Dataset Open Access

An EEG dataset for cross-session mental workload estimation: Passive BCI competition of the Neuroergonomics Conference 2021

Hinss, Marcel F.; Darmet, Ludovic; Somon, Bertille; Jahanpour, Emilie; Lotte, Fabien; Ladouce, Simon; Roy, Raphaëlle N.

Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="" xmlns:oai_dc="" xmlns:xsi="" xsi:schemaLocation="">
  <dc:creator>Hinss, Marcel F.</dc:creator>
  <dc:creator>Darmet, Ludovic</dc:creator>
  <dc:creator>Somon, Bertille</dc:creator>
  <dc:creator>Jahanpour, Emilie</dc:creator>
  <dc:creator>Lotte, Fabien</dc:creator>
  <dc:creator>Ladouce, Simon</dc:creator>
  <dc:creator>Roy, Raphaëlle N.</dc:creator>
  <dc:description>The dataset is part of a new open EEG database designed to answer a need for more publicly available EEG-based dataset to design and benchmark passive brain-computer interface pipelines (as detailed in [Hinss2021]). This database is currently being created and will be fully released before the end of the year. It will include data acquired over 30 participant, 4 tasks and 3 sessions. For this competition, hosted by the Neuroergonomics Conference 2021, only one task and half the participants will be analyzed. Hence, this competition focuses on a renowned task that elicits various levels of mental/cognitive workload: the Multi-Atribute Task Battery-II (MATB-II) developed by NASA ( It is composed of 4 sub-tasks: system monitoring, tracking, resource management and communications. By varying the number and complexity of the sub-tasks, 3 levels of workload were elicited (verified through statistical analyzes of both subjective and objective -behavioral and cardiac- data). Each difficulty level was performed by 15 subjects (6 female; 9 average 25 y.o.) during 5 minutes per session, in a pseudo-randomized order. Each session was separated by 7 days. We used a 62 actiChamp EEG channels device (BrainProducts; electrode placement 10-20 system).


For the competition, your goal is to predict the mental workload for a given subject (intra-subject estimation) using the EEG data from another session (inter-session adaptation). More information on the conference website and in the documentation file.</dc:description>
  <dc:description>The project was validated by the local ethical committee of the University of Toulouse (CER number 2021-342).</dc:description>
  <dc:subject>Passive BCI</dc:subject>
  <dc:subject>Physiological computing</dc:subject>
  <dc:title>An EEG dataset for cross-session mental workload estimation: Passive BCI competition of the Neuroergonomics Conference 2021</dc:title>
All versions This version
Views 965432
Downloads 2,0401,130
Data volume 148.5 GB99.3 GB
Unique views 800380
Unique downloads 768454


Cite as