Selective review of offline change point detection methods

Abstract

This article presents a selective survey of algorithms for the offline detection of multiple change points in multivariate time series. A general yet structuring methodological strategy is adopted to organize this vast body of work. More precisely, detection algorithms considered in this review are characterized by three elements: a cost function, a search method and a constraint on the number of changes. Each of those elements is described, reviewed and discussed separately. Implementations of the main algorithms described in this article are provided within a Python package called ruptures.

Optimal Transport Based Change Point Detection and Time Series Segment Clustering

“…Following previous works of [14] [21] [11] we use the area under the curve (CP-AUC) to evaluate change point performance. We also report the F1 score (CP-F1) for offline multiple CPD, [22] using a margin of error δ for the acceptable offset to the true label.…”

Series arc fault detection in photovoltaic system by small‐signal impedance and noise monitoring

“…Fortunately, this problem, known as step detection, has been the subject of many research articles, and multiple algorithms 33 have been proposed already. Moreover, the reactance value of the PV array is not known in advance, nor it is known what increase in X a SEA would introduce.…”

“…Moreover, the reactance value of the PV array is not known in advance, nor it is known what increase in X a SEA would introduce. Fortunately, this problem, known as step detection, has been the subject of many research articles, and multiple algorithms 33 have been proposed already.…”

A two‐stage degradation model considering the stage‐varying of dispersity regulation

“…Based on the above discussion, the key issue lies in that a two‐stage degradation procedure usually shows different stochastic properties between the two stages. Therefore, it is very important to describe the regularity difference corresponding to the two degradation stages, and the mathematical description and engineering significance of the differences are worthwhile noticing in current researches …”

“…Therefore, it is very important to describe the regularity difference corresponding to the two degradation stages, and the mathematical description and engineering significance of the differences are worthwhile noticing in current researches. 12 Most literatures regarding two-stage degradation modeling adopt a same stochastic process or degradation path for both stages, where different parameters are involved as distinction. Among them, Zhang 13 proposed a multiphase stochastic model with random jumps based on Wiener process for the lithium-ion battery degradation; Bae 14 constructed a hierarchal Bayesian change point regression model to fit the PDPs' degradation which has a two-stage pattern 11 ; Wang 15 proposed a change point Wiener process model to fit the degradation paths of OLEDs, which also showed a two-phase regularity; Feng 16 applied a novel three-phase path degradation model to high-voltage-pulse capacitor deterioration problem; more literature can be referred to Wen, 17 Sheng,18 and Kong.…”