The Temple University Hospital EEG corpus

The recently established Neural Engineering Data Consortium (NEDC) is in the process of developing its first large-scale corpus. This corpus, known as the Temple University Hospital EEG Corpus, upon completion, will total over 20,000 EEG studies, and include patient information, medical histories and physician assessments, making it the largest and most comprehensive publicly released EEG corpus. For the first time, there will be sufficient data to support the application of state of the art machine learning algorithms. In this paper, we present pilot results of experiments in which we attempted to predict some basic attributes of an EEG from the raw EEG data using a pilot database of 100 EEGs. Standard machine learning approaches are shown to be capable of predicting commonly occurring events from simple features with high accuracy on closed-loop testing, and can deliver error rates slightly below 50% on a 12-way open set classification problem.