TAILOR WP3 and WP4 would like to announce a new Coordinated Action focussed on Explainability & Time Series. The objective is to design novel methods for time series explanations and apply them into real case studies, such as high tide in Venice or similar. A first call for this Coordinated Action will be organised in January 2023.
About this Coordinated Action
The objective is to design novel methods for time series explanations [1,2,3] and apply them into real case studies, such as high tide in Venice etc.
 Riccardo Guidotti, Matteo D’Onofrio, Matrix Profile-Based Interpretable Time Series Classifier, Front. Artif. Intell. 4:699448. doi:10.3389/frai.2021.699448
 Riccardo Guidotti, Anna Monreale, Francesco Spinnato, Dino Pedreschi, Fosca Giannotti, Explaining any time series classifier, 2020 IEEE CogMI
 Theissler, A., Spinnato, F., Schlegel, U., & Guidotti, R. (2022). Explainable AI for Time Series Classification: A review, taxonomy and research directions. IEEE Access.
Datasets: TBA (ECG200?), Venice data, …
Duration: MXX for initial results; M48 for final results
Involved WP3 task(s): T3.1 Explainability, T3.7 Trustworthy AI as a whole, T4.3 Learning and reasoning with embeddings, knowledge graphs, & ontologies
CA leader: T3.1
Other WP(4-7) task(s):
Partner(s): UNIPI (Riccardo Guidotti), SNS (Francesco Spinnato), CNR (Umberto Straccia, Franco Alberto Cardillo), DFKI (Silke Balzert-Walter), SUPSI (Francesca Faraci), INRIA (Elisa Fromont), Liu (Fredrik Heintz), UCC (Andrea Visentin)
Output: Papers + Contribution for:
Involved WP3 tasks Workshop
Deliverable D3.1 Research Challenges and Technological Gaps of Trustworthy AI (report) [M42]
Deliverable D3.3: Synergies Industry, Challenges, Roadmap concerning Trustworthy AI (report) [M42]
How to participate
Contact Francesca Pratesi and Riccardo Guidotti