Data fusion for paroxysmal events’ classification from EEG

Long-term video-EEG monitoring for paroxysmal events.

BACKGROUND Long term video-electroencephalography monitoring (VEM) has been widely used for the diagnosis, classification, and management of seizures. Few studies have systemically examined its safety issues and clinical utility. This prospective study investigates the general clinical application of long term VEM in the management of paroxysmal events. METHODS This study cohort consisted of ...

Video-EEG monitoring of paroxysmal events in the elderly.

OBJECTIVES To determine the importance of video-EEG monitoring (VEM) in elderly patients with various paroxysmal events. MATERIAL AND METHODS We retrospectively identified 16 subjects > or = 60 years old out of 834 (1.9%; 7 females, mean age 67.8 +/- 7.7 years), who were admitted to the Video-EEG Unit between 1997 and 2005 and compared data between those with and without epileptic events. R...

Data Fusion for Object Classification

Objective evaluation metrics for automatic classification of EEG events

The evaluation of machine learning algorithms in biomedical fields for applications involving sequential data lacks standardization. Common quantitative scalar evaluation metrics such as sensitivity and specificity can often be misleading depending on the requirements of the application. Evaluation metrics must ultimately reflect the needs of users yet be sufficiently sensitive to guide algorit...

Classification of EEG Signals for Discrimination of Two Imagined Words

In this study, a Brain-Computer Interface (BCI) in Silent-Talk application was implemented. The goal was an electroencephalograph (EEG) classifier for three different classes including two imagined words (Man and Red) and the silence. During the experiment, subjects were requested to silently repeat one of the two words or do nothing in a pre-selected random order. EEG signals were recorded by ...