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.
Congratulations. Two reviewers agreed the paper is ready for publication.
[# PeerJ Staff Note - this decision was reviewed and approved by Jyotismita Chaki, a PeerJ Section Editor covering this Section #]
no comment
no comment
no comment
The author has made modifications according to the premise's suggestions. I suggest accepting the article.
clear
well defined
Results provided
author made changes based on review comments
Please follow the reviewer's recommendations, especially reviewer 1.
**PeerJ Staff Note:** Please ensure that all review, editorial, and staff comments are addressed in a response letter and that any edits or clarifications mentioned in the letter are also inserted into the revised manuscript where appropriate.
The paper is well written, understandable and uses a good English style. Raw data (code) is provided and complete.
I believe there are some issues that need to be resolved:
1. The introduction correctly introduces the objectives of the paper, but the background does not reflect quite a few of the contributions combining LSTM and ARIMA. The rest of the references are significant and appropriated.
2. Figures are correct and relevant, but a more detailed description would be needed in the text of the paper related to figures 3 and 6.
Some aspects should be improved:
1. The paper presents an interesting idea, although not a completely novel one. The multi-source prediction model is novel but not the hybridization ARIMA-LSTM.
2. The idea of using multi-source data is very interesting, but its use in the proposed model should be better explained and its contribution should be explained in more detail.
3. The Fully Connected (FC) layer of the model should be better described.
4. The evaluation indicators used in the model should be justified, or at least commented.
5. I wonder if there is not some error in the ablation study, since it talks about both the ARIMA-LSTM model and the ARIMA-LSTM-FC model. It is clear that until you apply the FC layer you do not get the final unified results, so there really is no ARIMA-LSTM component result. This should be adequately clarified in the paper.
Conclusions are consistent with the results and the planed objectives, beyond the misunderstanding regarding ARIMA-LSTM and ARIMA-LSTM-FC.
The abstract needs to be improved, with a focus on introducing the content of this study.
1. The main content of the article is to use FC to combine the ARIMA-LSTM model. So, how should the ARIMA-LSTM model mentioned in Figure 4 be combined?
2. Simply optimizing the ARIMA-LSTM model with FC lacks innovation and further improvement is needed. Lack of innovation, significant modifications are needed here.
The conclusion should provide a more detailed explanation of which indicators of the methods used in the article are better than other models, and whether this result is universal.
Authors proposed an ARIMA-LSTM (Autoregressive Integrated Moving Average and Long Short-Term Memory ) model for predicting future cases and utilize multi-source data to enhance prediction performance.
Please see additional comments.
Please see additional comments.
Reviewer Comments:
1. List of keywords missing
2. Proposed work flow diagram missing
3. Dataset details can be specified in a table
4. What is the training-testing ratio?
Above are my comments.
Paper can be accepted with revisions.
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.