首页|University of Florida Researchers Highlight Research in Machine Learning (Predic ting Hurricane Evacuation Decisions with Interpretable Machine Learning Methods)
University of Florida Researchers Highlight Research in Machine Learning (Predic ting Hurricane Evacuation Decisions with Interpretable Machine Learning Methods)
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-Research findings on artificial intell igence are discussed in a new report. According to news reporting from the Unive rsity of Florida by NewsRx journalists,research stated,"Facing the escalating effects of climate change,it is critical to improve the prediction and understa nding of the hurricane evacuation decisions made by households in order to enhan ce emergency management." The news editors obtained a quote from the research from University of Florida: "Current studies in this area often have relied on psychology-driven linear mode ls,which frequently exhibited limitations in practice. The present study propos ed a novel interpretable machine learning approach to predict household-level ev acuation decisions by leveraging easily accessible demographic and resource-rela ted predictors,compared to existing models that mainly rely on psychological fa ctors. An enhanced logistic regression model (that is,an interpretable machine learning approach) was developed for accurate predictions by automatically accou nting for nonlinearities and interactions (that is,univariate and bivariate thr eshold effects). Specifically,nonlinearity and interaction detection were enabl ed by low-depth decision trees,which offer transparent model structure and robu stness. A survey dataset collected in the aftermath of Hurricanes Katrina and Ri ta,two of the most intense tropical storms of the last two decades,was employe d to test the new methodology. The findings show that,when predicting the house holds' evacuation decisions,the enhanced logistic regression model outperformed previous linear models in terms of both model fit and predictive capability."
University of FloridaCyborgsEmerging TechnologiesMachine Learning
NETL
NSTL
