Temple University Hospital EEG (TUH EEG) Resources

Mission

Our goal is to enable deep learning research in neuroscience by releasing the largest publicly available unencumbered database of EEG recordings. This ongoing project currently includes over 30,000 EEGs spanning the years from 2002 to present. Data collected can be used for both research and commercialization purposes.


Get Access

To request access to these resources, please fill out this form. You will receive an automatically-generated username and password via email. Please be patient since it takes a few minutes to receive the email.

Since these databases are quite large, it is best to transfer them via hard disk. If you are interested in this option, please follow the instructions here.

EEG Annotation
Electroencephalogram
Annotation of an EEG

What's New

  • (20190323) NEDC TUH EEG Seizure (v1.5.0): This release includes the expansion of the training dataset from 1,984 files to 4,597. Calibration sequences of the new data have been manually annotated and added to the seizure spreadsheet.
  • (20190308) IBM TUSZ Pre-Processed Data (v1.0.0): This is our first release of IBMPPD which preprocesses the TUH Seizure Detection Corpus using two methods, both of which use an FFT sliding window approach (STFT) in the beginning.
  • (20181217) Meysam Golmohammadi attended the International Conference on Machine Learning and Applications (ICMLA) and presented his paper on Deep Architectures for Spatio-Temporal Modeling.

Read More