optimized seizure detection algorithm: a fast approach for onset of epileptic in eeg signals using gt discriminant analysis and k-nn classifier

background: epilepsy is a severe disorder of the central nervous system that predisposes  the person to recurrent seizures. fifty million people worldwide suffer from  epilepsy; after alzheimer's and stroke, it is the third widespread nervous disorder. objective: in this paper, an algorithm to detect the onset of epileptic seizures  based on the analysis of brain electrical signals (eeg) has been proposed. 844 hours  of eeg were recorded form 23 pediatric patients consecutively with 163 occurrences  of seizures. signals had been collected from children's hospital boston with a sampling  frequency of 256 hz through 18 channels in order to assess epilepsy surgery. by  selecting effective features from seizure and non-seizure signals of each individual and  putting them into two categories, the proposed algorithm detects the onset of seizures  quickly and with high sensitivity. method: in this algorithm, l-sec epochs of signals are displayed in form of a thirdorder  tensor in spatial, spectral and temporal spaces by applying wavelet transform.  then, after applying general tensor discriminant analysis (gtda) on tensors and calculating  mapping matrix, feature vectors are extracted. gtda increases the sensitivity  of the algorithm by storing data without deleting them. finally, k-nearest neighbors  (knn) is used to classify the selected features. results: the results of simulating algorithm on algorithm standard dataset shows  that the algorithm is capable of detecting 98 percent of seizures with an average delay  of 4.7 seconds and the average error rate detection of three errors in 24 hours. conclusion: today, the lack of an automated system to detect or predict the seizure  onset is strongly felt.