The automatic seizure detection is significant for epilepsy diagnosis and it can alleviate the work intensity of inspecting prolonged electroencephalogram （EEG）. This paper presents and investigates a novel machine ...The automatic seizure detection is significant for epilepsy diagnosis and it can alleviate the work intensity of inspecting prolonged electroencephalogram （EEG）. This paper presents and investigates a novel machine learning approach utilizing gradient boosting to detect seizures from long-term EEG. We apply relative fluctuation index to extract features of long-term intracranial EEG data. A classifier trained with the gradient boosting algorithm is adopted to discriminate the seizure and non-seizure EEG signals. Smoothing and collar technique are finally used as post-processing in order to improve the detection accuracy further. The seizure detection method is assessed on Freiburg EEG datasets from 21 patients. The experimental results indicate that the proposed method yields an average sensitivity of 94. 60% with a false detection rate of 0. 18/h.展开更多
A new method of phase spectral analysis of EEG is proposed for the comparative analysis of phase spectra between normal EEG and epileptic EEG signals based on the wavelet decomposition technique. By using multiscale w...A new method of phase spectral analysis of EEG is proposed for the comparative analysis of phase spectra between normal EEG and epileptic EEG signals based on the wavelet decomposition technique. By using multiscale wavelet decomposition,the original EEGs are mapped to an orthogonal wavelet space,such that the variations of phase can be observed at multiscale. It is found that the phase (and phase difference) spectra of normal EEGs are distinct from that of epileptic EEGs. That is the variations of phase (and phase difference) of normal EEGs have a distinct periodic pattern with the electrical activity proceeds in the brain,but do not the epileptic EEGs. For epileptic EEGs,only at those transient points,the phase variations are obvious. In order to verify these results with the observational data,the phase variations of EEGs in principal component space are observed and found that,the features of phase spectra is in correspondence with that the wavelet space. These results make it possible to view the behavior of EEG rhythms as a dynamic spectrum.展开更多
基金Key Program of Natural Science Foundation of Shandong Province(No.ZR2013FZ002)The Program of Science and Technology of Suzhou(No.ZXY2013030)Independent Innovation Foundation of Shandong University(No.11170074611102)
文摘The automatic seizure detection is significant for epilepsy diagnosis and it can alleviate the work intensity of inspecting prolonged electroencephalogram （EEG）. This paper presents and investigates a novel machine learning approach utilizing gradient boosting to detect seizures from long-term EEG. We apply relative fluctuation index to extract features of long-term intracranial EEG data. A classifier trained with the gradient boosting algorithm is adopted to discriminate the seizure and non-seizure EEG signals. Smoothing and collar technique are finally used as post-processing in order to improve the detection accuracy further. The seizure detection method is assessed on Freiburg EEG datasets from 21 patients. The experimental results indicate that the proposed method yields an average sensitivity of 94. 60% with a false detection rate of 0. 18/h.
基金National Natural Science Foundation of China( Grant No.10 2 340 70 )NaturalScience Foundation of Fujian Province of China( Grant No.C0 310 0 2 8)
文摘A new method of phase spectral analysis of EEG is proposed for the comparative analysis of phase spectra between normal EEG and epileptic EEG signals based on the wavelet decomposition technique. By using multiscale wavelet decomposition,the original EEGs are mapped to an orthogonal wavelet space,such that the variations of phase can be observed at multiscale. It is found that the phase (and phase difference) spectra of normal EEGs are distinct from that of epileptic EEGs. That is the variations of phase (and phase difference) of normal EEGs have a distinct periodic pattern with the electrical activity proceeds in the brain,but do not the epileptic EEGs. For epileptic EEGs,only at those transient points,the phase variations are obvious. In order to verify these results with the observational data,the phase variations of EEGs in principal component space are observed and found that,the features of phase spectra is in correspondence with that the wavelet space. These results make it possible to view the behavior of EEG rhythms as a dynamic spectrum.
