On sound-based interpretation of neonatal EEG
Abstract
Significant training is required to visually interpret neonatal EEG signals. This study explores alternative sound-based methods for EEG interpretation which are designed to allow for intuitive and quick differentiation... [ view full abstract ]
Significant training is required to visually interpret neonatal EEG signals. This study explores alternative sound-based methods for EEG interpretation which are designed to allow for intuitive and quick differentiation between healthy background activity and abnormal activity such as seizures. A novel method based on frequency and amplitude modulation (FM/AM) is presented. The algorithm is tuned to facilitate, in the audio domain, the perception of rhythmic activity which is specific to neonatal seizures. The method is compared with the previously developed phase vocoder algorithm for different time compressing factors. A survey is conducted amongst a cohort of non-EEG experts to quantitatively examine the performance of sound-based methods in comparison with the visual interpretation. It is shown that both sonification methods perform similarly well, with smaller variance in comparison with visual. A post-survey analysis of ear sensitivity to frequency evolution is presented.
Authors
-
Sergi Gómez Quintana
(University College Cork)
-
Mark O'sullivan
(University College Cork)
-
Sean Mathieson
(INFANT)
-
Geraldine B. Boylan
(INFANT)
-
Emanuel Popovici
(University College Cork)
-
Andriy Temko
(INFANT)
Topic Areas
Digital Signal Processing , AI and Machine Learning , Biomedical applications
Session
Fr1a » Biomedical (10:00 - Friday, 22nd June, 02.014 (Ashby))
Presentation Files
The presenter has not uploaded any presentation files.