EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhanced EEG Forecasting: A Probabilistic Deep Learning Approach

Hanna Pankka, Jaakko Lehtinen, Risto J Ilmoniemi, Timo Roine

Neural Computation · 18.03.2025 · 37 (4) · 793-814

DOI: 10.1162/neco_a_01743 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Neural Computation, online erschienen am 18.03.2025. Verfasst von Hanna Pankka und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neuroscience and Biomedical Engineering, Aalto University School of Science, FI-02150 Espoo, Finland hanna.e.pankka@aalto.fi. Hauptthemen laut MEDLINE: Electroencephalography, Deep Learning, Brain. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Research Council, European Union’s Horizon 2020 research and innovation program, Jenny and Antti Wihuri Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Forecasting electroencephalography (EEG) signals, that is, estimating future values of the time series based on the past ones, is essential in many real-time EEG-based applications, such as brain–computer interfaces and closed-loop brain stimulation. As these applications are becoming more and more common, the importance of a good prediction model has increased. Previously, the autoregressive model (AR) has been employed for this task; however, its prediction accuracy tends to fade quickly as multiple steps are predicted. We aim to improve on this by applying probabilistic deep learning to make robust longer-range forecasts. For this, we applied the probabilistic deep neural network model WaveNet to forecast resting-state EEG in theta- (4–7.5 Hz) and alpha-frequency (8–13 Hz) bands and compared it to the AR model. WaveNet reliably predicted EEG signals in both theta and alpha frequencies 150 ms ahead, with mean absolute errors of 1.0 ± 1.1 µV (theta) and 0.9 ± 1.1 µV (alpha), and outperformed the AR model in estimating the signal amplitude and phase. Furthermore, we found that the probabilistic approach offers a way of forecasting even more accurately while effectively discarding uncertain predictions. We demonstrate for the first time that probabilistic deep learning can be used to forecast resting-state EEG time series. In the future, the developed model can enhance the real-time estimation of brain states in brain–computer interfaces and brain stimulation protocols. It may also be useful for answering neuroscientific questions and for diagnostic purposes.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographyDeep LearningBrainHumansForecastingNeural Networks, ComputerBrain-Computer Interfaces

Autor:innen und Institutionen

  • Department of Neuroscience and Biomedical Engineering, Aalto University School of Science, FI-02150 Espoo, Finland hanna.e.pankka@aalto.fi.
  • Department of Computer Science, Aalto University School of Science, FI-02150 Espoo, Finland.
  • NVIDIA, FI-00180 Helsinki, Finland jaakko.lehtinen@aalto.fi.
  • Department of Neuroscience and Biomedical Engineering, Aalto University School of Science, FI-02150 Espoo, Finland risto.ilmoniemi@aalto.fi.
  • Department of Neuroscience and Biomedical Engineering, Aalto University School of Science, FI-02150 Espoo, Finland timo.roine@aalto.fi.

Förderung

  • European Research Council
  • European Union’s Horizon 2020 research and innovation program
  • Jenny and Antti Wihuri Foundation

Zitieren

APA

Pankka, H., Lehtinen, J., Ilmoniemi, R. J., & Roine, T. (2025). Enhanced EEG Forecasting: A Probabilistic Deep Learning Approach. Neural Computation, 37(4), 793-814. https://doi.org/10.1162/neco_a_01743

Vancouver

Pankka H, Lehtinen J, Ilmoniemi RJ, Roine T. Enhanced EEG Forecasting: A Probabilistic Deep Learning Approach. Neural Computation. 2025;37(4):793-814. doi:10.1162/neco_a_01743

BibTeX
@article{Pankka2025,
  author = {Pankka, Hanna and Lehtinen, Jaakko and Ilmoniemi, Risto J and Roine, Timo},
  title = {Enhanced EEG Forecasting: A Probabilistic Deep Learning Approach},
  journal = {Neural Computation},
  year = {2025},
  volume = {37},
  number = {4},
  pages = {793--814},
  doi = {10.1162/neco_a_01743}
}
Kostenlos starten →