IRIS PubliCatt
PubliCatt è il repository istituzionale ad accesso aperto dell'Università Cattolica del Sacro Cuore, dove gli utenti autorizzati afferenti all'Ateneo provvedono direttamente e autonomamente a depositare e a rendere visibili le proprie pubblicazioni, inserendo i dati descrittivi del documento stesso ("metadati", quali il titolo, autore, abstract, etc.) e, laddove possibile, il testo della pubblicazione stessa (full-text).
PubliCatt utilizza la piattaforma IRIS (Institutional Research Information System) sviluppata da CINECA.
EnglishThis paper addresses the prediction of epileptic seizures from the online analysis of EEG data. This problem is of paramount importance for the realization of monitoring/control units to be implanted on drug-resistant epileptic patients. The proposed solution relies in a novel way on autoregressive modeling of the EEG time series and combines a least-squares parameter estimator for EEG feature extraction along with a support vector machine (SVM) for binary classification between preictal/ictal and interictal states. This choice is characterized by low computational requirements compatible with a real-time implementation of the overall system. Moreover, experimental results on the Freiburg dataset exhibited correct prediction of all seizures (100 % sensitivity) and, due to a novel regularization of the SVM classifier based on the Kalman filter, also a low false alarm rate.
Chisci, L., Mavino, A., Perferi, G., Sciandrone, M., Anile, C., Colicchio, G., Fuggetta, F., Real-time epileptic seizure prediction using AR models and support vector machines., <<IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING>>, 2010; 2010 (Maggio): 1124-1132 [http://hdl.handle.net/10807/33879]
| Autori: | ||
| Titolo: | Real-time epileptic seizure prediction using AR models and support vector machines. | |
| Data di pubblicazione: | 2010 | |
| Abstract: | This paper addresses the prediction of epileptic seizures from the online analysis of EEG data. This problem is of paramount importance for the realization of monitoring/control units to be implanted on drug-resistant epileptic patients. The proposed solution relies in a novel way on autoregressive modeling of the EEG time series and combines a least-squares parameter estimator for EEG feature extraction along with a support vector machine (SVM) for binary classification between preictal/ictal and interictal states. This choice is characterized by low computational requirements compatible with a real-time implementation of the overall system. Moreover, experimental results on the Freiburg dataset exhibited correct prediction of all seizures (100 % sensitivity) and, due to a novel regularization of the SVM classifier based on the Kalman filter, also a low false alarm rate. | |
| Lingua: | Inglese | |
| Rivista: | ||
| Citazione: | Chisci, L., Mavino, A., Perferi, G., Sciandrone, M., Anile, C., Colicchio, G., Fuggetta, F., Real-time epileptic seizure prediction using AR models and support vector machines., <<IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING>>, 2010; 2010 (Maggio): 1124-1132 [http://hdl.handle.net/10807/33879] | |
| Appare nelle tipologie: | Articolo in rivista, Nota a sentenza |
File in questo prodotto:
Copyright © 2021