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.
All reviewers have confirmed that the authors have addressed all of their comments.
[# PeerJ Staff Note - this decision was reviewed and approved by Carlos Fernandez-Lozano, a 'PeerJ Computer Science' Section Editor covering this Section #]
Accepted
ok
ok
no
The suggestions in the previous review have been incorporated by the authors
The suggestions in previous review have been incorporated by the authors
The suggestions in previous review have been incorporated by the authors
The authors have addressed all the previously pointed issues successfully.
The authors have addressed all the previously pointed issues successfully
The authors have addressed all the previously pointed issues successfully
Please see both reviewer's comments. Reviewers suggest simplifying sentences, avoiding jargon, stating the problem and objectives early, providing overviews of VMD and DNN, ensuring a logical progression of ideas, and using clear headings and labeled figures. Additionally, it highlights the need to explain the significance of results, emphasize key findings, elaborate on the minimum fuzzy entropy criterion, and provide details on datasets, the DNN architecture, and training processes.
• It covers most of the available data but many references relevent to this review are missing.
• At the end of the introduction, the goal and tasks for achieving it must be clearly defined. And in the conclusions, give a numbered list in accordance with the solved tasks
• Authors should check the MS for grammatical errors.
OK
OK
This is a meaningful study, by incorporating these suggestions, the deep learning network can be fine-tuned to achieve higher accuracy and better generalization, ultimately enhancing the e-commerce product price prediction model's performance.
- Incorporate advanced architectural designs such as Residual Networks (ResNet) or Long Short-Term Memory (LSTM) networks to capture temporal dependencies more effectively.
- Use more hidden layers and neurons to increase the model's capacity, ensuring that dropout layers are appropriately placed to mitigate overfitting.
- Implement learning rate schedules or adaptive learning rate optimizers like Adam to dynamically adjust the learning rate during training, enhancing convergence speed and model performance.
- Introduce regularization techniques such as L2 regularization to prevent overfitting and improve generalization capabilities
- Utilize normalization or standardization techniques to scale the input features, ensuring uniformity across the dataset.
- Conduct an extensive hyperparameter tuning using grid search or randomized search to identify the optimal set of hyperparameters for the VMD-DNN model.
- Experiment with different batch sizes, learning rates, and activation functions to determine the most effective combination.
- Consider additional evaluation metrics such as Mean Squared Error (MSE) and R-squared (R^2) to provide a more comprehensive assessment of model performance.
- Use cross-validation techniques to ensure the robustness of the model's performance across different subsets of data.
There are some minor basic structure and format issues authors should address:
Simplify complex sentences to make the text more accessible.
Avoid unnecessary jargon to ensure readability for a broader audience.
Clearly state the problem and the objective of the study early on.
Consider providing a brief overview of VMD and DNN for readers unfamiliar with these concepts.
Ensure a logical progression of ideas. For example, start with the problem statement, followed by the methodology, results, and conclusion.
Use headings or subheadings to organize sections if appropriate.
Ensure all figures (e.g., Figure 1, Figure 2, Figure 3) are clearly labeled and referenced
Provide more context about the datasets used for evaluation.
Please re-write the algorithm1 in more professional way
Explain the significance of the results, such as why the error reduction rates and DS scores are noteworthy.
Emphasize the key findings and their implications more clearly
Elaborate on the minimum fuzzy entropy criterion for selecting the optimal modal number (K).
Include details on the architecture and training process of the DNN used for forecasting.
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.