EBUL

The collection and statistical analysis of physiological signals are ubiquitous in modern life, from the continuous monitoring of patients in hospitals to data obtained for neuroscience research. While statistical methods based on handcrafted quantities are efficient to capture well-identified effects, they require clear hypotheses on the underlying physiological processes. Alternatively, data-driven unsupervised approaches offer an opportunity to explore and leverage such signals for population well-being. Yet, off-the-shelve generic unsupervised algorithms remain limited. Physiological signals are recorded together with surrounding events, that are typically not exploited by unsupervised methods. Moreover, physiological signals can often be described by extracting characteristic events, such as heartbeat in ECG or steps in gait recordings. Leveraging this notion of events, the main objective of EBUL is to develop a new generation of unsupervised learning methods that jointly model physiological signals and events. EBUL will develop dedicated machine learning and statistical signal processing methods and favor the emergence of new challenges for these fields focusing on two open problems: 1) end-to-end unsupervised methods to jointly model physiological signals and events, and 2) physiological events' models with multivariate Point Processes. These challenges will be tackled through contributions to self-supervised learning methods and point processes. The methods developed in EBUL will have broad applications for fields where physical signals enriched with events are processed. Yet, the primary purpose of EBUL will be to process physiological signals, in particular in the neuroscience field. The tools developed through EBUL will be evaluated on general anesthesia data, to help anesthetists develop tools to improve patient care. The open-source software produced in EBUL will ensure a broad impact of the project.