Review of Machine and Deep Learning Techniques in Epileptic Seizure Detection using Physiological Signals and Sentiment Analysis

Epilepsy is one of the significant neurological disorders affecting nearly 65 million people worldwide. The repeated seizure characterized as epilepsy. Different algorithms were proposed for efficient detection using intracranial and surface EEG signals. In last decade, various machine learning techniques based on approaches proposed. This paper discusses different deep A wide range such support vector (SVM) classifiers, artificial neural network (ANN) classifier, a convolutional (CNN) long-short term memory (LSTM) are compared in this paper. effectiveness time-domain features, frequency domain time-frequency features discussed along with techniques. Along EEG, other physiological signals electrocardiogram used to enhance accuracy which recent years have found good classification accuracy. paper, an LSTM learning-network-based approach implemented state-of-the-art methods. achieved 96.5% seizure-nonseizure signal classification. Apart from analyzing signals, sentiment analysis also has potential detect seizure. Impact Statement- review gives summary research work related epileptic Manual detetion time consuming requires expertise. So intelligence automatic detection. researchers working developing ECG, accelerometer, analysis. There need that can discuss previous give further direction. We comparison table. It help researcher get overview both EEG-based approaches. new easily compare models decide model they want start on. practical application Sentiment another dimension summerizing it will prospective reader.