Building Damage Assessment Using Deep Learning: Bibliometric Analysis

Natural catastrophes have become one of the hottest subjects as a result of the harm they have caused to human structures. In recent years, research pertaining to the discipline of building damage assessment (BDA), which seeks to study the effect of damage on structures, has grown substantially. This bibliometric study seeks to determine the state of the art in the subject of Building Damage Assessment Using Deep Learning by examining several papers. The method used (Donthu et al., 202) divides the steps of bibliometric analysis into four parts: identifying the field of research to be analyzed, identifying the methods used in bibliometric analysis, collecting research data with similar fields, and executing and analyzing the results of bibliometric analysis on the collected data. In the data collecting and analysis portion (Garza-Reyes, 2015), the identification of data search keywords, the execution of data searches, the enhancement of search results, statistical data processing, and data analysis are carried out. Several research questions pertaining to trends, influences, themes, authors, and other crucial components of doing research in the area of building damage assessment are answered using these techniques. The outcome is the mapping and resolution of all research problems, as well as the acquisition of bibliometric analysis-related data. The provided findings have been mapped into several types of visualization, including network % clustering graphs, overlay graphs, and density graphs, as well as other forms of visualization that will aid researchers in comprehending the study circumstances in the field. It is envisaged that this bibliometric study would make it simpler for scholars to do research in related topics.