@inproceedings{73ff3063959a40e8b646a9fd83168e22,
title = "Anomaly Detection of Hard Disk Drives Based on Multi-scale Feature",
abstract = "Hard disk drives (HDDs) as a cheap and relatively stable storage tool are widely used by enterprises. However, there is also a risk of fault to the hard disk. Early warning of the HDDs can avoid the data loss caused by the hard disk damage. This paper describes our submission to the PAKDD2020 Alibaba AI Ops Competition, we proposed an anomaly detection method of HDDs based on multi-scale feature. In our method, the original data are classified according to the characteristics of different attributes and proposed a multi-scale feature extraction framework. In order to solve the problem of different data distribution and sample imbalance, the health samples were sampled in time. Finally, we use Lightgbm model to regress and predict the hard disk that will break in the next 30 days. On the real dataset get the 0.5155 precision and 0.2564 recall. Final rank is 24.",
keywords = "Anomaly detection, Lightgbm, Muti-scale features",
author = "Xiandong Ran and Zhou Su",
note = "Publisher Copyright: {\textcopyright} 2020, Springer Nature Singapore Pte Ltd.; AI Ops Competition on Large-Scale Disk Failure Prediction, AI Ops 2020, held at the 24th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2020 ; Conference date: 11-05-2020 Through 14-05-2020",
year = "2020",
doi = "10.1007/978-981-15-7749-9\_5",
language = "英语",
isbn = "9789811577482",
series = "Communications in Computer and Information Science",
publisher = "Springer",
pages = "40--50",
editor = "Cheng He and Yi Liu and Mengling Feng and Lee, \{Patrick P.C.\} and Shujie Han and Pinghui Wang",
booktitle = "Large-Scale Disk Failure Prediction - PAKDD 2020 Competition and Workshop, AI Ops 2020, Revised Selected Papers",
}