Explainable artificial intelligence (xai) on timeseries data: A survey
Most of state of the art methods applied on time series consist of deep learning methods that
are too complex to be interpreted. This lack of interpretability is a major drawback, as several …
are too complex to be interpreted. This lack of interpretability is a major drawback, as several …
A Review of the Applications of Explainable Machine Learning for Lithium–Ion Batteries: From Production to State and Performance Estimation
Lithium–ion batteries play a crucial role in clean transportation systems including EVs,
aircraft, and electric micromobilities. The design of battery cells and their production process …
aircraft, and electric micromobilities. The design of battery cells and their production process …
[HTML][HTML] Knowledge graph-based rich and confidentiality preserving Explainable Artificial Intelligence (XAI)
JM Rožanec, B Fortuna, D Mladenić - Information fusion, 2022 - Elsevier
The paper proposes a novel architecture for explainable artificial intelligence based on
semantic technologies and artificial intelligence. We tailor the architecture for the domain of …
semantic technologies and artificial intelligence. We tailor the architecture for the domain of …
Uncertainty-aware deep ensembles for reliable and explainable predictions of clinical time series
K Wickstrøm, KØ Mikalsen… - IEEE Journal of …, 2020 - ieeexplore.ieee.org
Deep learning-based support systems have demonstrated encouraging results in numerous
clinical applications involving the processing of time series data. While such systems often …
clinical applications involving the processing of time series data. While such systems often …
Metrics and evaluations of time series explanations: An application in affect computing
N Fouladgar, M Alirezaie, K Främling - IEEE Access, 2022 - ieeexplore.ieee.org
Explainable artificial intelligence (XAI) has shed light on enormous applications by clarifying
why neural models make specific decisions. However, it remains challenging to measure …
why neural models make specific decisions. However, it remains challenging to measure …
Causal inference in non-linear time-series using deep networks and knockoff counterfactuals
W Ahmad, M Shadaydeh… - 2021 20th IEEE …, 2021 - ieeexplore.ieee.org
Estimating causal relations is vital in understanding the complex interactions in multivariate
time series. Non-linear coupling of variables is one of the major challenges in accurate …
time series. Non-linear coupling of variables is one of the major challenges in accurate …
Global explanations for multivariate time series models
Several explainable AI algorithms have been proposed to help make machine learning
models more interpretable and trustworthy. However in spite of numerous methodological …
models more interpretable and trustworthy. However in spite of numerous methodological …
Learning from Complex Medical Data Sources
J Rebane - 2022 - diva-portal.org
Large, varied, and time-evolving data sources can be observed across many domains and
present a unique challenge for classification problems, in which traditional machine learning …
present a unique challenge for classification problems, in which traditional machine learning …