ANN based Predictive Model for identifying Epileptic Seizures with Random Forest Feature Selection

Epilepsy is a neurological disorder that adversely affects the social life of the affected people. Nearly 65 million people were affected worldwide. In many cases, (nearly30%) of this disease cannot be healed with medications. However, seizure prediction will help in disease prevention. Encephalogram is the common test that helps to diagnose the epilepsy. The electrical activity of human brain can be recorded as EEG signals. The manual inspection to detect abnormalities in the epileptic form is more time-consuming and inaccurate. This arises a need for automated framework that helps in precisely distinguishing EEG signals. Various researchers have employed different machine-learning models for seizure prediction. But achieving high performance is still a challenging task. The proposed model provides a reliable system for seizure prediction with improved performance by using different ANN models. Neural network is presently a blazing technique in machine learning paradigm, which constitutes noble success in several healthcare data analysis. There are many ML models available for seizure detection with EEG signals. The existing models preprocess the data and extract the feature before classification. According to our knowledge, there is no work with ANN for seizure classification has been done on the preprocessed clinical dataset. This research work proposes a framework with preprocessed dataset and extracted time domain features. The proposed system provides automated seizure prediction framework, which integrates random-forest method for feature selection and ANN classifiers for seizure prediction. There are several forms of neural network, where everyone have their individual precise use case. In the proposed framework, different ANN methods like ANN with resilient back-propagation with weights, ANN with resilient back-propagation without weights and two types of globally convergent methods are used as classifiers with sigmoid as activation function and they are trained and tested as trail and error method to find the best number of hidden layers and nodes in each layer. According to the results, this framework provides a expedite analysis with the selected attributes of EEG signals to detect seizures and reduces time complexity in analyzing the large datasets. Among different ANN methods(RPROP+, RPROP-, SAG, SLR), SLR provides good accuracy as 99.56 % and precision as 99.2%.