Change Detection in Multivariate Datastreams: Likelihood and Detectability Loss

Authors: Cesare Alippi, Giacomo Boracchi, Diego Carrera, Manuel Roveri

IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our empirical analysis has been designed to address the following goals: i) showing that SNR(φ0 ! φ1), which is the underpinning element of our theoretical result, is a suitable measure of change detectability. In particular, we show that the power of hypothesis tests able to detect both changes in mean and in variance of L( ) also decays. ii) Showing that detectability loss is not due to density-estimation problems, but it becomes a more serious issue when φ0 is estimated from training data. iii) Showing that detectability loss occurs also in Gaussian mixtures, and iv) showing that detectability loss occurs also on high-dimensional real-world datasets, which are far from being Gaussian or having independent components. We address the first two points in Section 4.1, while the third and fourth ones in Sections 4.2 and 4.3, respectively.
Researcher Affiliation Academia Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milano, Italy 2Universit a della Svizzera Italiana, Lugano, Switzerland
Pseudocode No The paper does not contain any pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statement or link regarding the availability of its source code.
Open Datasets Yes We design a change-detection problem on the Wine Quality Dataset [Cortez et al., 2009] and the Mini Boo NE Particle Dataset [Roe et al., 2005] from the UCI repository [Lichman, 2013].
Dataset Splits No The paper describes generating a 'training set' and a 'test set', but does not mention a distinct 'validation' set or specific splits for one.
Hardware Specification No The paper does not provide any specific details about the hardware used for the experiments.
Software Dependencies No The paper does not list specific software dependencies with version numbers.
Experiment Setup Yes To compute the power, we set h to guarantee a significance levelα = 0.05. Following the procedure in Appendix, we synthetically introduce changes φ0 ! φ1 having s KL(φ0, φ1) = 1 which, in the univariate Gaussian case, corresponds to v equals to the standard deviation of φ0. ... on data windows WP and WR which contains 500 data each.