首页|Investigators from University of Naples Federico II Report New Data on Artificia l Intelligence (Evaluating Explainable Artificial Intelligence Tools for Hard Di sk Drive Predictive Maintenance)
Investigators from University of Naples Federico II Report New Data on Artificia l Intelligence (Evaluating Explainable Artificial Intelligence Tools for Hard Di sk Drive Predictive Maintenance)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Investigators discuss new findings in Artificial Intelligence. According to news reporting originating from Naples, It aly, by NewsRx correspondents, research stated, “In the last years, one of the m ain challenges in Industry 4.0 concerns maintenance operations optimization, whi ch has been widely dealt with several predictive maintenance frameworks aiming t o jointly reduce maintenance costs and downtime intervals. Nevertheless, the mos t recent and effective frameworks mainly rely on deep learning models, but their internal representations (black box) are too complex for human understanding ma king difficult explain their predictions.” Our news editors obtained a quote from the research from the University of Naple s Federico II, “This issue can be challenged by using eXplainable artificial int elligence (XAI) methodologies, the aim of which is to explain the decisions of d ata-driven AI models, characterizing the strengths and weaknesses of the decisio n-making process by making results more understandable by humans. In this paper, we focus on explanation of the predictions made by a recurrent neural networks based model, which requires a treedimensional dataset because it exploits spati al and temporal features for estimating remaining useful life (RUL) of hard disk drives (HDDs). In particular, we have analyzed in depth as explanations about R UL prediction provided by different XAI tools, compared using different metrics and showing the generated dashboards, can be really useful for supporting predic tive maintenance task by means of both global and local explanations. For this a im, we have realized an explanation framework able to investigate local interpre table model-agnostic explanations (LIME) and SHapley Additive exPlanations (SHAP ) tools w.r.t. to the Backblaze Dataset and a long short-term memory (LSTM) pred iction model.”
NaplesItalyEuropeArtificial Intell igenceEmerging TechnologiesMachine LearningUniversity of Naples Federico I I
NETL
NSTL
