sentences throughout the manuscript. Repetitions are corrected in the revised manuscript. 5. Figures are barely visible and sometimes (Figure 4) tend not to depict what the authors are stating in the text. The quality of the images is enhanced for better visibility. 6. Some figures tend to explain things better than how the authors narrate things, which again goes towards the disadvantage of the authors. The description of the figures is included in the revised manuscript. 7. In the manuscript, the authors write “The AlexNet architecture is depicted in Figure 5” and then the caption of Figure 5 reads, “Architecture of the improved AlexNet model”. I wonder whether Figure 5 is the original AlexNet or the authors’ improved version. The AlexNet network structure is given in Figure 5. The improved AlexNet network structure is given in Figure 6. 8. Acronyms have not been properly introduced. The entire manuscript is rechecked and the acronyms are properly mentioned. 9. Data distributions/dataset analyses have not been provided. Data distributions are highlighted in the dataset section 3.2. 10. Authors claim to propose AlexNet based on FFT in the Abstract, which is wrong. AlexNet is already a CNN and the authors are proposing to use FFT for feature extraction of ECG signals, and later use AlexNet for classification. Or rather, they are improving AlexNet architecture as the authors claim. Again, the language needs to be sorted out here. The abstract is rewritten with correctness. This paper proposes the use of an ECG arrhythmia classification scheme based on Fast Fourier Transform (FFT) for feature extraction and an improved AlexNet classifier to differentiate between four types of arrhythmias conditions that were obtained from records. 11. Then, the authors write in Section 3.4, Paragraph 2, “Fast Fourier transform technology has successfully extracted feature components from ECG data, such as PQRST signals”. If FFT has done it successfully, what exactly are the authors accomplishing in the current manuscript? Each complex ECG signal has a real and an imaginary component. The Fast Fourier Transform removes low frequencies from the ECG signal. The inverse fast Fourier transform is used to remove noise. The Fast Fourier Transform is used to transform the input signal from the dataset after it has been preprocessed by removing nulls. The extracted features were suitable for detecting arrhythmia in patient records, and the results were obtained using Matlab. The created Excel file can then be used to classify and detect various anomalies. 12. The authors write in Section 3.5, last Paragraph, “Each ECG image is transmitted to the improved AlexNet in this stage”. Which stage are the authors referring to here? Again, one can see the issue with the language. The description of the stage is included in the revised manuscript. Each ECG image is transmitted to the improved AlexNet in this classification stage. The individual ECG beats that were recovered from the Fourier coefficients were further divided into two groups for training and testing to facilitate classification. Using the FFT coefficient as the function vector in the classifier's input vector, the improved AlexNet classifier is used to differentiate between the four different types of ECG arrhythmias. Attachments Attachment Submitted filename: Response to reviewer comments.docx https://doi.org/10.1371/journal.pone.0274225.r002
8 Aug 2022 Decision Letter - Mohamed Hammad, Editor PONE-D-22-16995R1Classification of ECG Signal using FFT based Improved Alexnet ClassifierPLOS ONE Dear Dr. M, Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process. ============================== Please submit your revised manuscript by Sep 22 2022 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file. Please include the following items when submitting your revised manuscript: A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'. A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'. An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'. If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter. If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols. We look forward to receiving your revised manuscript. Kind regards, Mohamed Hammad, Ph.D. Academic Editor PLOS ONE Journal Requirements: Please review your reference list to ensure that it is complete and correct. If you have cited papers that have been retracted, please include the rationale for doing so in the manuscript text, or remove these references and replace them with relevant current references. Any changes to the reference list should be mentioned in the rebuttal letter that accompanies your revised manuscript. If you need to cite a retracted article, indicate the article’s retracted status in the References list and also include a citation and full reference for the retraction notice. [Note: HTML markup is below. Please do not edit.] Reviewers' comments: Reviewer's Responses to Questions Comments to the Author 1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation. Reviewer #1: All comments have been addressed Reviewer #2: All comments have been addressed ******** 2. Is the manuscript technically sound, and do the data support the conclusions? The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented. Reviewer #1: Yes Reviewer #2: Yes ****** 3. