Relation between prognostics predictor evaluation metrics and local interpretability SHAP values

DOI10.1016/J.ARTINT.2022.103667OpenAlexW4213228517MaRDI QIDQ2124455FDOQ2124455

Marcia L. Baptista, Kai Goebel, Elsa M. P. Henriques

Publication date: 11 April 2022

Published in: Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.artint.2022.103667

zbMATH Keywords

monotonicityprognosabilitylocal interpretabilitymodel-agnostic interpretabilitySHAP valuestrendability

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Cites Work

• Title not available (Why is that?)
• Survival analysis with temporal covariate effects
• Fuzzy sets
• Title not available (Why is that?)
• An experiment in linguistic synthesis with a fuzzy logic controller
• Title not available (Why is that?)
• Explanation in artificial intelligence: insights from the social sciences
• Title not available (Why is that?)
• ANOVA method applied to proton exchange membrane fuel cell ageing forecasting using an echo state network
• Explaining individual predictions when features are dependent: more accurate approximations to Shapley values
• Online sequential echo state network with sparse RLS algorithm for time series prediction

Cited In (1)

• On the failings of Shapley values for explainability

Uses Software

• t-SNE
• shap
• Grad-CAM
• NormLIME

This page was built for publication: Relation between prognostics predictor evaluation metrics and local interpretability SHAP values

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2124455)