Data modeling for detection of epidemic outbreak

被引：0

作者：

Jaenisch, HM ^{[1
]}

Handley, JW ^{[1
]}

Jaenisch, KL ^{[1
]}

Conn, MS ^{[1
]}

Faucheux, JP ^{[1
]}

机构：

[1] dtech Syst Inc, Huntsville, AL 35804 USA

来源：

Sensors, and Command, Control, Communications, and Intelligence (C31) Technologies for Homeland Security and Homeland Defense IV, Pts 1 and 2 | 2005年 / 5778卷

关键词：

data modeling; epidemic detection; outbreak; change detection; Essence II; chem-bio attack;

D O I：

10.1117/12.603374

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

Data Modeling is successfully applied to outbreak detection using epidemicological time series data. With proper selection of features, same day detection was demonstrated. Predictive Data Models are derived from the features in the form of integro-differential equations or their solution. These models are used as real-time change detectors. Data Modeling enables change detection using only nominal (no-outbreak) examples for training. Modeling naturally occurring dynamics due to assignable causes such as flu season enables distinction to be made of chemical and biological (chem-bio) causes.

引用

页码：626 / 637

页数：12