Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 31, 2021SensorsOpen Access

Tracking of Mental Workload with a Mobile EEG Sensor

View Full Paper
Ask AI
Bookmark
Share

Key result

A mobile EEG setup combined with machine learning models successfully discriminated between distinct levels of cognitive load with an accuracy of 86%.

Why the study?

Mental workload is an important aspect of learning performance and motivation, and the study investigated whether a mobile EEG setup could track it to evaluate cognitive training approaches.

Can a mobile EEG setup track mental workload during a cognitive task in healthy subjects?

Population

Twenty five healthy subjects

Comparison

Three-level N-back test with mobile EEG at two assessment time points

Authors

EKEkaterina KutafinaAHAnne HeiligersRPRadomir Popović

Discussion

Loading...

Member takes

Overview

Mobile EEG-ML may support cognitive workload tracking in healthy subjects; hypothesis-generating for clinical use pending prospective validation.

Structured PICO

Can a mobile EEG setup track mental workload during a cognitive task in healthy subjects?

P
Population
24 healthy adults aged 18 to 65 years completed a three-level N-back task while wearing a mobile EEG device to assess mental workload.
E
Exposure
Self-mounted mobile EEG device and tablet-based three-level N-back test
C
Comparator
Different levels of cognitive load (within-subject comparison)
O
Outcome
Changes in cognitive load (mental workload) as reflected by EEG alterationssurrogate

A mobile EEG setup combined with machine learning can accurately detect changes in mental workload, offering a potential tool for evaluating cognitive training.

Limitations

  • Lower signal-to-noise ratio compared to clinical-grade devices
  • Limited brain coverage of the mobile EEG device
  • Small sample size of healthy volunteers

Cite This Study

Kutafina et al. (2021) studied Healthy (n=24). Cognitive load (N-back task) vs. Baseline (rest) was evaluated on Classification accuracy of cognitive load (L0 vs L3) using artificial neural networks. A mobile EEG setup combined with machine learning models successfully discriminated between distinct levels of cognitive load with an accuracy of 86%.

synapsesocial.com/papers/6a9ef4100bf853f8dc192d45https://doi.org/10.3390/s21155205
View Full Paper
Ask AI
Bookmark
Share