An improved approximate entropy based epilepsy seizure detection using multi-wavelet and artificial neural networks

Abstract

Epilepsy seizure is the result of the transient and unexpected electrical disturbance of the brain signal. The detection of epilepsy is only possible by analysing the normal and abnormal changes of brain electrical signal. The detection of epilepsy, which includes EEG recordings for the spikes and seizures, is very time consuming, especially in the case of long recordings. In this paper, an Artificial Intelligence (AI) based epilepsy detection technique is proposed. The technique is the combination of Multi-Wavelet Transform (MWT) and Artificial Neural Network (ANN). MWT is a technique based on wavelet theory, which is used to extract the features of EEG signal. The irregularity of EEG signal is measured by using the propose Improved Approximate Entropy (IApE). ANN is an AI that used to detect the type of EEG signal. The proposed technique is implemented, tested and the sensitivity, specificity, accuracy, precision response of IApE and ApE are compared.