A cusum change-point detection algorithm for non-stationary sequences with application to data network surveillance

De, Veronica Montes; Jeske, Daniel R.; Zhang, Qi; Rendon, C.; Marvasti, Mazda A.

doi:10.1016/j.jss.2010.02.006

Cited by 42 publications

(8 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The RuLSIF method has demonstrated to provide very good results in identifying change-points through the assessment of a relative probability density-ratio [Fuez et al, 2015]; ii) a Cumulative Sum (CUSUM) change-point detection algorithm [Carslaw et al, 2006]. The CUSUM is one of the most popular changepoint method that has been adopted in many different research framework, such as air pollution concentration [Carslaw et al, 2006], failures of computer networks [Montes De Oca et al, 2010], functionality of animal brain activity [Koepcke et al, 2016], failures of water distribution networks [Misiunas et al, 2006]; iii) a change-point detection method that relies on the identification of changes of the mean value of the monitored system behaviour, by defining a penalty cost function [Lavielle, 2005]; iv) a change-point detection method that relies on the identification of changes of the slope of the monitored system behaviour, by using a Pruned Exact Linear Time (PELT) method [Killick et al, 2012]. The change-point methods iii) and iv), which rely on the same theoretical basis, have been chosen due to their efficiency and low computational burdensome.…”

Section: Change-point Methods: Theoretical Backgroundmentioning

confidence: 99%

An ensemble-based change-point detection method for identifying unexpected behaviour of railway tunnel infrastructures

Vagnoli

Remenyte‐Prescott

2018

Tunnelling and Underground Space Technology

View full text Add to dashboard Cite

A large amount of data is generated by Structural Health Monitoring (SHM) systems and, as a consequence, processing and interpreting this data can be difficult and time consuming. Particularly, if work activities such as maintenance or modernization are carried out on a bridge or tunnel infrastructure, a robust data analysis is needed, in order to accurately and quickly process the data and provide reliable information to decision makers. In this way the service disruption can be minimized and the safety of the asset and the workforce guaranteed. In this paper a data mining method for detecting critical behaviour of a railway tunnel is presented. The method starts with a pre-processing step that aims to remove the noise in the recorded data. A feature definition and selection step is then performed to identify the most critical area of the tunnel. An ensemble of change-point detection algorithms is proposed, in order to analyse the critical area of the tunnel and point out the time when unexpected behaviour occurs, as well as its duration and location. The work activities, which are carried out at the time of occurrence of the critical behaviour and have caused this behaviour, are finally identified from a database of the work schedule and used for the validation of the results. Using the proposed method, fast and reliable information about infrastructure condition is provided to decision makers.

show abstract

Section: Change-point Methods: Theoretical Backgroundmentioning

confidence: 99%

An ensemble-based change-point detection method for identifying unexpected behaviour of railway tunnel infrastructures

Vagnoli

Remenyte‐Prescott

2018

Tunnelling and Underground Space Technology

View full text Add to dashboard Cite

show abstract

“…If the threshold is reached within a predefined time window then a change has been detected [ 35 ]. Some variants of CUSUM are also able to handle non-stationary sequences (where the “normal” distribution can shift) [ 36 ] and FG risk adjustment (by replacing static control limits with simulation-based dynamic probability control limits for each subject) [ 37 ].…”

Section: History Of Change Detectionmentioning

confidence: 99%

Representation Learning for Fine-Grained Change Detection

Mahony

Campbell

Krpálková

et al. 2021

Sensors

View full text Add to dashboard Cite

Fine-grained change detection in sensor data is very challenging for artificial intelligence though it is critically important in practice. It is the process of identifying differences in the state of an object or phenomenon where the differences are class-specific and are difficult to generalise. As a result, many recent technologies that leverage big data and deep learning struggle with this task. This review focuses on the state-of-the-art methods, applications, and challenges of representation learning for fine-grained change detection. Our research focuses on methods of harnessing the latent metric space of representation learning techniques as an interim output for hybrid human-machine intelligence. We review methods for transforming and projecting embedding space such that significant changes can be communicated more effectively and a more comprehensive interpretation of underlying relationships in sensor data is facilitated. We conduct this research in our work towards developing a method for aligning the axes of latent embedding space with meaningful real-world metrics so that the reasoning behind the detection of change in relation to past observations may be revealed and adjusted. This is an important topic in many fields concerned with producing more meaningful and explainable outputs from deep learning and also for providing means for knowledge injection and model calibration in order to maintain user confidence.

show abstract

“…Jeske et al and Montes de Oca et al defined a time slot structure on the data stream and assumed that after a suitable application‐dependent transformation, the data within a time slot are independent and identically distributed (iid). Historical data are used to estimate the time slot distributions nonparametrically, and then, a CUSUM tracking statistic based on the empirical probability integral transformations is proposed.…”

Section: Monitoring Reliability Of Data Networkmentioning

confidence: 99%