Ilija Šimić
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ilija Šimić has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Eduardo Veas
Graz University of Technology, Graz, Austria
2 shared publications - Adam Mourad
VIRTUAL VEHICLE Research GmbH, Inffeldgasse 21A, 8010 Graz, Austria
1 shared publication - Amil Salihi
VIRTUAL VEHICLE Research GmbH, Inffeldgasse 21A, 8010 Graz, Austria
1 shared publication - Christian Partl
Know-Center GmbH, Austria
1 shared publication Eduardo Veas
Graz University of Technology, Graz, Austria
1 shared publication- Franz Pichler
VIRTUAL VEHICLE Research GmbH, Inffeldgasse 21A, 8010 Graz, Austria
1 shared publication
Latest Publications
- Open Access
- 22 July 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-30
A comprehensive analysis of perturbation methods in explainable AI feature attribution validation for neural time series classifiers
In domains where AI model predictions have significant consequences, such as industry, medicine, and finance, the need for explainable AI (XAI) is of utmost importance. However, ensuring that explanation methods provide faithful and trustworthy explanations requires rigorous validation. Feature attribution methods (AMs) are among the most prevalent explanation methods, as they identify decisive aspects that influence model predictions through feature importance estimates. Evaluating the correctness of AMs is typically done by systematically perturbing features according to their estimated importance and measuring the impact on the classifier’s performance. This paper extends our previous work which revealed flaws in the most commonly used metric for validating AMs when applied to time series data. In this work we introduce a novel metric, the Consistency-Magnitude-Index, which facilitates a faithful assessment of feature importance attribution. Additionally, we introduce an adapted methodology for robust faithfulness evaluation, leveraging a set of diverse perturbation methods. Our work includes an extended evaluation of AMs on time series data, that presents the influence and importance of perturbation methods and region size selection in relation to dataset and model characteristics. Based on the results of our extensive evaluation, we provide guidelines for future AM faithfulness assessments. Finally, we demonstrate our methodology through a concrete multivariate time series example.
- 22 July 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-30
Open AccessA comprehensive analysis of perturbation methods in explainable AI feature attribution validation for neural time series classifiers
In domains where AI model predictions have significant consequences, such as industry, medicine, and finance, the need for explainable AI (XAI) is of utmost importance. However, ensuring that explanation methods provide faithful and trustworthy explanations requires rigorous validation. Feature attribution methods (AMs) are among the most prevalent explanation methods, as they identify decisive aspects that influence model predictions through feature importance estimates. Evaluating the correctness of AMs is typically done by systematically perturbing features according to their estimated importance and measuring the impact on the classifier’s performance. This paper extends our previous work which revealed flaws in the most commonly used metric for validating AMs when applied to time series data. In this work we introduce a novel metric, the Consistency-Magnitude-Index, which facilitates a faithful assessment of feature importance attribution. Additionally, we introduce an adapted methodology for robust faithfulness evaluation, leveraging a set of diverse perturbation methods. Our work includes an extended evaluation of AMs on time series data, that presents the influence and importance of perturbation methods and region size selection in relation to dataset and model characteristics. Based on the results of our extensive evaluation, we provide guidelines for future AM faithfulness assessments. Finally, we demonstrate our methodology through a concrete multivariate time series example.
