Next Article in Journal
Challenges with Verifying Microbial Degradation of Polyethylene
Next Article in Special Issue
The Role of Nanoparticle Shapes and Structures in Material Characterisation of Polyvinyl Alcohol (PVA) Bionanocomposite Films
Previous Article in Journal
Antibacterial, Flexible, and Conductive Membrane Based on MWCNTs/Ag Coated Electro-Spun PLA Nanofibrous Scaffolds as Wearable Fabric for Body Motion Sensing
Previous Article in Special Issue
Development of Coffee Biochar Filler for the Production of Electrical Conductive Reinforced Plastic
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Polymers
Volume 12
Issue 1
10.3390/polym12010122
Review Report
polymers-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

Printed Edition

A printed edition of this Special Issue is available at MDPI Books....
share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
Article
Peer-Review Record

Application of Adaptive Neuro-Fuzzy Inference System in Flammability Parameter Prediction

Polymers 2020, 12(1), 122; https://doi.org/10.3390/polym12010122
by Rhoda Afriyie Mensah 1, Jie Xiao 1, Oisik Das 2, Lin Jiang 1,*, Qiang Xu 1,* and Mohammed Okoe Alhassan 1
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Polymers 2020, 12(1), 122; https://doi.org/10.3390/polym12010122
Submission received: 12 December 2019 / Revised: 27 December 2019 / Accepted: 1 January 2020 / Published: 5 January 2020
(This article belongs to the Special Issue Performance and Application of Novel Biocomposites)

Round 1

Reviewer 1 Report

An innovative method to recover flammability parameters using statistical ANFIS approach is described. This is an interesting paper and it deserves to be published. However It will be good if some more comments are added.

for example:

what is the criterion for selecting fuzzing rules, have they some physical meaning?

what is the criterion adopted to select training and test samples in the provided simulation?

how well this method can predict results outside of the training range?

It is possible to use this method to predict cone calorimeter results from MCC results?

Can you commet on why HRC is better predicted than THR?

figure 5: colors in the insert "logical operations" does not meet with the model structure.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

This paper presents a machine learning based approach to predicting material flammability data in the microcombustion calorimeter (MCC). An Adaptive neuro-fuzzy inference system (ANFIS) was implemented in this study to predict the heat release capacity (HRC) and total heat released (THR) of polystyrene tested in the MCC. The following comments need to be addresses before the paper is published.

Lines 101-113, define how the HRC and THR were calculated from the specific HRR.

Line 171, Describe how the ANFIS implemented (language/program, common subroutines, etc) and computer used for training.

Lines 313 – 317. Provide a plots comparing the predictions of the ANFIS, FFBPNN and data for both HRC and THR to better show the level of difference between the models.

Lines 313-317, what is the difference in training time for the ANFIS and FFBPNN methods providing computing resource for training.

ANNs typically need large amounts of data to achieve good prediction. In this work, only a limited amount of data was used. Is this what affected the FFBPNN accuracy in Table 9?

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Back to TopTop