Epileptic Seizure Prediction by Exploiting Spatiotemporal Relationship of EEG Signals Using Phase Correlation

Abstract

Automated seizure prediction has a potential in epilepsy monitoring, diagnosis, and rehabilitation. Electroencephalogram (EEG) is widely used for seizure detection and prediction. This paper proposes a new seizure prediction approach based on spatiotemporal relationship of EEG signals using phase correlation. This measures the relative change between current and reference vectors of EEG signals which can be used to identify preictal/ictal (before the actual seizure onset/ actual seizure period) and interictal (period between adjacent seizures) EEG signals to predict the seizure. The experiments show that the proposed method is less sensitive to artifacts and provides higher prediction accuracy (i.e., 91.95%) and lower number of false alarms compared to the state-of-the-art methods using intracranial EEG signals in different brain locations of 21 patients from a benchmark data set.

Epileptic seizure detection by combining robust‐principal component analysis and least square‐support vector machine

“…The performance of the proposed seizure detection method was compared with three state‐of‐the‐art methods . Table shows the performance comparison between our proposed method and those mentioned methods.…”

“…If no less than k positives are found within n consecutive windows, then all the n windows are labeled as “1”s; otherwise, are labeled as “0”s. We applied 3 ‐of‐ 5 analysis to identify the detection horizon for 0.25 s, and this produced better results. Figure shows the seizure detection result from the detection conducted in each 0.05s window based on the 3‐of‐5 analysis method.…”

Principle components analysis for seizures prediction using wavelet transform

“…Senger and Tetzlaff (2016) have applied principle component analysis (PCA) for preprocessing of EEG signals and then zero crossing levels have been observed and noted for prediction of epileptic seizure. Parvez and Paul (2016) has proposed that classification between preictal and interictal state for prediction of epileptic seizures need pre-processing as well as post processing of EEG signals. For pre-processing differential window has been applied on EEG signals to make them more distinct for classification.…”

Hybrid Dragonfly Optimization-Based Artificial Neural Network for the Recognition of Epilepsy

“…Parvez and Paul [24] put forth a seizure prediction method centered on the spatiotemporal relationship of the EEG using phase correlation. This technique measured the relative change betwixt the current & reference vectors of EEG signals.…”