Program of the workshop
The workshop will held on September 18, 2020. It will be organized fully virtually within the ECML conference system.
The main sessions of the workshop will be organized using Zoom platform. The virtual poster session is still under construction (Zoom or Discord).
All the connection information will be available on this webpage and on the ECML whova program manager (please, note that attending to this workshop is not free of charge. A registration to ECML conference is required).
All papers can be downloaded on the accepted papers page.
(local time at Ghent: CEST = UTC+2)
- 09h – 09h15: Workshop introduction by organizers Live session on Zoom
- 9h15 – 10h15: Session Temporal data: advanced representations Live session on Zoom
- Ordinal versus nominal time series classification by David Guijo-Rubio, Pedro Antonio Gutiérrez, Anthony Bagnall and César Hervás-Martínez
- Generalized chronicles for temporal sequence classification by Yann Dauxais and Thomas Guyet
- Multivariate time series unsupervised representation on a causality graph for health monitoring of mechanical systems by Edouard Pineau, Sébastien Razakarivony and Thomas Bonald
- 10h30 – 11h15 : Invited talk from Themis Palpanas Live session on ZoomScalable Machine Learning on Large Sequence Collections
- 11h20 – 12h10 : Spotlight presentations of the posters (5 minutes per poster, the list of the posters is here) Live session on Zoom
- Lunch break
- 13h – 14h: virtual poster session Discussion around the posters: we will organize one virtual room per poster where interested people can join and discuss with authors (click on icon to join the poster discussion)
- Temporal Exceptional Model Mining using Dynamic Bayesian Networks:
- “J’veux du soleil”: Towards a decade of solar irradiation data (La Réunion Island, SW Indian Ocean):
- Visual Analytics for Extracting Trends from Spatio-Temporal Data:
- Layered Integration Approach for Multi-view Analysis of Temporal Data:
- A Feature Selection Method for Multi-Dimension Time-Series Data:
- Real-Time Outlier Detection in Time Series Data of Water Sensors:
- Lightweight Temporal Self-Attention for Classifying Satellite Images Time Series:
- Creating and Characterising Electricity Load Profiles of Residential Buildings:
- Trust Assessment on Streaming Data: a Real Time Predictive Approach:
- 14h – 15h: Session Time series: Classification Live session on Zoom
- On the Usage and Performance of The Hierarchical Vote Collective of Transformation-based Ensembles version 1.0 (HIVE-COTE v1.0) by Anthony Bagnall, Michael Flynn, James Large, Jason Lines and Matthew Middlehurst
- Adversarial Regularization for Explainable-by-Design Time Series Classification by Yichang Wang, Rémi Emonet, Elisa Fromont, Simon Malinowski and Romain Tavenard
- A Model-Agnostic Approach to Quantifying the Informativeness of Explanation Methods for Time Series Classification by Thu Trang Nguyen, Thach Le Nguyen and Georgiana Ifrim
- 15h15 – 16h15: Session Time series: classification and forecasting Live session on Zoom
- Evolving data as a context to improve A/B-Tests by Emmanuelle Claeys, Pierre Gancarski, Myriam Maumy and Hubert Wassner
- Demand forecasting in the presence of privileged information by Mozhdeh Ariannezhad, Sebastian Schelter and Maarten de Rijke
- GANNSTER: Graph-augmented neural network spatio-temporal reasoner for traffic forecasting by Carlos Salort Sanchez, Alexander Wieder, Paolo Sottovia, Stefano Bortoli, Jan Baumbach and Cristian Axenie
- 16h15 – 16h30: Poster session (tentative) Live session on Zoom