Abstract:In this study, a seizure prediction method is proposed based on a patient-specific approach by extracting undulated global and local features of preictal/ictal and interictal periods of EEG signals. The proposed method consists of feature extraction, classification, and regularization. The undulated global feature is extracted using phase correlation between two consecutive epochs of EEG signals and an undulated local feature is extracted using the fluctuation and deviation of EEG signals within the epoch. The… Show more
“…It is nontrivial to note that the SPH was implicitly set to zero, which means prediction at a time close to or at seizure onset can be counted as a successful prediction. Likewise, research conducted by Zhang & Parhi (2016) and Parvez & Paul (2017) also implied the use of zero SPH, which will not be compared directly with our results. Among the rest of the studies listed in Table 5, Eftekhar et al (2014) had a very good prediction sensitivity of 90.95%…”
Section: Resultsmentioning
confidence: 81%
“…A lightweight approach based on spike rate achieved 75.8% sensitivity and FPR of 0.09/h (Li et al, 2013). By use of the synchronization information, a method based on phase-match error of two consecutive epochs and variation within each epoch resulted in 95.4% sensitivity and FPR of 0.36/h (Parvez & Paul, 2017).…”
Seizure prediction has attracted growing attention as one of the most challenging predictive data analysis efforts to improve the life of patients with drug-resistant epilepsy and tonic seizures. Many outstanding studies have reported great results in providing sensible indirect (warning systems) or direct (interactive neural stimulation) control over refractory seizures, some of which achieved high performance. However, to achieve high sensitivity and a low false prediction rate, many of these studies relied on handcraft feature extraction and/or tailored feature extraction, which is performed for each patient independently. This approach, however, is not generalizable, and requires significant modifications for each new patient within a new dataset. In this article, we apply convolutional neural networks to different intracranial and scalp electroencephalogram (EEG) datasets and propose a generalized retrospective and patient-specific seizure prediction method. We use the short-time Fourier transform on 30-s EEG windows to extract information in both the frequency domain and the time domain. The algorithm automatically generates optimized features for each patient to best classify preictal and interictal segments. The method can be applied to any other patient from any dataset without the need for manual feature extraction. The proposed approach achieves sensitivity of 81.4%, 81.2%, and 75% and a false prediction rate of 0.06/h, 0.16/h, and 0.21/h on the Freiburg Hospital intracranial EEG dataset, the Boston Children's Hospital-MIT scalp EEG dataset, and the American Epilepsy Society Seizure Prediction Challenge dataset, respectively. Our prediction method is also statistically better than an unspecific random predictor for most of the patients in all three datasets.
“…It is nontrivial to note that the SPH was implicitly set to zero, which means prediction at a time close to or at seizure onset can be counted as a successful prediction. Likewise, research conducted by Zhang & Parhi (2016) and Parvez & Paul (2017) also implied the use of zero SPH, which will not be compared directly with our results. Among the rest of the studies listed in Table 5, Eftekhar et al (2014) had a very good prediction sensitivity of 90.95%…”
Section: Resultsmentioning
confidence: 81%
“…A lightweight approach based on spike rate achieved 75.8% sensitivity and FPR of 0.09/h (Li et al, 2013). By use of the synchronization information, a method based on phase-match error of two consecutive epochs and variation within each epoch resulted in 95.4% sensitivity and FPR of 0.36/h (Parvez & Paul, 2017).…”
Seizure prediction has attracted growing attention as one of the most challenging predictive data analysis efforts to improve the life of patients with drug-resistant epilepsy and tonic seizures. Many outstanding studies have reported great results in providing sensible indirect (warning systems) or direct (interactive neural stimulation) control over refractory seizures, some of which achieved high performance. However, to achieve high sensitivity and a low false prediction rate, many of these studies relied on handcraft feature extraction and/or tailored feature extraction, which is performed for each patient independently. This approach, however, is not generalizable, and requires significant modifications for each new patient within a new dataset. In this article, we apply convolutional neural networks to different intracranial and scalp electroencephalogram (EEG) datasets and propose a generalized retrospective and patient-specific seizure prediction method. We use the short-time Fourier transform on 30-s EEG windows to extract information in both the frequency domain and the time domain. The algorithm automatically generates optimized features for each patient to best classify preictal and interictal segments. The method can be applied to any other patient from any dataset without the need for manual feature extraction. The proposed approach achieves sensitivity of 81.4%, 81.2%, and 75% and a false prediction rate of 0.06/h, 0.16/h, and 0.21/h on the Freiburg Hospital intracranial EEG dataset, the Boston Children's Hospital-MIT scalp EEG dataset, and the American Epilepsy Society Seizure Prediction Challenge dataset, respectively. Our prediction method is also statistically better than an unspecific random predictor for most of the patients in all three datasets.
“…Generally, for signal classification, more than one signal is required, because every movement is originated from different parts of the muscle and depends on a number of different muscles; therefore, the use of different channels helps to extract as much information as possible from the action(s) performed by the muscle(s). Among the various studies that have been done, it is common to work with four [1,9,13,23,29,38,39], six [19,40,41], or eight [2,7,11,22,30] channels for the acquisition of the signal; some research papers even work with a smaller number of channels [26,42]. Table 3 depicts an abridgement of the number of channels used by different studies and Table 4 summarizes the electrode type used and the place of electrode placement body.…”
Section: Referencementioning
confidence: 99%
“…[25] 1 [16,17,20,26] 2 [24,31] 3 [1,[8][9][10]13,21,23,29,35,39,[44][45][46] 4 [19,36,40,41] 6 [2,7,11,15,22,30,32,34] 8 [37] 12 [33] 14 [12,14] 16 [47] 22 Table 4. Electrodes type and place of electrode placement body.…”
This paper gives an overview of the different research works related to electromyographic signals (EMG) classification based on Support Vector Machines (SVM). The article summarizes the techniques used to make the classification in each reference. Furthermore, it includes the obtained accuracy, the number of signals or channels used, the way the authors made the feature vector, and the type of kernels used. Hence, this article also includes a compilation about the bands used to filter signals, the number of signals recommended, the most commonly used sampling frequencies, and certain features that can create the characteristics of the vector. This research gathers articles related to different kinds of SVM-based classification and other tools for signal processing in the field.
“…CNN provides maximum classification accuracy and true positive rate. Parvez and Paul (2017) used phase correlation for feature extraction and least square support vector machine has been used for classification. U of v classification method has been applied as post processing for removing artifacts and to avoid misclassification.…”
Epilepsy is a disease in which frequent seizures occur due to abnormal activity of neurons. Patients affected by this disease can be treated with the help of medicines or surgical procedures. However, both of these methods are not quite useful. The only method to treat epilepsy patients effectively is to predict the seizure before its onset. It has been observed that abnormal activity in the brain signals starts before the occurrence of seizure known as the preictal state. Many researchers have proposed machine learning models for prediction of epileptic seizures by detecting the start of preictal state. However, pre-processing, feature extraction and classification remains a great challenge in the prediction of preictal state. Therefore, we propose a model that uses common spatial pattern filtering and wavelet transform for preprocessing, principal component analysis for feature extraction and support vector machines for detecting preictal state. We have applied our model on 23 subjects and an average sensitivity of 93.1% has been observed for 84 seizures.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.