- Open Access
- 2 May 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (9) , 5078
Explainable Artificial Intelligence for State of Charge Estimation of Lithium-Ion Batteries
The production of electric vehicle (EV) batteries is playing an increasingly significant role in the decarbonization of the mobility sector. In order for EV batteries to be competitive against internal combustion engines, it is crucial to maximize the primary and secondary life cycles of batteries. This necessitates a battery management system that can ensure performance, safety, and longevity. State of Charge (SoC) estimation is important for such a system, as it ensures efficiency of the battery’s performance, and it is necessary for the prediction of the battery’s health and lifespan. Existing SoC estimation methods heavily depend on laboratory tests, which are both costly and time consuming. Additionally, the simulated nature of laboratory settings cannot guarantee robustness when the same method is applied to field data collected from real-world scenarios. A suitable alternative to this problem is the use of data-driven approaches. The goal of this work is the estimation of SoC with a real-world dataset using neural networks. Furthermore, we demonstrate how explainable AI (xAI) and importance estimate can be applied to inform what signals and which parts of a signal are important for SoC estimation. This helps to reduce redundancy, and it provides more information regarding the relationships within battery cells that are otherwise obscured by the complexity of the battery. The methods that we used resulted in a mean squared error (MSE) of as low as 3 × , and the information provided by xAI suggested that it is possible to discard up to 25% of the input profile whilst retaining similar performance.- 2 May 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (9) , 5078
Open AccessExplainable Artificial Intelligence for State of Charge Estimation of Lithium-Ion Batteries
The production of electric vehicle (EV) batteries is playing an increasingly significant role in the decarbonization of the mobility sector. In order for EV batteries to be competitive against internal combustion engines, it is crucial to maximize the primary and secondary life cycles of batteries. This necessitates a battery management system that can ensure performance, safety, and longevity. State of Charge (SoC) estimation is important for such a system, as it ensures efficiency of the battery’s performance, and it is necessary for the prediction of the battery’s health and lifespan. Existing SoC estimation methods heavily depend on laboratory tests, which are both costly and time consuming. Additionally, the simulated nature of laboratory settings cannot guarantee robustness when the same method is applied to field data collected from real-world scenarios. A suitable alternative to this problem is the use of data-driven approaches. The goal of this work is the estimation of SoC with a real-world dataset using neural networks. Furthermore, we demonstrate how explainable AI (xAI) and importance estimate can be applied to inform what signals and which parts of a signal are important for SoC estimation. This helps to reduce redundancy, and it provides more information regarding the relationships within battery cells that are otherwise obscured by the complexity of the battery. The methods that we used resulted in a mean squared error (MSE) of as low as 3 × , and the information provided by xAI suggested that it is possible to discard up to 25% of the input profile whilst retaining similar performance. - Open Access
- 18 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 33-36
XAIVIER: Time Series Classifier Verification with Faithful Explainable AI
Ensuring that a machine learning model performs as intended is a critical step before it can be used in practice. This is commonly done by measuring a model’s predictive performance (e.g., accuracy). However, in high-stakes settings it is often necessary to verify on which data aspects the model actually relies on. This demo presents XAIVIER, the eXplainable AI VIsual Explorer and Recommender, a web application for interactive XAI on time series data. XAIVIER supports dataset exploration and model inspection, allowing users to explain model predictions using various explainer methods. An explainer recommender is provided to advise users which explainer delivers most faithful explanations for their dataset and model. Finally, explanation-based grouping is provided to reveal the model’s underlying decision-making strategies. The proposed set of features aims to cover the full model verification use case for time series classifiers. A demo of XAIVIER is available at https://xai-explorer-demo.know-center.at
- 18 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 33-36
Open AccessXAIVIER: Time Series Classifier Verification with Faithful Explainable AI
Ensuring that a machine learning model performs as intended is a critical step before it can be used in practice. This is commonly done by measuring a model’s predictive performance (e.g., accuracy). However, in high-stakes settings it is often necessary to verify on which data aspects the model actually relies on. This demo presents XAIVIER, the eXplainable AI VIsual Explorer and Recommender, a web application for interactive XAI on time series data. XAIVIER supports dataset exploration and model inspection, allowing users to explain model predictions using various explainer methods. An explainer recommender is provided to advise users which explainer delivers most faithful explanations for their dataset and model. Finally, explanation-based grouping is provided to reveal the model’s underlying decision-making strategies. The proposed set of features aims to cover the full model verification use case for time series classifiers. A demo of XAIVIER is available at https://xai-explorer-demo.know-center.at