Abstract | ||
---|---|---|
A system will produce massive status data during its runtime, which contains rich status information. In this work, we target at detecting system faults as early as possible based on the system status data sequences. Firstly, we formalized the system fault detection into classification problem, in which different types of status data were integrated to reflect the system status. Secondly, we devised a detection method to predict the class of a status sequence when its full length is not yet available. At last, a series of experiments were conducted to verify the proposed methods's effectiveness. |
Year | DOI | Venue |
---|---|---|
2016 | 10.3233/978-1-61499-722-1-519 | Frontiers in Artificial Intelligence and Applications |
Keywords | Field | DocType |
Fault detection,Early prediction,Data sequence | Geology,Reliability engineering | Conference |
Volume | ISSN | Citations |
293 | 0922-6389 | 0 |
PageRank | References | Authors |
0.34 | 0 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
You Li | 1 | 4 | 1.73 |
Yuming Lin | 2 | 37 | 4.76 |