Automatic seizure detection using a novel EEG feature based on nonlinear complexity

Abstract

Epileptic seizure detection using EEGs is a heavy workload of traditional visual inspection for diagnosing epilepsy. Therefore, more and more research on automatic seizure detection have been developed in recent years. The appropriate feature extraction method and efficient classifier are recognized to be crucial in the successful realization. In this paper, we first create a novel feature extraction method based on fuzzy conditional Renyi entropy (FCRE), which focuses on characterizing the physiological complexity of the underlying signal transduction processes. Then we propose an automatic seizure detection method FCRE-ELM, which integrates the fuzzy conditional Renyi entropy FCRE and extreme learning machine (ELM) for differentiating seizure EEGs from non-seizure EEGs or normal EEGs. The experimental results on the open EEG database have shown that the proposed method FCRE-ELM does a good job in epileptic seizure detection while preserving the efficiency and simplicity.