Abstract
Complex sleep stage transition rules pose a challenge for the
learning of inter-epoch context with Deep Neural Networks (DNNs) in
ElectroEncephaloGraphy (EEG) based sleep scoring. While DNNs were
able to overcome the limits of expert systems, the dominant bidirectional
Long Short-Term Memory (LSTM) still has some limitations of
Recurrent Neural Networks. We propose a sleep Self-Attention Model
(SAM) that replaces LSTMs for inter-epoch context modelling in a sleep
scoring DNN. With the ability to access distant EEG as easily as adjacent
EEG, we aim to improve long-term dependency learning for critical
sleep stages such as Rapid Eye Movement (REM). Restricting attention
to a local scope reduces computational complexity to a linear one with
respect to recording duration. We evaluate SAM on two public sleep
EEG datasets: MASS-SS3 and SEDF-78 and compare it to literature
and an LSTM baseline model via a paired t-test. On MASS-SS3 SAM
achieves κ = 0.80, which is equivalent to the best reported result, with no
significant difference to baseline. On SEDF-78 SAM achieves κ = 0.78,
surpassing previous best results, statistically significant, with +4% F1-
score improvement in REM. Strikingly, SAM achieves these results with
a model size that is at least 50 times smaller than the baseline.
Originalsprache | Englisch |
---|---|
Titel | Neural Information Processing - 28th International Conference, ICONIP 2021, Sanur, Bali, Indonesia, December 8–12, 2021, Proceedings, Part III |
Seiten | 380-389 |
Seitenumfang | 10 |
DOIs | |
Publikationsstatus | Veröffentlicht - 2021 |
Research Field
- Exploration of Digital Health
Schlagwörter
- Attention
- Sleep scoring
- Inter-epoch context