Novel CNN-Based Approach for Reading Urban Form Data in 2D Images: An Application for Predicting Restaurant Location in Seoul, Korea

被引:5
|
作者
Yang, Jeyun [1 ]
Kwon, Youngsang [1 ,2 ]
机构
[1] Seoul Natl Univ, Dept Civil & Environm Engn, Seoul 08826, South Korea
[2] Seoul Natl Univ, Adv Inst Convergence Technol, Smart City Res Ctr, Suwon 16229, South Korea
基金
新加坡国家研究基金会;
关键词
convolutional neural network; CNN; restaurant location; retail location; urban retail store; deep learning; classification model; RETAIL LOCATION; CITIES; GENTRIFICATION; MORPHOLOGY; FRAMEWORK; DEMAND; FOOD;
D O I
10.3390/ijgi12090373
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Artificial intelligence (AI) has demonstrated its ability to complete complex tasks in various fields. In urban studies, AI technology has been utilized in some limited domains, such as control of traffic and air quality. This study uses AI to better understand diverse urban studies data through a novel approach that uses a convolutional neural network (CNN). In this study, a building outline in the form of a two-dimensional image is used with its corresponding metadata to test the applicability of CNN in reading urban data. MobileNet, a high-efficiency CNN model, is trained to predict the location of restaurants in each building in Seoul, Korea. Consequently, using only 2D image data, the model satisfactorily predicts the locations of restaurants (AUC = 0.732); the model with 2D images and their metadata has higher performance but has an overfitting problem. In addition, the model using only 2D image data accurately predicts the regional distribution of restaurants and shows some typical urban forms with restaurants. The proposed model has several technical limitations but shows the potential to provide a further understanding of urban settings.
引用
收藏
页数:21
相关论文
共 15 条
  • [11] A Data-Driven Approach to Generating Stochastic Mesoscale 3D Shale Volume Elements From 2D SEM Images and Predicting the Equivalent Modulus
    Hong, Yang
    Li, Xiang
    Gao, Yue
    Liu, Zhanli
    Yan, Ziming
    Zhuang, Zhuo
    INTERNATIONAL JOURNAL OF APPLIED MECHANICS, 2023, 15 (10)
  • [12] Hybrid-COVID: a novel hybrid 2D/3D CNN based on cross-domain adaptation approach for COVID-19 screening from chest X-ray images
    Bayoudh, Khaled
    Hamdaoui, Faycal
    Mtibaa, Abdellatif
    PHYSICAL AND ENGINEERING SCIENCES IN MEDICINE, 2020, 43 (04) : 1415 - 1431
  • [13] Hybrid-COVID: a novel hybrid 2D/3D CNN based on cross-domain adaptation approach for COVID-19 screening from chest X-ray images
    Khaled Bayoudh
    Fayçal Hamdaoui
    Abdellatif Mtibaa
    Physical and Engineering Sciences in Medicine, 2020, 43 : 1415 - 1431
  • [14] 3D Object Reconstruction from a Single 2D Image: Performance of Two Novel Frameworks Based on Lightweight CNN Architectures and Free-Form Deformation of Meshes
    Pradhan, Saurabh
    Madhusudhanan, Kiran
    Munoz-Giraldo, Leandro
    Faruq, MohiUddin
    Jomaa, Hadi
    ELEVENTH INTERNATIONAL CONFERENCE ON GRAPHICS AND IMAGE PROCESSING (ICGIP 2019), 2020, 11373
  • [15] Flood Susceptibility Mapping Using Image-Based 2D-CNN Deep Learning: Overview and Case Study Application Using Multiparametric Spatial Data in Data-Scarce Urban Environments
    Ouma, Yashon O.
    Omai, Lawrence
    INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS, 2023, 2023