Integrating predictive analytics into a spatiotemporal epidemic simulation

Chris Bryan, Xue Wu, Susan Mniszewski, Kwan-Liu Ma

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

The Epidemic Simulation System (EpiSimS) is a scalable, complex modeling tool for analyzing disease within the United States. Due to its high input dimensionality, time requirements, and resource constraints, simulating over the entire parameter space is unfeasible. One solution is to take a granular sampling of the input space and use simpler predictive models (emulators) in between. The quality of the implemented emulator depends on many factors: robustness, sophistication, configuration, and suitability to the input data. Visual analytics can be leveraged to provide guidance and understanding of these things to the user. In this paper, we have implemented a novel interface and workflow for emulator building and use. We introduce a workflow to build emulators, make predictions, and then analyze the results. Our prediction process first predicts temporal time series, and uses these to derive predicted spatial densities. Integrated into the EpiSimS framework, we target users who are non-experts at statistical modeling. This approach allows for a high level of analysis into the state of the built emulators and their resultant predictions. We present our workflow, models, the associated system, and evaluate the overall utility with feedback from EpiSimS scientists.

Original languageEnglish (US)
Title of host publication2015 IEEE Conference on Visual Analytics Science and Technology, VAST 2015 - Proceedings
EditorsMin Chen, Gennady Andrienko
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages17-24
Number of pages8
ISBN (Electronic)9781467397834
DOIs
StatePublished - Dec 4 2015
Event10th IEEE Conference on Visual Analytics Science and Technology, VAST 2015 - Chicago, United States
Duration: Oct 25 2015Oct 30 2015

Other

Other10th IEEE Conference on Visual Analytics Science and Technology, VAST 2015
CountryUnited States
CityChicago
Period10/25/1510/30/15

Fingerprint

Time series
Sampling
Feedback
Predictive analytics

Keywords

  • Epidemic Visualization
  • Predictive Modeling
  • Spatial-Temporal Systems
  • Visual Analytics

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Cite this

Bryan, C., Wu, X., Mniszewski, S., & Ma, K-L. (2015). Integrating predictive analytics into a spatiotemporal epidemic simulation. In M. Chen, & G. Andrienko (Eds.), 2015 IEEE Conference on Visual Analytics Science and Technology, VAST 2015 - Proceedings (pp. 17-24). [7347626] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/VAST.2015.7347626

Integrating predictive analytics into a spatiotemporal epidemic simulation. / Bryan, Chris; Wu, Xue; Mniszewski, Susan; Ma, Kwan-Liu.

2015 IEEE Conference on Visual Analytics Science and Technology, VAST 2015 - Proceedings. ed. / Min Chen; Gennady Andrienko. Institute of Electrical and Electronics Engineers Inc., 2015. p. 17-24 7347626.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Bryan, C, Wu, X, Mniszewski, S & Ma, K-L 2015, Integrating predictive analytics into a spatiotemporal epidemic simulation. in M Chen & G Andrienko (eds), 2015 IEEE Conference on Visual Analytics Science and Technology, VAST 2015 - Proceedings., 7347626, Institute of Electrical and Electronics Engineers Inc., pp. 17-24, 10th IEEE Conference on Visual Analytics Science and Technology, VAST 2015, Chicago, United States, 10/25/15. https://doi.org/10.1109/VAST.2015.7347626
Bryan C, Wu X, Mniszewski S, Ma K-L. Integrating predictive analytics into a spatiotemporal epidemic simulation. In Chen M, Andrienko G, editors, 2015 IEEE Conference on Visual Analytics Science and Technology, VAST 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2015. p. 17-24. 7347626 https://doi.org/10.1109/VAST.2015.7347626
Bryan, Chris ; Wu, Xue ; Mniszewski, Susan ; Ma, Kwan-Liu. / Integrating predictive analytics into a spatiotemporal epidemic simulation. 2015 IEEE Conference on Visual Analytics Science and Technology, VAST 2015 - Proceedings. editor / Min Chen ; Gennady Andrienko. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 17-24
@inproceedings{712c72f785cf41c095e8b2afb27a1271,
title = "Integrating predictive analytics into a spatiotemporal epidemic simulation",
abstract = "The Epidemic Simulation System (EpiSimS) is a scalable, complex modeling tool for analyzing disease within the United States. Due to its high input dimensionality, time requirements, and resource constraints, simulating over the entire parameter space is unfeasible. One solution is to take a granular sampling of the input space and use simpler predictive models (emulators) in between. The quality of the implemented emulator depends on many factors: robustness, sophistication, configuration, and suitability to the input data. Visual analytics can be leveraged to provide guidance and understanding of these things to the user. In this paper, we have implemented a novel interface and workflow for emulator building and use. We introduce a workflow to build emulators, make predictions, and then analyze the results. Our prediction process first predicts temporal time series, and uses these to derive predicted spatial densities. Integrated into the EpiSimS framework, we target users who are non-experts at statistical modeling. This approach allows for a high level of analysis into the state of the built emulators and their resultant predictions. We present our workflow, models, the associated system, and evaluate the overall utility with feedback from EpiSimS scientists.",
keywords = "Epidemic Visualization, Predictive Modeling, Spatial-Temporal Systems, Visual Analytics",
author = "Chris Bryan and Xue Wu and Susan Mniszewski and Kwan-Liu Ma",
year = "2015",
month = "12",
day = "4",
doi = "10.1109/VAST.2015.7347626",
language = "English (US)",
pages = "17--24",
editor = "Min Chen and Gennady Andrienko",
booktitle = "2015 IEEE Conference on Visual Analytics Science and Technology, VAST 2015 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Integrating predictive analytics into a spatiotemporal epidemic simulation

