Dec. 3, 2023
My initial perception of this document's contents was good and positive. The document is well-formatted, with text, figure plots, and "all the rest". However, we are now in 2023 and there is now available, for anyone to use, these technologies we all know on "social media" by "ChatGPT". So my assessment below takes into consideration all automation writing tools and apps I know to date.
What I did not analyze nor evaluated ============================
Text content, its quality, and grammar. I will leave this task when more important issues are solved on the document.
Experimental Data ====================================
Page 15 - Data availability
"No data was used for the research described in the article." << this statement is NOT TRUE. A research document with no data is ... a blog post or an internet article. Authors need to correct the statement to reflect what was previously written.
Artificial Neural Networks Modeling ========================
The authors mention the use of Keras library and Python language to model proposed ANN architectures however is missing on the document the following :
- is missing an algorithm of the ANN model used.
- is missing a link to a repository with the Python code programmed for this work.
- is missing on both text contents and mathematical equations utilized in the ANN model. For instance, what kind of models were utilized in the ANN algorithm? For instance, what was the loss function ? Optimizers used? Is any customization made to the ANN model ?
- The only data I could find quickly and visually about the performance of the proposed ANN model was in Figures 6 and 7.; Below Figure 7 authors use relative terminology to compare modeled results. This kind of comparison is not adequate for a scientific research document.
" ...stress-strain curve obtained from ANN is a good match..."
- is missing throughout the document, statistical analysis equations used, for instance, how was accuracy determined and compared with other models evaluated from the Digimat software application.
- Accuracy alone is insufficient to well characterize performance of the proposed ANN algorithm and to compare it with other models, in particular with the " Mori-Tanaka mean-field homogenization". Is well-known "accuracy" to be a good performance indicator in global analysis and assessment. For this work, It is required more, other statistical parameters, preferably ones that are able to infer performance with more detail and less "globally".
On a final note to both Editors and Authors ===========================
I find necessary the inclusion of a statement by the authors about the usage of any assisted writing tools. From simple MS Word add-ons such as Grammarly and Writefull to test automation tools such as ChatGPT and even more elaborate algorithms, able to deliver a complete document with text and graphics ready to be edited and replaced with simple copy & paste functionality.
My final recommendation is to accept pending a major revision to the document in accordance with what is previously stated.