Towards Robust Neuroadaptive HCI: Exploring Modern Machine Learning Methods to Estimate Mental Workload From EEG Signals

Abstract : Estimating mental workload from brain signals such as Electroencephalography (EEG) has proven very promising in multiple Human-Computer Interaction (HCI) applications , e.g., to design games or educational applications with adaptive difficulty, or to assess how cognitively difficult to use an interface can be. However, current EEG-based workload estimation may not be robust enough for some practical applications. Indeed, the currently obtained work-load classification accuracies are relatively low, making the resulting estimations not fully trustable. This paper thus studies promising modern machine learning algorithms, including Riemannian geometry-based methods and Deep Learning, to estimate workload from EEG signals. We study them with both user-specific and user-independent calibration , to go towards calibration-free systems. Our results suggested that a shallow Convolutional Neural Network obtained the best performance in both conditions, outperform-ing state-of-the-art methods on the used data sets. This suggests that Deep Learning can bring new possibilities in HCI.
Complete list of metadatas

Cited literature [17 references]  Display  Hide  Download

https://hal.inria.fr/hal-01849055
Contributor : Fabien Lotte <>
Submitted on : Wednesday, July 25, 2018 - 2:24:08 PM
Last modification on : Tuesday, September 17, 2019 - 10:36:28 AM
Long-term archiving on : Friday, October 26, 2018 - 2:25:24 PM

File

lbw1521-appriouA.pdf
Files produced by the author(s)

Identifiers

Citation

Aurélien Appriou, Andrzej Cichocki, Fabien Lotte. Towards Robust Neuroadaptive HCI: Exploring Modern Machine Learning Methods to Estimate Mental Workload From EEG Signals. ACM CHI Conference on Human Factors in Computing Systems - Extended Abstracts (Late Breaking Work), Apr 2018, Montreal, Canada. ⟨10.1145/3170427.3188617⟩. ⟨hal-01849055⟩

Share

Metrics

Record views

551

Files downloads

469