Rapid detection of hot-spot by tensor decomposition with application to weekly gonorrhea data

Yujie Zhao, Hao Yan, Sarah E. Holte, Roxanne P. Kerani, Yajun Mei

Research output: Contribution to conferencePaperpeer-review

Abstract

In many bio-surveillance and healthcare applications, data sources are measured from many spatial locations repeatedly over time, say, daily/weekly/monthly. In these applications, we are typically interested in detecting hot-spots, which are defined as some structured outliers that are sparse over the spatial domain but persistent over time. In this paper, we propose a tensor decomposition method to detect when and where the hot-spots occur. Our proposed methods represent the observed raw data as a three-dimensional tensor including a circular time dimension for daily/weekly/monthly patterns, and then decompose the tensor into three components: smooth global trend, local hot-spots, and residuals. A combination of LASSO and fused LASSO is used to estimate the model parameters, and a CUSUM procedure is applied to detect when and where the hot-spots might occur. The usefulness of our proposed methodology is validated through numerical simulation and a real-world dataset in the weekly number of gonorrhea cases from 2006 to 2018 for 50 states in the United States.

Original languageEnglish (US)
Pages289-310
Number of pages22
StatePublished - 2020
Event13th International Workshop on Intelligent Statistical Quality Control 2019, IWISQC 2019 - Hong Kong, Hong Kong
Duration: Aug 12 2019Aug 14 2019

Conference

Conference13th International Workshop on Intelligent Statistical Quality Control 2019, IWISQC 2019
Country/TerritoryHong Kong
CityHong Kong
Period8/12/198/14/19

Keywords

  • Circular time
  • CUSUM
  • Hot-spot
  • Spatio-temporal model
  • Tensor decomposition

ASJC Scopus subject areas

  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Rapid detection of hot-spot by tensor decomposition with application to weekly gonorrhea data'. Together they form a unique fingerprint.

Cite this