Robust and Rapid Adaption for Concept Drift in Software System Anomaly Detection

Ma, Minghua; Zhang, Shenglin; Pei, Dan; Huang, Xin; Dai, Hongwei

doi:10.1109/issre.2018.00013

Cited by 55 publications

(8 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One key functionality of MID is incident detection (i.e., anomaly detection) on time series data. Anomaly detection is also a critical task with lots of efforts from both industrial practitioners and academic researchers [19,32,41,48]. Specifically, there is a body of work focusing on anomaly detection in key performance indicators (KPIs) in order to monitor systems and identify incidents [9,23,25,30,46].…”

Section: Related Work 71 Incident Identificationmentioning

confidence: 99%

Efficient incident identification from multi-dimensional issue reports via meta-heuristic search

Luo

Qin

et al. 2020

Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Softw

View full text Add to dashboard Cite

Section: Related Work 71 Incident Identificationmentioning

confidence: 99%

Efficient incident identification from multi-dimensional issue reports via meta-heuristic search

Luo

Qin

et al. 2020

Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Softw

View full text Add to dashboard Cite

“…In recent years, there are more and more RCA algorithms and anomaly detection algorithms depending on graphs. The researches of some MSA and cloud applications are very representative [9]- [21].…”

Section: Introductionmentioning

confidence: 99%

“…Yan et al described the design and development of a Generic Root Cause Analysis platform (G-RCA) for service quality management (SQM) in large IP networks [19]. Ma et al presented a framework, StepWise, which can detect concept drift without tuning detection threshold or per-KPI (Key Performance Indicator) model parameters in a large scale KPI streams [21].…”

Section: Introductionmentioning

confidence: 99%

An Anomaly Detection Algorithm for Microservice Architecture Based on Robust Principal Component Analysis

Jin

Zhu

et al. 2020

IEEE Access

View full text Add to dashboard Cite

“…If anomaly detection methods cannot update their definition of abnormal behaviors in time, they cannot accurately detect anomalies in new data. Therefore, it is essential that online anomaly detection methods have the ability to adapt to the concept drift [32,33,34,35,36,37,38]. This paper proposes the method of sparse Gaussian processes with Q-function (SGP-Q).…”

Section: Introductionmentioning

confidence: 99%

Online Anomaly Detection with Sparse Gaussian Processes

Fei¹,

Sun²

2019

Preprint

View full text Add to dashboard Cite

Online anomaly detection of time-series data is an important and challenging task in machine learning. Gaussian processes (GPs) are powerful and flexible models for modeling time-series data. However, the high time complexity of GPs limits their applications in online anomaly detection. Attributed to some internal or external changes, concept drift usually occurs in time-series data, where the characteristics of data and meanings of abnormal behaviors alter over time. Online anomaly detection methods should have the ability to adapt to concept drift. Motivated by the above facts, this paper proposes the method of sparse Gaussian processes with Qfunction (SGP-Q). The SGP-Q employs sparse Gaussian processes (SGPs) whose time complexity is lower than that of GPs, thus significantly speeding up online anomaly detection. By using Q-function properly, the SGP-Q can adapt to concept drift well. Moreover, the SGP-Q makes use of few abnormal data in the training data by its strategy of updating training data, resulting in more accurate sparse Gaussian process regression models and better anomaly detection results. We evaluate the SGP-Q on various artificial and real-world datasets. Experimental results validate the effectiveness of the SGP-Q.

show abstract

Robust and Rapid Adaption for Concept Drift in Software System Anomaly Detection

Cited by 55 publications

References 25 publications

Efficient incident identification from multi-dimensional issue reports via meta-heuristic search

Efficient incident identification from multi-dimensional issue reports via meta-heuristic search

An Anomaly Detection Algorithm for Microservice Architecture Based on Robust Principal Component Analysis

Online Anomaly Detection with Sparse Gaussian Processes

Contact Info

Product

Resources

About