Scribd
Upload
137 views1 page

001 - Automatic Detection and Characterization of Nocturnal Eye Movements PDF

This MSc project involves developing algorithms to automatically detect and characterize nocturnal eye movements from polysomnography data. The goal is to extract more information than current sleep staging methods by analyzing eye movement types and features. Supervised by experts from DTU and the Danish Center for Sleep Medicine, the project will use an existing eye movement dataset labeled by two experts to develop detectors for slow and rapid eye movements and identify distinguishing features. This advanced analysis could improve sleep diagnosis and further understanding of sleep physiology and disease pathophysiology.

Uploaded by

Sanchithya Ariyawansha
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
137 views1 page

001 - Automatic Detection and Characterization of Nocturnal Eye Movements PDF

This MSc project involves developing algorithms to automatically detect and characterize nocturnal eye movements from polysomnography data. The goal is to extract more information than current sleep staging methods by analyzing eye movement types and features. Supervised by experts from DTU and the Danish Center for Sleep Medicine, the project will use an existing eye movement dataset labeled by two experts to develop detectors for slow and rapid eye movements and identify distinguishing features. This advanced analysis could improve sleep diagnosis and further understanding of sleep physiology and disease pathophysiology.

Uploaded by

Sanchithya Ariyawansha
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

MSc project

Title:
Automatic detection and characterization of nocturnal eye movements (A collaboration between DTU
and Danish Center for Sleep Medicine, Rigshospitalet, Glostrup)

Introduction:
The basic understanding and classification of sleep staging relies on a classification dating back to 1968 by
Rechtshaffen and Kales. It divides sleep stages into Rapid Eye Movement (REM) and Non-REM (NREM)
sleep. Central to this classification is polysomnography (PSG) which assess complex electrophysiological
signals including brain activity measured by electroencephalography (EEG), eye movements measured by
electrooculography (EOG), motor activity by electromyography (EMG) and several other physiological
modalities. The current sleep classification relies on visual identification of specific patterns in the PSG
signals, and traditionally, the huge amount of data recorded is tremendously downsized to a simple
diagram (called a hypnogram) summing up the overall sleep architecture of the recording night. Therefore,
the simplistic analysis performed in the PSG data does not take into account important but unexploited
macro and micro sleep events. This results in limitations for both diagnosis and a deeper understanding of
the disease pathophysiology.
This project will exploit the micro sleep event eye movements that traditionally are identified as either
rapid (characteristic for REM sleep) or slow. Not many details are stated and not much is known about the
physiology or meaning of the different types of nocturnal eye movements, but duo to the neurons involved
in controlling them, it is of utmost important to detect and characterize them to forward the analysis and
understanding of sleep in health and disease.

Objectives:
The Danish Center for Sleep Medicine has developed a detailed routine for identification and labeling of
nocturnal eye movements, and has gathered data from two different experts. Using this dataset, this
project will be one of the first aiming at 1) developing detectors for slow and rapid eye movements, and 2)
extracting features that can help in characterizing (and defining) the different types of nocturnal eye
movements.

Supervisors:
Assoc. Professor Julie A. E. Christensen, DTU Elektro/Danish Center for Sleep Medicine
Professor, MD Poul J. Jennum, Danish Center for Sleep Medicine, Rigshospitalet, Glostrup

Prerequisities:
Experience with Matlab, signal processing and machine learning is required.

Contact:
Assoc. Professor Julie A. E. Christensen, DTU Elektro/Danish Center for Sleep Medicine: [email protected]

You might also like