Adaptive filtering of EEG and epilepsy detection using Recurrence Quantification Analysis

This study presents the adaptive filtering of Electroencephalogram (EEG) signal and epileptic seizure detection using Recurrence Quantification Analysis (RQA). The adaptive filtering is used to remove line frequency artifact from EEG signal in which the parameters can be adjusted to maintain the input output relationship. The filtered output from adaptive filter is compared with the notch filter and wavelet filter and proven to be efficient in terms of Signal to Noise Ratio (SNR). The major advantage of choosing RQA is that, it provides better information even for short non-stationary and non linear signals where other methods fail to provide good results. And it requires no assumptions about data set size or distribution of the data. The algorithm is applied on epileptic EEG signal from CHB MIT database. The RQA measures are determined from the recurrence plot and its performance is measured in terms of sensitivity and specificity as 97.4% and 93.5% respectively.