Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.11159 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913056736411648 |
|---|---|
| author | Jutte, Annemarie Ahmed, Faizan Linssen, Jeroen van Keulen, Maurice |
| author_facet | Jutte, Annemarie Ahmed, Faizan Linssen, Jeroen van Keulen, Maurice |
| contents | In high-stakes domains, such as healthcare and industry, the explainability of AI-based decision-making has become crucial. Without insight into model reasoning, the reliability of these models cannot be ensured. Applications often rely on the time series data type which, unlike the image data type, is underexplored with respect to the development of explainable AI (XAI) techniques. Most existing XAI techniques for time series are focused on point- or subsequence-based explanations. This limits their usability since points and subsequences do not capture all relevant patterns and may not result in human-interpretable explainability. In this paper, we close this gap and propose a concept-based XAI approach (C-SHAP), where concepts are defined as high-level patterns extracted from the time series data. C-SHAP leverages the SHAP method to determine the influence of these concepts on predictions. The effectiveness of the developed framework is illustrated for use cases from healthcare and industry, in the form of Human Activity Recognition (HAR) and predictive maintenance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_11159 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | C-SHAP for time series: An approach to high-level temporal explanations Jutte, Annemarie Ahmed, Faizan Linssen, Jeroen van Keulen, Maurice Artificial Intelligence In high-stakes domains, such as healthcare and industry, the explainability of AI-based decision-making has become crucial. Without insight into model reasoning, the reliability of these models cannot be ensured. Applications often rely on the time series data type which, unlike the image data type, is underexplored with respect to the development of explainable AI (XAI) techniques. Most existing XAI techniques for time series are focused on point- or subsequence-based explanations. This limits their usability since points and subsequences do not capture all relevant patterns and may not result in human-interpretable explainability. In this paper, we close this gap and propose a concept-based XAI approach (C-SHAP), where concepts are defined as high-level patterns extracted from the time series data. C-SHAP leverages the SHAP method to determine the influence of these concepts on predictions. The effectiveness of the developed framework is illustrated for use cases from healthcare and industry, in the form of Human Activity Recognition (HAR) and predictive maintenance. |
| title | C-SHAP for time series: An approach to high-level temporal explanations |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2504.11159 |