Seminar: Graduate Seminar
Deep-Learning-Based Classification of Cyclic Alternating Pattern Sleep Phases
Date:
November,27,2024
Start Time:
13:30 - 14:30
Location:
506, Zisapel Building
Zoom:
Zoom link
Add to:
Lecturer:
Yoav Kahana
Research Areas:
| The cyclic alternating pattern (CAP) is a periodic brain activity that occurs during non-REM sleep. It defines the microstructure of sleep and plays a crucial role in sleep assessment, as it is associated with various sleep disorders. CAP is primarily identified through EEG signals recorded during a polysomnography (PSG) study.
In this seminar, we present a novel algorithm that uses a convolutional neural network (CNN) to classify CAP phases using their time-frequency representations. The algorithm incorporates contextual information from the EEG signal and applies data augmentation tailored to its characteristics. An ablation study was conducted to evaluate and optimize the key components of the proposed algorithm. M.Sc. student under the supervision of Prof. Israel Cohen and Dr. Alon Amar.
|