Ephrem Tibebe Mekonnen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ephrem Tibebe Mekonnen has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- André Almo
Technological University Dublin
1 shared publication - Attracta Brennan
School of Computer Science, University of Galway, Ireland
1 shared publication Luca Longo
School of Computer Science, College of Health and Science, Technological University Dublin, Dublin, Ireland
1 shared publication- Mariana Rocha
Technological University Dublin
1 shared publication - Maíra Amaral
Technological University Dublin
1 shared publication Pierpaolo Dondio
School of Computer Science, College of Health and Science, Technological University Dublin, Dublin, Ireland
1 shared publication
Latest Publications
- Open Access
- 20 September 2024
- Published by Frontiers Media SA in Frontiers in Artificial Intelligence
- Vol. 7, 1381921
A global model-agnostic rule-based XAI method based on Parameterized Event Primitives for time series classifiers
Time series classification is a challenging research area where machine learning and deep learning techniques have shown remarkable performance. However, often, these are seen as black boxes due to their minimal interpretability. On the one hand, there is a plethora of eXplainable AI (XAI) methods designed to elucidate the functioning of models trained on image and tabular data. On the other hand, adapting these methods to explain deep learning-based time series classifiers may not be straightforward due to the temporal nature of time series data. This research proposes a novel global post-hoc explainable method for unearthing the key time steps behind the inferences made by deep learning-based time series classifiers. This novel approach generates a decision tree graph, a specific set of rules, that can be seen as explanations, potentially enhancing interpretability. The methodology involves two major phases: (1) training and evaluating deep-learning-based time series classification models, and (2) extracting parameterized primitive events, such as increasing, decreasing, local max and local min, from each instance of the evaluation set and clustering such events to extract prototypical ones. These prototypical primitive events are then used as input to a decision-tree classifier trained to fit the model predictions of the test set rather than the ground truth data. Experiments were conducted on diverse real-world datasets sourced from the UCR archive, employing metrics such as accuracy, fidelity, robustness, number of nodes, and depth of the extracted rules. The findings indicate that this global post-hoc method can improve the global interpretability of complex time series classification models.
- 20 September 2024
- Published by Frontiers Media SA in Frontiers in Artificial Intelligence
- Vol. 7, 1381921
Open AccessA global model-agnostic rule-based XAI method based on Parameterized Event Primitives for time series classifiers
Time series classification is a challenging research area where machine learning and deep learning techniques have shown remarkable performance. However, often, these are seen as black boxes due to their minimal interpretability. On the one hand, there is a plethora of eXplainable AI (XAI) methods designed to elucidate the functioning of models trained on image and tabular data. On the other hand, adapting these methods to explain deep learning-based time series classifiers may not be straightforward due to the temporal nature of time series data. This research proposes a novel global post-hoc explainable method for unearthing the key time steps behind the inferences made by deep learning-based time series classifiers. This novel approach generates a decision tree graph, a specific set of rules, that can be seen as explanations, potentially enhancing interpretability. The methodology involves two major phases: (1) training and evaluating deep-learning-based time series classification models, and (2) extracting parameterized primitive events, such as increasing, decreasing, local max and local min, from each instance of the evaluation set and clustering such events to extract prototypical ones. These prototypical primitive events are then used as input to a decision-tree classifier trained to fit the model predictions of the test set rather than the ground truth data. Experiments were conducted on diverse real-world datasets sourced from the UCR archive, employing metrics such as accuracy, fidelity, robustness, number of nodes, and depth of the extracted rules. The findings indicate that this global post-hoc method can improve the global interpretability of complex time series classification models.
- 29 November 2023
- Published by Springer Nature
- p. 183-193
Not (Only) a Matter of Position: Player Traits Which Influence the Experience with the Leaderboard in a Digital Maths Game
- 29 November 2023
- Published by Springer Nature
- p. 183-193
Not (Only) a Matter of Position: Player Traits Which Influence the Experience with the Leaderboard in a Digital Maths Game