Sleep Learning

Computational pipeline for scoring animal sleep from EEG/EMG

About

Welcome to the homepage of the Sleep Learning web platform which implements animal sleep scoring algorithm described in the corresponding paper which you can find here [link]. Our program takes EEG/EMG signals recorded over certain period of time e.g. 8-24 hours, as an input and then automatically evaluates their sleep dynamics by segmenting EEG/EMGs into 4 sec epochs and then categorizing each epoch into either (a) one of the three basic vigilance states: wakefulness, NREM, REM; or (b) one of three types of artifacts: wake-artifact, NREM-artifact, REM-artifact. Our machine learning-based method is designed to provide fast, accurate and parameter-free evaluation of animal sleep recordings. To obtain access to our platform, please write us at sleeplearning@ethz.ch.

Contributors

Djordje Miladinovic
ETH Zürich

Leader of the project and a PhD student at ETH Zurich. His interests lie in the area of multi-modal data fusion and dynamics learning from rich sensory data, especially with the application to sleep analysis.

Ami Beuret
ETH Zürich

PhD candidate at Information Science and Engineering group at ETH Zurich working on intersection of machine learning and medicine.

Stefan Bauer
ETH Zürich

Research Group Leader at the MPI for Intelligent Systems in Tübingen, working on the identification and learning of dynamical systems.

Joachim M. Buhmann
ETH Zürich

is full Professor for Computer Science at ETH Zurich since October 2003. His research interests cover the area of pattern recognition and data analysis, i.e., machine learning, statistical learning theory and applied statistics. The application areas range from computer vision and image analysis, remote sensing to bioinformatics.

Steven Brown
University of Zürich

is the section leader of the Chronobiology and Sleep Research group at the UZH's Institute of Pharmacology and Toxicology.

Software Workshop
Max Planck Institute for Intelligent Systems

The Software Workshop is a unique central scientific facility that brings together scientists and software engineers to translate basic research into software systems that can be used internally and deployed.

Contact Us

If you would like to use our service or if you have questions, comments or remarks please write to sleeplearning@ethz.ch.