Failure rates of Hard Disk Drives (HDDs) are high and often due to a variety of different conditions. Thus, there is increasing demand for technologies dedicated to anticipating possible causes of failure, so to allow for preventive maintenance operations. In this paper, we propose a framework to predict HDD health status according to a long short-term memory (LSTM) model. We also employ eXplainable Artificial Intelligence (XAI) tools, to provide effective explanations of the model decisions, thus making the final results more useful to human decision-making processes. We extensively evaluate our approach on standard data-sets, proving its feasibility for real world applications.
An explainable artificial intelligence methodology for hard disk fault prediction / Galli, A.; Moscato, V.; Sperli, G.; Santo, A. D.. - 12391:(2020), pp. 403-413. (Intervento presentato al convegno 31st International Conference on Database and Expert Systems Applications, DEXA 2020 tenutosi a svk nel 2020) [10.1007/978-3-030-59003-1_26].
An explainable artificial intelligence methodology for hard disk fault prediction
Galli A.;Moscato V.;Sperli G.;
2020
Abstract
Failure rates of Hard Disk Drives (HDDs) are high and often due to a variety of different conditions. Thus, there is increasing demand for technologies dedicated to anticipating possible causes of failure, so to allow for preventive maintenance operations. In this paper, we propose a framework to predict HDD health status according to a long short-term memory (LSTM) model. We also employ eXplainable Artificial Intelligence (XAI) tools, to provide effective explanations of the model decisions, thus making the final results more useful to human decision-making processes. We extensively evaluate our approach on standard data-sets, proving its feasibility for real world applications.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
