4 papers
What Does Explainable AI Mean in Practice? Evaluative Requirements from a Longitudinal Clinical Case Study
Tor Sporsem, Stine Rasdal Finserås, Lars Adde +1
This paper reports a case study on how explainability requirements were elicited during the development of an AI system for predicting cerebral palsy (CP) risk in infants. Over 18…
Choose Your Explanation: A Comparison of SHAP and GradCAM in Human Activity Recognition
Felix Tempel, Daniel Groos, Espen Alexander F. Ihlen +2
Explaining machine learning (ML) models using eXplainable AI (XAI) techniques has become essential to make them more transparent and trustworthy. This is especially important in hi…
Explaining Human Activity Recognition with SHAP: Validating Insights with Perturbation and Quantitative Measures
Felix Tempel, Espen Alexander F. Ihlen, Lars Adde +1
In Human Activity Recognition (HAR), understanding the intricacy of body movements within high-risk applications is essential. This study uses SHapley Additive exPlanations (SHAP)…
Towards Biomarker Discovery for Early Cerebral Palsy Detection: Evaluating Explanations Through Kinematic Perturbations
Kimji N. Pellano, Inga Strümke, Daniel Groos +3
Cerebral Palsy (CP) is a prevalent motor disability in children, for which early detection can significantly improve treatment outcomes. While skeleton-based Graph Convolutional Ne…