Отрывок: Table 1 also provides AUC results for the features. AUC 0.5 indicates that there is no dependency between feature and target variable. As a result, only important features with AUC>0.6 were used in a model. 3.2. Model Training and Testing Dataset was randomly divided into train and test parts in 70/30 proportion. Coefficients evaluation was performed on a train subset, and prediction was made on test subset. As a result, AUC was meas...
Полная запись метаданных
Поле DC Значение Язык
dc.contributor.authorObukhov, Yu.V.-
dc.contributor.authorObukhov, K.Yu.-
dc.contributor.authorNikitov, S.A.-
dc.date.accessioned2018-05-18 11:10:12-
dc.date.available2018-05-18 11:10:12-
dc.date.issued2018-
dc.identifierDspace\SGAU\20180517\69473ru
dc.identifier.citationObukhov Yu.V. Metric Classification of Traumatic Brain Injury Epileptiform Activity from Electroencephalography Data/ Obukhov Yu.V., Obukhov K.Yu., Nikitov S.A.// Сборник трудов IV международной конференции и молодежной школы «Информационные технологии и нанотехнологии» (ИТНТ-2018) - Самара: Новая техника, 2018. - С.2871-2873.ru
dc.identifier.urihttp://repo.ssau.ru/handle/Informacionnye-tehnologii-i-nanotehnologii/Metric-Classification-of-Traumatic-Brain-Injury-Epileptiform-Activity-from-Electroencephalography-Data-69473-
dc.description.abstractPrediction algorithm of Epilepsy Seizures and Sleep Spindles in electroencephalography (EEG) data is studied in this article. EEG data was measured in rats with Post-Traumatic Epilepsy (PTE) before and after Traumatic Brain Injury (TBI). Experts manually partitioned records into two classes: one, which refers to epileptic activity - Epilepsy Seizures, and second class, which refers to normal behavior of rats - Sleep Spindles (SS). Proposed algorithm was trained and tested on the collected data, which contained EEG features, previously extracted by detection algorithm. Feature importance was evaluated, and logistic regression model was built. Cross validation results were 79% Area Under Curve (AUC) for the best model.ru
dc.description.sponsorshipAuthors would like to express gratitude to Ilya Komoltsev and Ivan Kershner for providing the dataset. The research was supported by the Russian Scientific Foundation, project No. 16-11-10258.ru
dc.language.isoenru
dc.publisherНовая техникаru
dc.subjectTraumatic brain injuryru
dc.subjectEEGru
dc.subjectWaveletru
dc.subjectSpectrogramru
dc.subjectRidgesru
dc.subjectEvent detectionru
dc.subjectEpileptiform seizuresru
dc.subjectMetric classificationru
dc.subjectLogistic regressionru
dc.titleMetric Classification of Traumatic Brain Injury Epileptiform Activity from Electroencephalography Dataru
dc.typeArticleru
dc.textpartTable 1 also provides AUC results for the features. AUC 0.5 indicates that there is no dependency between feature and target variable. As a result, only important features with AUC>0.6 were used in a model. 3.2. Model Training and Testing Dataset was randomly divided into train and test parts in 70/30 proportion. Coefficients evaluation was performed on a train subset, and prediction was made on test subset. As a result, AUC was meas...-
Располагается в коллекциях: Информационные технологии и нанотехнологии

Файлы этого ресурса:
Файл Описание Размер Формат  
paper_387.pdfосновная статья724.42 kBAdobe PDFПросмотреть/Открыть
Показать базовое описание ресурса Просмотр статистики
Поделиться:



Все ресурсы в архиве электронных ресурсов защищены авторским правом, все права сохранены.