On-line Novelty Detection Using the Kalman Filter and Extreme Value Theory by Lee, H, Roberts, S, IEEE

“…Our approach is based on a Kalman filter in order to model time-series data and extreme value theory is used to compute a novelty measure in a principled manner. …”

A COMPARISON OF APPROACHES TO MULTIVARIATE EXTREME VALUE THEORY FOR NOVELTY DETECTION by Clifton, D, Hugueny, S, Tarassenko, L, IEEE

NOVELTY DETECTION WITH MULTIVARIATE EXTREME VALUE THEORY, PART II: AN ANALYTICAL APPROACH TO UNIMODAL ESTIMATION by Hugueny, S, Clifton, D, Tarassenko, L, IEEE

NOVELTY DETECTION WITH MULTIVARIATE EXTREME VALUE THEORY, PART I: A NUMERICAL APPROACH TO MULTIMODAL ESTIMATION by Clifton, D, Hugueny, S, Tarassenko, L, IEEE

“…Extreme Value Theory (EVT) describes the distribution of data considered extreme with respect to some generative distribution, effectively modelling the tails of that distribution. …”

PINNING THE TAIL ON THE DISTRIBUTION: A MULTIVARIATE EXTENSION TO THE GENERALISED PARETO DISTRIBUTION by Clifton, D, Hugueny, S, Tarassenko, L, IEEE

“…Models of normality are constructed from commonly-available examples of "normal" behaviour, and we then reason about the presence of abnormalities with respect to this normal model. Extreme value theory (EVT) is a branch of statistics that is concerned with modelling extremal events, and is therefore appealing for use with novelty detection. …”

Bayesian extreme value statistics for novelty detection in gas-turbine engines by Clifton, D, McGrogan, N, Tarassenko, L, King, D, King, S, Anuzis, P, IEEE

“…We present a novel method for the identification of abnormal episodes in gas-turbine vibration data, in which we show 1) how a model of normal engine behaviour is constructed using signatures of "normal" engine vibration response; 2) how extreme value theory (EVT), a branch of statistics used to determine the expected value of extreme values drawn from a distribution, can be used to set novelty thresholds in the model, which, if exceeded, indicate an "abnormal" episode; 3) application to large data sets of modern gas-turbine flight data, which shows successful novelty detection results with low false-positive alarm rates. …”