Next Article in Journal
A Prototype Plant for Oilseed Extraction: Analysis of Mass and Energy Flows
Next Article in Special Issue
Total Repair Cost Simulation Considering Multiple Probabilistic Measures and Service Life
Previous Article in Journal
An Exploratory Study of Consumer Food Waste Attitudes, Social Norms, Behavioral Intentions, and Restaurant Plate Waste Behaviors in Taiwan
Previous Article in Special Issue
Analysis of Major Environmental Impact Categories of Road Construction Materials
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Sustainability
Volume 12
Issue 22
10.3390/su12229785
Review Report
sustainability-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
Article
Peer-Review Record

MultiDefectNet: Multi-Class Defect Detection of Building Façade Based on Deep Convolutional Neural Network

Sustainability 2020, 12(22), 9785; https://doi.org/10.3390/su12229785
by Kisu Lee 1, Goopyo Hong 2, Lee Sael 3, Sanghyo Lee 4,* and Ha Young Kim 1,*
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Sustainability 2020, 12(22), 9785; https://doi.org/10.3390/su12229785
Submission received: 4 November 2020 / Revised: 20 November 2020 / Accepted: 20 November 2020 / Published: 23 November 2020
(This article belongs to the Special Issue Sustainability and Industry 4.0 in Civil and Infrastructure Engineering)

Round 1

Reviewer 1 Report

The article is well structured and deals with an important topic.

The issue of building maintenance is increasingly topical, but the increasing complexity of the construction process, changes to sustainability parameters and globalisation make upgrading operations increasingly difficult. The authors are asked how it is possible to “develop a model capable of detecting multiclass defects from real-world image data obtained from various building facades” when there is an ever-increasing number of variables, with very different features?

The façade depends on the structure, the materials, the technologies, the quality of the installation, its appropriateness in the location, for the air pollution, the acoustic standards, etc.

Thinking about all the variables of an element (facade) is complex, even more so if you think about the building.

The whole must then be seen with the expected duration of the element and therefore of the building. All this must lead to a rethink of how to manage maintenance.

Comments and Suggestions for Authors

What methods had been implemented in this research?  

Could the study be aimed at a precise facade technology placed in a building that is architecturally and structurally defined and above all contextualised?

Author Response

Thank you for your comments. Please check the answer to your comments through the attached file.

Author Response File: Author Response.doc

Reviewer 2 Report

The article proposes an artificial neural network for detecting damage to building facades.

The authors focus on the detailed specification of the approach used. Little space has been devoted to the very nature of the type of damage and the circumstances of its occurrence. The conclusions could be broader with a clear emphasis on the practical value of the proposed approach and the limitations.

Author Response

Thank you for your comments. Please check the answer to your comments through the attached file.

Author Response File: Author Response.doc

Back to TopTop