An empirical likelihood-based CUSUM for on-line model change detection

Verdier, Ghislain

doi:10.1080/03610926.2019.1565834

Cited by 5 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, Cumulative Sum (CUSUM) accumulates the likelihood deviations to a reference point, and when its accumulated sum exceeds a threshold, the approach detects a change point [Page 1955]. Other studies using CUSUM make several modifications on it, such as the likelihood ratio estimate [Verdier 2020]. Algorithms like CUSUM and Change-Finder [Yamanishi and Takeuchi 2002] rely on pre-designed parametric models and are less flexible in real-world scenarios.…”

Section: Change Point Detectionmentioning

confidence: 99%

SAXJS: An Online Change Point Detection for Wearable Sensor Data

Riqueti,

Barros,

Borges

et al. 2023

Anais Do XLI Simpósio Brasileiro De Redes De Computadores E Sistemas Distribuídos (SBRC 2023)

View full text Add to dashboard Cite

Wearable electronics are devices used by humans that can continuously and uninterruptedly monitor human activity through sensor data. The data collected by them have several applications, such as recommending running techniques and helping to monitor health status. Segmenting such data into chunks containing only a single human activity is challenging due to the wide variability of underlying process characteristics presented in the data. To deal with this problem, we propose a new change point detection algorithm based on the Symbolic Aggregate approXimation (SAX) transformation, the probability of transition between symbols, and the Jensen-Shannon distance.

show abstract

Section: Change Point Detectionmentioning

confidence: 99%

SAXJS: An Online Change Point Detection for Wearable Sensor Data

Riqueti,

Barros,

Borges

et al. 2023

Anais Do XLI Simpósio Brasileiro De Redes De Computadores E Sistemas Distribuídos (SBRC 2023)

View full text Add to dashboard Cite

show abstract

“…Both of these burst identification methods require entire workload traces available offline. AdaFrame [32] timely detects the change in cloud application workloads for minimizing the time to trigger autoscaling using a probabilistic approach based on CUSUM [33]. Once the workload change is detected, their proposed method scale-out by adding one virtual machine to handle the change.…”

Section: Related Workmentioning

confidence: 99%

Burst-Aware Predictive Autoscaling for Containerized Microservices

Abdullah

Iqbal

Berral

et al. 2022

IEEE Trans. Serv. Comput.

View full text Add to dashboard Cite

Autoscaling methods are used for cloud-hosted applications to dynamically scale the allocated resources for guaranteeing Qualityof-Service (QoS). The public-facing application serves dynamic workloads, which contain bursts and pose challenges for autoscaling methods to ensure application performance. Existing State-of-the-art autoscaling methods are burst-oblivious to determine and provision the appropriate resources. For dynamic workloads, it is hard to detect and handle bursts online for maintaining application performance. In this paper, we propose a novel burst-aware autoscaling method which detects burst in dynamic workloads using workload forecasting, resource prediction, and scaling decision making while minimizing response time service-level objectives (SLO) violations. We evaluated our approach through a trace-driven simulation, using multiple synthetic and realistic bursty workloads for containerized microservices, improving performance when comparing against existing state-of-the-art autoscaling methods. Such experiments show an increase of ×1.09 in total processed requests, a reduction of ×5.17 for SLO violations, and an increase of ×0.767 cost as compared to the baseline method.

show abstract

“…Likewise, detecting a change with a delay of 30 minutes, for instance, may be interesting for door faults on a train, whilst the same delay may be problematic for autonomous vehicle cameras. [61], [62], [63], [64], [65], [66], [67] -More applicable online and concept drift change detectionhost of the models assumes that the process id i.i.d…”

Section: Techniques Evaluationmentioning

confidence: 99%

Online change detection techniques in time series: An overview

Namoano

Starr

Emmanouilidis

et al. 2019

2019 IEEE International Conference on Prognostics and Health Management (ICPHM)

View full text Add to dashboard Cite

Time-series change detection has been studied in several fields. From sensor data, engineering systems, medical diagnosis, and financial markets to user actions on a network, huge amounts of temporal data are generated. There is a need for a clear separation between normal and abnormal behaviour of the system in order to investigate causes or forecast change. Characteristics include irregularities, deviations, anomalies, outliers, novelties or surprising patterns. The efficient detection of such patterns is challenging, especially when constraints need to be taken into account, such as the data velocity, volume, limited time for reacting to events, and the details of the temporal sequence. This paper reviews the main techniques for time series change point detection, focusing on online methods. Performance criteria including complexity, time granularity, and robustness is used to compare techniques, followed by a discussion about current challenges and open issues.

show abstract

An empirical likelihood-based CUSUM for on-line model change detection

Cited by 5 publications

References 21 publications

SAXJS: An Online Change Point Detection for Wearable Sensor Data

SAXJS: An Online Change Point Detection for Wearable Sensor Data

Burst-Aware Predictive Autoscaling for Containerized Microservices

Online change detection techniques in time series: An overview

Contact Info

Product

Resources

About