Heat Load Forecasting of Marine Diesel Engine Based on Long Short-Term Memory Network
Round 1
Reviewer 1 Report
The paper is nicely written and the problem is important. The problem is well-defined but an example/figure can enhance its understanding. The proposed method is well-explained and is innovative. The experiments are convincing. However, there are few comments that should be addressed by the authors.
-The introduction section can be improved by a motivational example. The authors need to better explain the context of this research, including why the research problem is important.
-In experimental evaluations add confidence intervals in the bar graphs to see the variations in the values.
-The algorithm pseudocode of the proposed model should be included.
-LSTM models consume higher memory and running time. How authors address this issue?
- Related work section should be enhanced by adding 5-6 more relevant articles. Moreover, some recent papers on Fault Tolerant Fire Detection in Smart Buildings and application of LSTM in Mobile Networks can enhance the visibility of the proposed work e.g,
COME-UP: Computation Offloading in Mobile Edge Computing with LSTM Based User Direction Prediction
A Fault Tolerant Surveillance System for Fire Detection and Prevention Using LoRaWAN in Smart Buildings
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Reviewer 2 Report
Note: Please check document properties and remove reviewer information, if any.
Comments for author File: Comments.pdf
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Reviewer 3 Report
· Abstract: “The model was applied to validate ship data of the Shanghai Fuhai ship, and the experimental results showed that 20 the mean absolute percentage error (MAPE) of the model is the lowest at 0.089”
How is it possible to use a model to validate experimental results?
This mistake needs to be solved in the whole manuscript
· In Section 1 the Authors need to describe the current status on the investigated topic and then clearly state what knowledge gap their work will fill COMPARED TO the current status on the investigated topic
· Passive voice needs to be adopted in the whole manuscript
· The Authors need to get editing help from someone with full professional proficiency in English
· Accuracy of the employed experimental equipment is missing
· “Combining artificial experience with data-driven analysis is a novel approach to selecting the optimal feature set input model for predicting and obtaining enhanced prediction results”
There is nothing novel in this approach (it is just the combination of 2 well-known tools)
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Round 2
Reviewer 1 Report
The revised version has incorporated a number of improvements and discussions that address properly my previous concerns. The paper contains sufficient contribution and is now suitable for publication.
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Reviewer 2 Report
Comments for author File: Comments.docx
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Reviewer 3 Report
The Authors failed to deal with all my recommendations
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Round 3
Reviewer 2 Report
Pl. see the attached file
Comments for author File: Comments.pdf
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Reviewer 3 Report
Passive voice should be adopted in the whole manuscript
Author Response
Please see the attachment.
Author Response File: Author Response.docx