Change point estimation of a normal process variance with monotonic change

Noorossana, Rassoul; Heydari, Majeed

doi:10.1016/j.scient.2012.01.011

Cited by 4 publications

(4 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In most cases, the detection algorithm and estimation method assume an abrupt change in the process. However, a more gradual change, such as a linear trend disturbance, may be important to consider [64][65][66]. The results in these last cases show that the performance and accuracy of the abrupt change methods are outperformed by those methods specifically designed for linear drift anomaly detection [64].…”

Section: Statistical Process Controlmentioning

confidence: 96%

See 1 more Smart Citation

Anomaly Detection in Activities of Daily Living with Linear Drift

et al. 2020

View full text Add to dashboard Cite

Background: Anomaly detection in Activities of Daily Living (ADL) plays an important role in e-health applications. An abrupt change in ADL taken by a subject might indicate that she/he needs some help. Another important issue related with e-health application is the case where the change in ADL experiments a linear drift, this is the case in cognitive decline, Alzheimer disease or dementia. Methods: This work presents a novel method for detecting a linear drift in ADL modeled as circular normal distributions. The method is based on techniques commonly used in Statistical Process Control, and is able to detect and estimate the change point in time when a linear drift started.

show abstract

Section: Statistical Process Controlmentioning

confidence: 96%

“…Different approaches have been presented for change point estimation: neural networks [55][56][57], fuzzy sets [58-60, 49, 61] and the bayesian approach [62,63], among others. Nevertheless, most existing approaches are based on MLE [64][65][66].…”

Section: Statistical Process Controlmentioning

confidence: 99%

Anomaly Detection in Activities of Daily Living with Linear Drift

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Thus, there is a need for estimators which can develop in monotonic nature and not require the knowledge of the exact change type exhibited by the process. In this regard, Noorossana and Shadman [23] and also Noorossana and Heydari [22] proposed an MLE provided a MLE estimator for change point estimation for monotonic changes in normal process mean and variance change, respectively. They evaluated their estimators for the process change point derived under a simple step change and linear trend change.…”

Section: Related Workmentioning

confidence: 99%

A type-2 fuzzy-statistical clustering approach for estimating the multiple change points in a process mean with monotonic change

Zarandi

Najafi

2014

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Identifying the real time of the change in a process, recognized as change point problem, simplifies the removal of change causes. In most of the change point models, the existence of different uncertainty levels is either ignored or paid a little attention to. This paper tries to address an appropriate model to estimate the multiple change points in a monotonic change process in an uncertain condition and for a known number of change points. In this regard, a novel set of membership functions and a novel objective function, based on using interval type-2 fuzzy sets, are introduced in a fuzzy-statistical clustering approach. The proposed approach, in addition to the ability of managing various amount of uncertainty, is free from the distribution of the process variables, and in the case of existence, a certain variable distribution, it is independent from it. Finally, extensive simulation studies are conducted to evaluate the performance of the proposed approach in simple step change, multiple step change, and linear trend change in the presence of isotonic change in the process mean. The results are compared with some of the powerful change point approaches.

show abstract

“…Some of these techniques can also be applied to the detection of variance change points, and other approaches to the analysis of variance homogeneity have been proposed by Hsu (1977); Inclan (1993); Inclan and Tiao (1994); Chen and Gupta (1997); Whitcher et al (2000); Killick et al (2010); Zhao et al (2010); Noorossana and Heydari (2012); Killick et al (2013); Nam et al (2015); Korkas and Fryzlewicz (2016). However, most available methods use specific assumptions on the underlying distribution, e.g., Gaussian sequences, or aim at detecting at most one change point.…”

Section: Introductionmentioning

confidence: 99%

Multi‐Scale Detection of Variance Changes in Renewal Processes in the Presence of Rate Change Points

Albert

Messer

Schiemann

et al. 2017

Journal Time Series Analysis

View full text Add to dashboard Cite

Non-stationarity of the rate or variance of events is a well-known problem in the description and analysis of time series of events, such as neuronal spike trains. A multiple filter test (MFT) for homogeneity of the rate has been proposed earlier that detects change points on multiple time scales simultaneously. It is based on a filtered derivative approach, and the rejection threshold derives from a Gaussian limit process L which is independent of the point process parameters.Here we extend the MFT to the analysis of variance homogeneity of life times. When the rate is constant, the MFT extends directly to the null hypothesis of constant variance and also to higher order moments under the assumption of homogeneity of lower order moments. In the presence of rate change points, we propose an adaptation of the test statistic. In order to ensure that rate changes are not falsely interpreted as variance changes, we propose to estimate the rate change points first, irrespective of potential variance changes, and incorporate these estimates in the statistical test for variance homogeneity. The resulting limit process shows slight deviations from L that depend on unknown process parameters. We use simulations to show that these deviations tend to be small for a wide range of parameter values, suggesting that the use of L does not considerably change the properties of the statistical test. Finally, the procedure is applied to empirical spike trains obtained from dopaminergic neurons in anaesthetized mice, indicating various profiles of rate and variance change points.

show abstract

Change point estimation of a normal process variance with monotonic change

Cited by 4 publications

References 28 publications

Anomaly Detection in Activities of Daily Living with Linear Drift

Anomaly Detection in Activities of Daily Living with Linear Drift

A type-2 fuzzy-statistical clustering approach for estimating the multiple change points in a process mean with monotonic change

Multi‐Scale Detection of Variance Changes in Renewal Processes in the Presence of Rate Change Points

Contact Info

Product

Resources

About