Change Detection in Streaming Multivariate Data Using Likelihood Detectors
Place: Large Lecture Room - CVC
Affiliation: School of Computer Science, Bangor University,Wales, UK
Change detection in streaming data relies on a fast estimation of the probability that the data in two consecutive windows come from different distributions. Choosing the criterion is one of the multitude of questions that need to be addressed when designing a change detection procedure. We present a log-likelihood justification for two well known criteria for detecting change in streaming multidimensional data: Kullback-Leibler (K-L) distance and Hotelling's T-square test for equal means (H). A semi-parametric log-likelihood criterion (SPLL) is subsequently proposed. Compared to the existing log-likelihood change detectors, SPLL trades some theoretical rigour for computation simplicity. We examine SPLL together with K-L and H on detecting induced change on 30 real data sets.