A deep learning model for building type estimation based on building names

Application to a micro land use analysis

Abstract

To consider the development of urban areas and future planning, it is important to analyze the micro land use transition of architectural units. The purpose of this study is to develop a machine learning model to estimate building type from building name and obtain micro land use transition data. The target area is the city center, where mixed building types are observed, and the types were classified into five types. The closer distance between the region to be studied and applied is better percentage of correct answers. Although it is better to collect the training data close to the area of application,even when the data is collected uniformly across the country, a useful generalied model a better result, than the human correct response rate.