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: Yes Reviewer #2: Yes ****** 4. Have the authors made all data underlying the findings in their manuscript fully available? The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified. Reviewer #1: Yes Reviewer #2: Yes ****** 5. Is the manuscript presented in an intelligible fashion and written in standard English? PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here. Reviewer #1: Yes Reviewer #2: Yes ****** 6. Review Comments to the Author Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters) Reviewer #1: Authors are incorporated all my comments. Only two minor suggestions from my side 1. Figure 2 should be changed; the author can generate one ECG beat segment using MATLAB or Python. The copied figure from the internet should be replaced with a new figure before publication. Reviewer #2: The author has addressed all the necessary comments and the revised manuscript is improved . Recommended for further publications ****** 7. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files. If you choose “no”, your identity will remain anonymous but your review may still be made public. Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy. Reviewer #1: Yes: Allam Jaya Prakash Reviewer #2: Yes: Anandakumar H ******** [NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.] While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org. Please note that Supporting Information files do not need this step. https://doi.org/10.1371/journal.pone.0274225.r003
Revision 2
14 Aug 2022 Author Response Reviewer #1: Authors are incorporated all my comments. Only two minor suggestions from my side. Comment 1: Figure 2 should be changed; the author can generate one ECG beat segment using MATLAB or Python. Response: Thank you for valuable suggestion. As per the comment, one ECG beat segment is generated using python and the same is included in the revised manuscript. Comment 2: The copied figure from the internet should be replaced with a new figure before publication. Response: Figure 2 is replaced with the new one in the revised paper. Attachments Attachment Submitted filename: Response to reviewer comments Ver 2.0.docx https://doi.org/10.1371/journal.pone.0274225.r004
24 Aug 2022 Decision Letter - Mohamed Hammad, Editor Classification of ECG Signal using FFT based Improved Alexnet Classifier PONE-D-22-16995R2 Dear Dr. M, We’re pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it meets all outstanding technical requirements. Within one week, you’ll receive an e-mail detailing the required amendments. When these have been addressed, you’ll receive a formal acceptance letter and your manuscript will be scheduled for publication. An invoice for payment will follow shortly after the formal acceptance. To ensure an efficient process, please log into Editorial Manager at http://www.editorialmanager.com/pone/, click the 'Update My Information' link at the top of the page, and double check that your user information is up-to-date. If you have any billing related questions, please contact our Author Billing department directly at authorbilling@plos.org. If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact. If they’ll be preparing press materials, please inform our press team as soon as possible -- no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org. Kind regards, Mohamed Hammad, Ph.D. Academic Editor PLOS ONE Additional Editor Comments (optional): Reviewers' comments: https://doi.org/10.1371/journal.pone.0274225.r005
Formally Accepted
7 Sep 2022 Acceptance Letter - Mohamed Hammad, Editor PONE-D-22-16995R2 Classification of ECG Signal using FFT based Improved Alexnet Classifier Dear Dr. Kumar M.: I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now with our production department. If your institution or institutions have a press office, please let them know about your upcoming paper now to help maximize its impact. If they'll be preparing press materials, please inform our press team within the next 48 hours. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information please contact onepress@plos.org. If we can help with anything else, please email us at plosone@plos.org. Thank you for submitting your work to PLOS ONE and supporting open access. Kind regards, PLOS ONE Editorial Office Staff on behalf of Dr. Mohamed Hammad Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0274225.r006

Open letter on the publication of peer review reports

PLOS recognizes the benefits of transparency in the peer review process. Therefore, we enable the publication of all of the content of peer review and author responses alongside final, published articles. Reviewers remain anonymous, unless they choose to reveal their names.

We encourage other journals to join us in this initiative. We hope that our action inspires the community, including researchers, research funders, and research institutions, to recognize the benefits of published peer review reports for all parts of the research system.

Learn more at ASAPbio .