Abstract:Epilepsy is one of the most common neurological disorders in the world. Prompt detection of seizure onset from electroencephalogram (EEG) signals can improve the treatment of epileptic patients. This paper presents a new adaptive patient-specific seizure onset detection framework that dynamically selects a feature from enhanced EEG signals to discriminate seizures from normal brain activity. The proposed framework employs principal component analysis and common spatial patterns to enhance the EEG signals and u… Show more
“…In [49], they first calculated the fuzzy entropy of EEG signals from different states, then a feature selection method has been used, and finally based on the optimal features, the support vector machine (SVM) was employed to make classifications. In [50], they presented a framework that employs principle component analysis and common spatial patterns to enhance the EEG signals and uses the extracted discriminative feature as an input for adaptive distance-based change point detector to make the final decision. And in [51], a novel framework was proposed, the morphological features were extracted based on the local binary pattern operator, and K-nearest neighbor classifier was used for classification.…”
Electroencephalogram (EEG) contains important physiological information that can reflect the activity of human brain, making it useful for epileptic seizure detection and epilepsy diagnosis. However visual inspection of large amounts of EEG by human expert is time-consuming, and meanwhile there are often inconsistences in judgement between physicians. In this paper, we develop a unified framework for early epileptic seizure detection and epilepsy diagnosis, which includes two phases. In the first phase, the signal intensity is first calculated for each data point of the given EEG, enabling the well-known autoregressive moving average (ARMA) model to characterize the dynamic behavior of the EEG time series. The residual error between the predicted value of learned ARMA model and the actually observed value is used as the anomaly score to support a null hypothesis testing for making epileptic seizure decision. The epileptic seizure detection phase can provide a quick detection for anomaly EEG patterns, but the resulting suspicious segment may include epilepsy or other disordering EEG activities thus required to be identified. Therefore, in the second phase, we use pattern recognition technique to classify the suspicious EEG segments. In particular, we propose a new and practical classifier based on a pairwise of one-class SVMs for epilepsy diagnosis. The proposed classifier requires normal and epilepsy data for training, but can recognize normal, epilepsy and even other disorders that would not be trained in the training samples. This point is practical and meaningful in real clinic scenarios as the input EEG may include other brain disordering diseases besides of epilepsy. We conducted experiments on the publicly-available Bern-Barcelona and CHB-MIT EEG database, respectively, to validate the effectiveness of the proposed framework, and our method achieved classification accuracy of 93% and 94% on them. Comprehensive experimental results, outperforming the state-of-the-arts, suggest its great potentials in real applications.
“…In [49], they first calculated the fuzzy entropy of EEG signals from different states, then a feature selection method has been used, and finally based on the optimal features, the support vector machine (SVM) was employed to make classifications. In [50], they presented a framework that employs principle component analysis and common spatial patterns to enhance the EEG signals and uses the extracted discriminative feature as an input for adaptive distance-based change point detector to make the final decision. And in [51], a novel framework was proposed, the morphological features were extracted based on the local binary pattern operator, and K-nearest neighbor classifier was used for classification.…”
Electroencephalogram (EEG) contains important physiological information that can reflect the activity of human brain, making it useful for epileptic seizure detection and epilepsy diagnosis. However visual inspection of large amounts of EEG by human expert is time-consuming, and meanwhile there are often inconsistences in judgement between physicians. In this paper, we develop a unified framework for early epileptic seizure detection and epilepsy diagnosis, which includes two phases. In the first phase, the signal intensity is first calculated for each data point of the given EEG, enabling the well-known autoregressive moving average (ARMA) model to characterize the dynamic behavior of the EEG time series. The residual error between the predicted value of learned ARMA model and the actually observed value is used as the anomaly score to support a null hypothesis testing for making epileptic seizure decision. The epileptic seizure detection phase can provide a quick detection for anomaly EEG patterns, but the resulting suspicious segment may include epilepsy or other disordering EEG activities thus required to be identified. Therefore, in the second phase, we use pattern recognition technique to classify the suspicious EEG segments. In particular, we propose a new and practical classifier based on a pairwise of one-class SVMs for epilepsy diagnosis. The proposed classifier requires normal and epilepsy data for training, but can recognize normal, epilepsy and even other disorders that would not be trained in the training samples. This point is practical and meaningful in real clinic scenarios as the input EEG may include other brain disordering diseases besides of epilepsy. We conducted experiments on the publicly-available Bern-Barcelona and CHB-MIT EEG database, respectively, to validate the effectiveness of the proposed framework, and our method achieved classification accuracy of 93% and 94% on them. Comprehensive experimental results, outperforming the state-of-the-arts, suggest its great potentials in real applications.
“…This example shows that the development of approach for automatic EEG signal analysis can be useful in diagnostics because it allows deciding whether a person has epilepsy without the occurrence of epileptic seizure. Investigation of automatic EEG signal is thus useful in the development of decision support systems for early diagnosis of epilepsy [11], [13], [14].…”
Section: Introductionmentioning
confidence: 99%
“…Data mining methods for signal classification, and EEG signal in particular, include two steps [14]. The first of them is signal preprocessing and the second is classification itself.…”
The analysis of EEG signal is a relevant problem in health informatics, and its development can help in detection of epileptic's seizures. The diagnosis is based on classification of EEG signal. Different methods and algorithms for classification of EEG signals with an accepted level of reliability and accuracy have been developed over years. All these methods have two steps that are signal preprocessing and classification. The goal of the preprocessing step is removing noise and reduction of the initial signal dimensionality. The signal dimensionality reduction is required by classification methods, but its result is a loss of small information before the classification. In this paper, an approach for EEG signal classification that takes this loss of information into account is considered. The novelty of the considered approach is usage of fuzzy classifier in the classification step. This classifier allows taking uncertainty of initial data into account, which is caused by loss of some information during dimensionality reduction of initial signal. However, application of fuzzy classifier needs modification of the preprocessing step because it requires data in fuzzy form. Therefore, fuzzification procedure is added to the preprocessing step. In this paper, Fuzzy Decision Tree (FDT) is used as the fuzzy classifier for the epileptic's seizure detection. Its application allows achieving 99.5% accuracy of the classification of epileptic's seizure. The comparison with other studies shows that FDT is very effective for task of epileptic's seizure detection.
“…This work is very time-consuming and error-prone [1]. Therefore, in recent years, automatic seizure detection has attracted a lot of attention and various algorithms are presented based on frequency analysis [2][3][4][5], time analysis [4][5][6], time-frequency analysis [7][8][9][10][11], and nonlinear analysis [12,13].…”
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.