Epileptic seizure classification using statistical sampling and a novel feature selection algorithm
This work addresses the challenge of interpreting long EEG signals for epilepsy diagnosis, though it appears incremental as it builds on existing methods with specific improvements.
The authors tackled automated epileptic seizure detection from EEG signals by proposing a two-step minimization technique involving statistical sampling and a novel feature selection algorithm, resulting in experimental results that outperform some state-of-the-art methods.
Epilepsy is a well-known neuronal disorder that can be identified by interpretation of the electroencephalogram (EEG) signal. Usually, the length of an EEG signal is quite long which is challenging to interpret manually. In this work, we propose an automated epileptic seizure detection method by applying a two-step minimization technique: first, we reduce the data points using a statistical sampling technique and then, we minimize the number of features using our novel feature selection algorithm. We then apply different machine learning algorithms for performance measurement of the proposed feature selection algorithm. The experimental results outperform some of the state-of-the-art methods for seizure detection using the reduced data points and the least number of features.