Seizure prediction using undulated global and local features

Mohammad Zavid Parvez, Manoranjan Paul

Research output: Contribution to journalArticlepeer-review

46 Citations (Scopus)
7 Downloads (Pure)


In this study, a seizure prediction method is proposed based on a patient-specific approach by extracting undulated global and local features of preictal/ictal and interictal periods of EEG signals. The proposed method consists of feature extraction, classification, and regularization. The undulated global feature is extracted using phase correlation between two consecutive epochs of EEG signals and an undulated local feature is extracted using the fluctuation and deviation of EEG signals within the epoch. These features are further used for classification of preictal/ictal and interictal EEG signals. A regularization technique is applied on the classified outputs for the reduction of false alarms and improvement of the overall prediction accuracy (PA). The experimental results confirm that the proposed method provides high PA (i.e., 95.4%) with low false positive per hour using intracranial EEG signals in different brain locations of 21 patients from a benchmark dataset. Combining global and local features enables the transition point to be determined between different types of signals with greater accuracy, resulting successful versus unsuccessful prediction of seizure. The theoretical contribution of this study may provide an opportunity for the development of a clinical device to predict forthcoming seizure in real time.

Original languageEnglish
Article number7451217
Pages (from-to)208-217
Number of pages10
JournalIEEE Transactions on Biomedical Engineering
Issue number1
Early online dateApr 2016
Publication statusPublished - Jan 2017


Dive into the research topics of 'Seizure prediction using undulated global and local features'. Together they form a unique fingerprint.

Cite this