|
|
|
|
|
通过深度学习和街景图片评估城市社会、环境及健康的不均衡状况 |
|
|
论文标题：Measuring social, environmental and health inequalities using deep learning and street imagery
期刊：
作者：Esra Suel, John W. Polak, James E. Bennett, Majid Ezzati
发表时间：2019/04/18
数字识别码： 10.1038/s41598-019-42036-w
原文链接：
图1
图2
图3
图4
摘要：Cities are home to an increasing majority of the world’s population. Currently, it is difficult to track social, economic, environmental and health outcomes in cities with high spatial and temporal resolution, needed to evaluate policies regarding urban inequalities. We applied a deep learning approach to images from Google Street View for measuring spatial distributions of income, education, unemployment, housing, living environment, health and crime. Our model predicts different outcomes directly from raw images without extracting intermediate user-defined features. To evaluate the performance of the approach, we first trained neural networks on a subset of images from London using ground truth data at high spatial resolution from official statistics. We then compared how trained networks separated the best-off from worst-off deciles for different outcomes in images not used in training. The best performance was achieved for quality of the living environment and mean income. Allocation was least successful for crime and self-reported health (but not objectively measured health). We also evaluated how networks trained in London predict outcomes three other major cities in the UK: Birmingham, Manchester, and Leeds. The transferability analysis showed that networks trained in London, fine-tuned with only 1% of images in other cities, achieved performances similar to ones from trained on data from target cities themselves. Our findings demonstrate that imagery has the potential complement traditional survey-based and administrative data sources for high-resolution urban surveillance to measure inequalities and monitor the impacts of policies that aim to address them.
阅读论文全文请访问：
期刊介绍： () is an online, open access journal from the publishers of Nature. We publish scientifically valid primary research from all areas of the natural and clinical sciences.
The 2017 journal metrics for Scientific Reports are as follows:
•2-year impact factor: 4.122
•5-year impact factor: 4.609
•Immediacy index: 0.576
•Eigenfactor® score: 0.71896
•Article Influence Score: 1.356
•2-year Median: 2
（来源：明升手机版(明升官网)）
特别声明：本文转载仅仅是出于传播信息的需要，并不意味着代表本网站观点或证实其内容的真实性；如其他媒体、网站或个人从本网站转载使用，须保留本网站注明的“来源”，并自负版权等法律责任；作者如果不希望被转载或者联系转载稿费等事宜，请与我们接洽。
