S5: Self-Supervised Learning Boosts Sleep Spindle Detection in Single-Channel EEG via Temporal Segmentation

Key Points

• This research aims to enhance the accuracy and efficiency of detecting sleep spindles in EEG signals using self-supervised learning.
• Developed a self-supervised learning approach to identify sleep spindles.
• Implemented a temporal segmentation strategy for EEG analysis.
• Created a graphical toolbox for user-friendly analysis of sleep spindle detection.
• Achieved precise detection of sleep spindles in single-channel EEG recordings.
• Demonstrated improved automation in spindle detection processes.