Date of Award

3-1992

Document Type

Thesis

Degree Name

Master of Science

Department

Department of Operational Sciences

First Advisor

Yupo Chan, PhD

Abstract

The Department of Defense employs a resource limited world-wide sensor system to detect certain events of interest. The purpose of this research was to establish a methodology using a univariate causal STARMA model for forecasting the relative probability of an event occurring in a geographical location during a time block of the day. These relative probabilities are used as input for a tasking model that assigns the scarce sensor resources so as to optimize the detection of these events. The STARMA model is appropriate for forecasting the relative probabilities because a definite temporal relationship and a definite spatial relationship exists in the data bases. The model created is a univariate causal STARMA model in that it only produces forecasts for one of the twenty-two given geographical regions. A causal univariate STARMA model was created to provide forecasts for one event type occurring at region 11 and appears to provide good forecasts. The model is both correlative and causal. The model is correlative in that it uses temporal and spatial correlations to develop the forecasts. The model is also causal in that it employs predictions from an analytical model.

AFIT Designator

AFIT-GOR-ENS-92M-12

DTIC Accession Number

ADA248109

Comments

The author's Vita page is omitted.

Download

Share

COinS