Transmission dynamics informed neural networks with application to disease transmission dynamics

发布时间：2024-03-25 作者：浏览次数：

Speaker:	肖燕妮	DateTime:	2024年3月30日（周六）上午9:00-10:00
Brief Introduction to Speaker: 肖燕妮西安交通大学数学与统计学院副院长、数学与生命科学交叉研究中心主任、博士生导师，主要从事数据和问题驱动的传染病动力学的研究。参与完成了国家“十一五”、“十二五”和“十三五”科技重大专项艾滋病领域的建模研究。主持国家自然科学基金7项，包括重点项目1项、重点国际合作1项，主持重点研发课题1项。2022年至今任中国生物数学专业委员会主任，2020年起任国务院第八届学科评议组成员（数学）。		Place:	6号楼2楼报告厅
Abstract:During the COVID-19 pandemic, control measures play an important role in mitigating the disease spread, and quantifying the dynamic contact rate and quarantine rate and estimate their impacts remain challenging. In this talk, we initially estimate the effective reproduction number by universal differential equation method which embeds neural network into a differential equation. We then develop the mechanism of physical-informed neural network (PINN) to propose the extended transmission-dynamics-informed neural network (TDINN) algorithm by combining scattered observational data with deep learning and epidemic models, to precisely quantify the intensity of interventions. The selected rate functions, quantifying the intensity of interventions, based on the time series inferred by deep learning have epidemiologically reasonable meanings. Finally, I shall give some concluding remarks. This is a joint work with Pengfei Song, Mengqi He, Sanyi Tang and Jianhong Wu.

上一条：药物毒理效应的普适性模型与数据分析
下一条： Permanents, perfect matchings and permutation statistics