Development and Comparison of Prediction Models for Sanitary Sewer Pipes Condition Assessment Using Multinomial Logistic Regression and Artificial Neural Network
Round 1
Reviewer 1 Report
This research aims to predict sanitary sewer pipes condition rating using inspection and condition assessment data. Two prediction models are developed. Experimental verification is conducted to show the performance of the models. My comments are as follows:
- Presentation of the paper is not ready for review. Please improve it
- The paper should be rewritten more concisely and clearly. Even from the abstract, Lines 28-29 “The results of this research reveal that MLR and ANN models are acceptable”, this sentence is unclear.
- There is no chapter number, citing method is not correct. Remove border of the figures. Some equations should be rewritten in the mathematic form. Quality of some figures should be improved, for example Fig. 5,6, 7.
- Architecture of ANN in Fig. 4 is not quite correct. Please check other architecture of the ANN model
- The introduction and literature review part is too long and not easy to follow. It should be divided.
- Please explain the new contributions and the novelties of this study, in comparision with the literature review.
- The theoretical part of the prediction models should be enhanced. For examples, activation function of the neuron? Training process, training algorithm,… I suggest the authors to read the paper related to ANN prediction to improve their study.
Author Response
The authors would like to thank the reviewer for the valuable comments, which certainly improved the quality of the paper.
Author Response File: Author Response.pdf
Reviewer 2 Report
This paper presents novel multinomial logistic regression (MLR) and artificial neural network (ANN) models to predict sanitary sewer pipelines condition rating using inspection and condition assessment data. MLR and ANN models have been developed by using city of Dallas' data. The MLR model is built using 80% of randomly selected data and validated using the remaining 20% of data. The ANN model is adequately trained, validated, and tested. The MLR and ANN models enable engineering accurate assessment of sanitary sewer pipelines condition rating, an important feature in providing the safe transportation of wastewater to treatment plants.
The authors of the paper are to be congratulated for their excellent research work. The paper is well written and sound in presentation. I recommend that the paper is accepted for publication in Sustainability.
Author Response
The authors would like to thank the reviewer for the valuable comments.
Author Response File: Author Response.pdf
Reviewer 3 Report
The paper is good quality, well structured and the content is clearly presented.
However, the quality of the figures must be improved. It is suggested to provide figures in vectorial format.
Author Response
The authors would like to thank the reviewer for the valuable comments, which certainly improved the quality of paper.
Author Response File: Author Response.pdf