Optimizing Channel Selection for Seizure Detection

by   Vinit Shah, et al.

Interpretation of electroencephalogram (EEG) signals can be complicated by obfuscating artifacts. Artifact detection plays an important role in the observation and analysis of EEG signals. Spatial information contained in the placement of the electrodes can be exploited to accurately detect artifacts. However, when fewer electrodes are used, less spatial information is available, making it harder to detect artifacts. In this study, we investigate the performance of a deep learning algorithm, CNN-LSTM, on several channel configurations. Each configuration was designed to minimize the amount of spatial information lost compared to a standard 22-channel EEG. Systems using a reduced number of channels ranging from 8 to 20 achieved sensitivities between 33 alarms increased dramatically (e.g., over 300 per 24 hours) when the number of channels was further reduced. Baseline performance of a system that used all 22 channels was 39 was the only system that included referential channels, the rapid increase in the false alarm rate as the number of channels was reduced underscores the importance of retaining referential channels for artifact reduction. This cautionary result is important because one of the biggest differences between various types of EEGs administered is the type of referential channel used.


page 1

page 2

page 3

page 4


Improved EEG Classification by factoring in sensor topography

Electroencephalography (EEG) serves as an effective diagnostic tool for ...

Robust learning from corrupted EEG with dynamic spatial filtering

Building machine learning models using EEG recorded outside of the labor...

Multiple Time Series Fusion Based on LSTM An Application to CAP A Phase Classification Using EEG

Biomedical decision making involves multiple signal processing, either f...

Analysis of artifacts in EEG signals for building BCIs

Brain-Computer Interface (BCI) is an essential mechanism that interprets...

Self-Supervised Learning for Anomalous Channel Detection in EEG Graphs: Application to Seizure Analysis

Electroencephalogram (EEG) signals are effective tools towards seizure a...

The WQN algorithm to adaptively correct artifacts in the EEG signal

Wavelet quantile normalization (WQN) is a nonparametric algorithm design...

Classification of eye-state using EEG recordings: speed-up gains using signal epochs and mutual information measure

The classification of electroencephalography (EEG) signals is useful in ...

Please sign up or login with your details

Forgot password? Click here to reset