Functional Kernel Density Estimation: Point and Fourier Approaches to Time Series Anomaly Detection

Abstract

We present an unsupervised method to detect anomalous time series among a collection of time series. To do so, we extend traditional Kernel Density Estimation for estimating probability distributions in Euclidean space to Hilbert spaces. The estimated probability densities we derive can be obtained formally through treating each series as a point in a Hilbert space, placing a kernel at those points, and summing the kernels (a “point approach”), or through using Kernel Density Estimation to approximate the distributions of Fourier mode coefficients to infer a probability density (a “Fourier approach”). We refer to these approaches as Functional Kernel Density Estimation for Anomaly Detection as they both yield functionals that can score a time series for how anomalous it is. Both methods naturally handle missing data and apply to a variety of settings, performing well when compared with an outlyingness score derived from a boxplot method for functional data, with a Principal Component Analysis approach for functional data, and with the Functional Isolation Forest method. We illustrate the use of the proposed methods with aviation safety report data from the International Air Transport Association (IATA).

Artificial Intelligence Analysis and Reverse Engineering of Molecular Subtypes of Diffuse Large B-Cell Lymphoma Using Gene Expression Data

“…It is a mixture of data modeling, unsupervised learning, and feature engineering (i.e., extraction and transformation of variables from raw data). Although KDE can include any number of variables and dimensions, it can result in a loss of performance [85][86][87][88].…”

Time Series Modelling

“…The paper by Davidescu et al [ 4 ] is centered around the time series of Romanian unemployment rates, which serves as the base for comparing the forecast performance of several well-established time series models. Not a single time series, but a large collection of univariate time series is considered by Lindstrom et al [ 5 ], who use functional kernel density estimation for uncovering anomalous time series within such a collection. They apply their approaches to time series on aviation safety events as provided by the International Air Transport Association.…”