Temporal data are frequently encountered in a wide range of domains such as bio-informatics, medicine, finance and engineering, among many others. They are naturally present in applications covering language, motion and vision analysis, or more emerging ones as energy efficient building, smart cities, dynamic social media or sensor networks. Contrary to static data, temporal data are of complex nature, they are generally noisy, of high dimensionality, they may be non stationary (i.e. first order statistics vary with time) and irregular (involving several time granularities), they may have several invariant domain-dependent factors as time delay, translation, scale or tendency effects. These temporal peculiarities make limited the majority of standard statistical models and machine learning approaches, that mainly assume i.i.d data, homoscedasticity, normality of residuals, etc. To tackle such challenging temporal data, one appeals for new advanced approaches at the intersection of statistics, time series analysis, signal processing and machine learning. Defining new approaches that transcend boundaries between several domains to extract valuable information from temporal data is undeniably a hot topic in the near future, that has been yet the subject of active research this last decade.
The proposed workshop welcomes papers that cover, but are not limited to, one or several of the following topics:
- Temporal data clustering
- Classification and regression of univariate and multivariate time series
- Early classification of temporal data
- Deep learning and learning representations for temporal data
- Metric and kernel learning for temporal data
- Modeling temporal dependencies
- Time series forecasting
- Time series annotation, segmentation and anomaly detection
- Spacial-temporal statistical analysis
- Functional data analysis methods
- Data streams
- Interpretable time-series analysis methods
- Dimensionality reduction, sparsity, algorithmic complexity and big data challenges
- Applications, including bio-informatics, medical, energy consumption, on temporal data
- Benchmarking and assessment methods for temporal data
We welcome contributions that address aspects including, but not limited to: novel techniques, innovative use and applications, techniques for the use of hybrid models. We are also happy to invite papers describing industry time series management platforms, in particular those that raise open questions for which there are no current off-the-shelf solutions.
