Research on a Visual Comfort Model Based on Individual Preference in China through Machine Learning Algorithm
Round 1
Reviewer 1 Report
This study developed a visual satisfaction model using data collected by an experiment with four types of machine learning algorithms. The model is used to predict appropriate vertical illuminance for a specific occupant. This research is interesting and overall well written.
Author Response
Point 1: the research design, questions, hypotheses and methods clearly can be improved.
Response 1: Thank you for your excellent suggestions which have helped us to greatly improve the paper. We have updated the reason and the process why we choose the hierarchy model in the new manuscript.
“In FMEA method, the risk assessment of failure mode always involves multiple team members. Because different experts may have different knowledge and personal preferences, they will express various and subjective views on the same failure mode. The failure modes of visual satisfaction are various and subjective, which is suitable to transform into quantitative set.
To solve the limitations of expert’s bounded rationality, the weight of each expert comes from three different dimensions: professional relevance, experience and title. The expert weight evaluation table is constructed in Table 3 [39,41]. Based on the professional relevance, experience and title of each expert, the weight is determined by equation (10).
Reviewer 2 Report
The work focuses on improving the indoor visual environment and reducing office consumption based on individual preference characteristics. The indicators of visual comfort are ranked by the failure mode and effect analysis (FMEA) method combined with the cloud model and TOPSIS technique. Personalized data about visual environment preference are obtained from the experiment and trained by classification tree, random forest, kernel support vector machine, and Gaussian mixed model. The results show that random forest has the best prediction performance. The paper seems to be interesting scientific work. However, some shortcomings must be eliminated before accepting. The list of my comments is as follows:
1. The abstract must be rewritten to show motivation and justification to undertake research clearly. Besides, the contribution must be emphasised stronger.
2. The introduction must be extended. A wide description of the background is needed.
3. The justification of the used method is insufficient. First of all, the chosen method are correct. However, in the paper, justification is omitted. I suggest using some reference literature to show why this method is used, i.e., 10.3390/sym12091549 and 10.1016/j.procs.2020.09.014 and fuzzy assessment information 10.1016/j.eswa.2021.115088
4. Figures caption one time is written by using capitalistic and one time by using normal letters. (Please fix it as FIGURE 2. It should be Figure 2.)
5. The figures are too small and poor of quality, e.g. figure 2.
6. Formula 17 should be fixed. There is * instead multiply (dot) sign.
7. Symbols 18-21 must be defined after the formulas.
8. The future directions research should be added to the Conclusions section.
Author Response
Please see the attachment.
Author Response File: 
Author Response.docx
Reviewer 3 Report
The following review is made until line 245 of the manuscript entitled “Research on a visual comfort model based on individual preference in China machine learning algorithm”:
- Introduction is kind of ambiguous describing different visual comfort models with different characteristics. My point is that the features of the model developed in the manuscript are not clear. In some part of the Introduction section, glare is mentioned as a factor of visual discomfort, but the mention is not related to other factors such as vertical/horizontal illuminance etc. This section needs an improvement on the description of different visual comfort models compared to the model of the manuscript.
- The reason why I stopped where the equations begin is the lack of nomenclature, making a non-sense task to review the mathematical model. Please place the description of the variables of the model.
- In line 245, it is stated that five experts were asked to make hierarchy of the proposed model. In my opinion, the scientific rigor is very weak as is described in the document. At least, a clearly described method of the hierarchy choosing process must be presented.
- So far, a review on the scientific writing should be carried out.
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Round 2
Reviewer 2 Report
The paper has been improved according to my suggestion. Therefore, I propose accepting in the current form.
Author Response
Point 1:Is the content succinctly described and contextualized with respect to previous and present theoretical background and empirical research (if applicable) on the topic?
Response 1: Thank you for your suggestions. We regret that we didn’t introduce the background of China’s energy consumption. We have added the percentage of energy consumption in China. The description is as follows:
“In 2018, the energy consumption of China's construction industry was 2.147 billion tce, accounting for 46.5% of China's total energy consumption. During the operation and maintenance, energy consumption was 1 billion tce, which accounts for 46.6% of the energy consumption of the building industry [3]. As a prominent building system, the lighting system consumes approximately 14% of energy in the operation phase.”
Reviewer 3 Report
After verifying the addressed comments for the Review Round 1, I’ve got the following comments:
- Please make a reference of the software Python (version, company etc).
- State in the abstract the main results: the best performance of RF and KSVM as machine learning methods, for instance.
- Line 42: “However” is not the best word to relate the two sentences of the paragraph.
- Line 45: Establish a percentage of consumption in China. If it doesn’t exist, state it.
Author Response
Please see the attachment.
Author Response File: Author Response.docx
