Failure Prediction in IBM BlueGene/L Event Logs

By Yinglung Liang, Yanyong Zhang, Hui Xiong, R. Sahoo. Industrial Conference on Data Mining, 2007

332 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

LogAnomaly: Unsupervised Detection of Sequential and Quantitative Anomalies in Unstructured Logs (2019, methodology): “Supervised approaches can be used to detect anomalies using various algorithms: logistic regression and decision tree (in [He et al., 2016]) and SVM (in [Liang et al., 2007]).”
LogBERT: Log Anomaly Detection via BERT (2021, methodology): “[41] trained an SVM classifier and a KNN classifier to diagnose system failures.”
Log-based Anomaly Detection Without Log Parsing (2021, methodology): “In this section, we evaluate the impact of log parsing errors on two representative anomaly detection methods SVM-based method [30], and LogRobust [8].”
Robust log-based anomaly detection on unstable log data (2019, methodology): “Over the years, many automated log-based approaches have been proposed to detect system anomalies [3, 10, 18, 29, 44].”
Experience Report: System Log Analysis for Anomaly Detection (2016, methodology): “3) SVM Support Vector Machine (SVM) is a supervised learning method for classiﬁcation.”
A Survey on Automated Log Analysis for Reliability Engineering (2020, methodology): “s examples are derived from normal ones in terms of some statistical properties. Support Vector Machine (SVM) is a supervised classification method that is commonly used for log anomaly detection. In [84], Liang et al. vectorized log partitions by identifying six types of features, including events ”