Automatic Seizure Detection in ECoG by Differential Operator and Windowed Variance

The detection of epileptic seizure signals based on fuzzy entropy

“…As reported in Majumdar and Vardhan (2011), the complexity of epileptic brain activity signals exhibit significant differences between the seizure and non-seizure periods. Progress in understanding these states has been vigorous as a result of gains achieved by investigators employing the study of brain entropy.…”

Band-sensitive seizure onset detection via CSP-enhanced EEG features

“…Enhancing seizure features while simultaneously attenuating nonseizure features can decrease the burden on the classification algorithm and improve the detector's overall performance in terms of sensitivity, detection onset latency, and false alarm rate. In [20], the authors propose a method based on EEG signal differentiation to enhance seizure features in an attempt to better detect the onset of a seizure via a windowed variance method. A seizure is characterized by abnormal synchronization in neuron firing, and thus, sharp spiking activities in quick succession are observed.…”

“…It has been found that differentiation accentuates the spiking activity while suppressing the background, thus, aiding in the detection of seizure onset using the windowed variance detection method. The detector in [20] achieves a sensitivity of 89.83%, latency of 9.2 s, and a false detection rate of 0.125 per hour. In [21], the regions of the brain involved in epilepsy are estimated by using the method of common spatial pattern (CSP) [22,23].…”

Correlation Analysis and Modeling of EEG – EMG Signal for Startle-Induced Seizures

“…After applying the DW to the data of EEG signal and EMG signal it discriminates between the pre-ictal and ictal states better. Majumdar and Vardhan (2011) the Fig. 3a and b shows the EEG signal and pre-processed signal.…”