首页|Investigators from Tongji University Target Machine Learning (The Association Be tween Urban Density and Multiple Health Risks Based On Interpretable Machine Lea rning: a Study of American Urban Communities)
Investigators from Tongji University Target Machine Learning (The Association Be tween Urban Density and Multiple Health Risks Based On Interpretable Machine Lea rning: a Study of American Urban Communities)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Machine Learning is th e subject of a report. According to news reporting originating from Shanghai, Pe ople's Republic of China, by NewsRx correspondents, research stated, "With the g rowing complexity in urban areas, cities have become unprecedentedly intricate s ystems. This paper aims to develop interpretable machine learning (ML) approache s to unravel the sophisticated associations." Financial supporters for this research include Peking University Lincoln Institu te Funds, Ministry of Housing and Urban-Rural Development Research Project, Shan ghai Rising-Star Program. Our news editors obtained a quote from the research from Tongji University, "In a case study of American urban communities, we apply interpretable ML methods to identify the associations between urban density and multiple health risks. We d efine urban density from three dimensions of population, built environment, and activity and measure multiple health risks based on categories of physical disea ses, mental diseases and health burden. Initially, we conduct cluster analysis t o control socioeconomic variables and select study samples. Then we build severa l ML models of multiple linear regression, decision trees, random forests, and e xtreme gradient boosting. Interpretable methods, including feature importance, p artial dependence plots, individual conditional expectations, and Shapley additi ve explanations, are used to interpret the models by identifying important facto rs, non-linear relationships, the interactions between variables. The results sh ow the advantages of interpretable ML methods in efficiency and transparency. Ou r findings verify that the associations between urban density and multiple healt h risks are complicated."
ShanghaiPeople's Republic of ChinaAs iaCyborgsEmerging TechnologiesMachine LearningRisk and PreventionTongj i University
NETL
NSTL
