Displaying results 1 - 2 of 2
-
Anomaly Pattern Detection for Biosurveillance
Content Type: Abstract
We propose a new method for detecting patterns of disease cases that correspond to emerging outbreaks. Our Anomaly Pattern Detector (APD) first uses a "local anomaly detector" to identify individually anomalous records and then searches over subsets… read more… particular rules for the current (test) and historical (training) datasets. How- ever, an outbreak may create a … we compare it to the corres- ponding subset in the training data. For each rule R, we determine the total number of corresponding records in the test and training datasets (C(R)test and C(R)train) and the number of … -
Learning Specific Detectors of Adverse Events in Multivariate Time Series
Content Type: Abstract
This paper describes how powerful detectors of adverse events manifested in multivariate series of bio-surveillance data can be learned using only a few labeled instances of such events.… using domain expertise, if the amount of available training data is insufficient to support automated learning … for machine learning techniques which would allow for training specific detectors even if the number of iden- … improvement can be obtained by combining into the training data labels on false posi- tives with one, then …