AU - Bryan, Chris

AU - Wu, Xue

AU - Mniszewski, Susan

AU - Ma, Kwan-Liu

PY - 2015/12/4

Y1 - 2015/12/4

N2 - The Epidemic Simulation System (EpiSimS) is a scalable, complex modeling tool for analyzing disease within the United States. Due to its high input dimensionality, time requirements, and resource constraints, simulating over the entire parameter space is unfeasible. One solution is to take a granular sampling of the input space and use simpler predictive models (emulators) in between. The quality of the implemented emulator depends on many factors: robustness, sophistication, configuration, and suitability to the input data. Visual analytics can be leveraged to provide guidance and understanding of these things to the user. In this paper, we have implemented a novel interface and workflow for emulator building and use. We introduce a workflow to build emulators, make predictions, and then analyze the results. Our prediction process first predicts temporal time series, and uses these to derive predicted spatial densities. Integrated into the EpiSimS framework, we target users who are non-experts at statistical modeling. This approach allows for a high level of analysis into the state of the built emulators and their resultant predictions. We present our workflow, models, the associated system, and evaluate the overall utility with feedback from EpiSimS scientists.

AB - The Epidemic Simulation System (EpiSimS) is a scalable, complex modeling tool for analyzing disease within the United States. Due to its high input dimensionality, time requirements, and resource constraints, simulating over the entire parameter space is unfeasible. One solution is to take a granular sampling of the input space and use simpler predictive models (emulators) in between. The quality of the implemented emulator depends on many factors: robustness, sophistication, configuration, and suitability to the input data. Visual analytics can be leveraged to provide guidance and understanding of these things to the user. In this paper, we have implemented a novel interface and workflow for emulator building and use. We introduce a workflow to build emulators, make predictions, and then analyze the results. Our prediction process first predicts temporal time series, and uses these to derive predicted spatial densities. Integrated into the EpiSimS framework, we target users who are non-experts at statistical modeling. This approach allows for a high level of analysis into the state of the built emulators and their resultant predictions. We present our workflow, models, the associated system, and evaluate the overall utility with feedback from EpiSimS scientists.

KW - Epidemic Visualization

KW - Predictive Modeling

KW - Spatial-Temporal Systems

KW - Visual Analytics

UR - http://www.scopus.com/inward/record.url?scp=84962788710&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962788710&partnerID=8YFLogxK

U2 - 10.1109/VAST.2015.7347626

DO - 10.1109/VAST.2015.7347626

M3 - Conference contribution

AN - SCOPUS:84962788710

SP - 17

EP - 24

BT - 2015 IEEE Conference on Visual Analytics Science and Technology, VAST 2015 - Proceedings

A2 - Chen, Min

A2 - Andrienko, Gennady

PB - Institute of Electrical and Electronics Engineers Inc.

ER -