IDEAS home Printed from https://ideas.repec.org/a/plo/pone00/0234178.html
   My bibliography  Save this article

Deep learning for EEG-based Motor Imagery classification: Accuracy-cost trade-off

Author

Listed:
  • Javier León
  • Juan José Escobar
  • Andrés Ortiz
  • Julio Ortega
  • Jesús González
  • Pedro Martín-Smith
  • John Q Gan
  • Miguel Damas

Abstract

Electroencephalography (EEG) datasets are often small and high dimensional, owing to cumbersome recording processes. In these conditions, powerful machine learning techniques are essential to deal with the large amount of information and overcome the curse of dimensionality. Artificial Neural Networks (ANNs) have achieved promising performance in EEG-based Brain-Computer Interface (BCI) applications, but they involve computationally intensive training algorithms and hyperparameter optimization methods. Thus, an awareness of the quality-cost trade-off, although usually overlooked, is highly beneficial. In this paper, we apply a hyperparameter optimization procedure based on Genetic Algorithms to Convolutional Neural Networks (CNNs), Feed-Forward Neural Networks (FFNNs), and Recurrent Neural Networks (RNNs), all of them purposely shallow. We compare their relative quality and energy-time cost, but we also analyze the variability in the structural complexity of networks of the same type with similar accuracies. The experimental results show that the optimization procedure improves accuracy in all models, and that CNN models with only one hidden convolutional layer can equal or slightly outperform a 6-layer Deep Belief Network. FFNN and RNN were not able to reach the same quality, although the cost was significantly lower. The results also highlight the fact that size within the same type of network is not necessarily correlated with accuracy, as smaller models can and do match, or even surpass, bigger ones in performance. In this regard, overfitting is likely a contributing factor since deep learning approaches struggle with limited training examples.

Suggested Citation

  • Javier León & Juan José Escobar & Andrés Ortiz & Julio Ortega & Jesús González & Pedro Martín-Smith & John Q Gan & Miguel Damas, 2020. "Deep learning for EEG-based Motor Imagery classification: Accuracy-cost trade-off," PLOS ONE, Public Library of Science, vol. 15(6), pages 1-30, June.
  • Handle: RePEc:plo:pone00:0234178
    DOI: 10.1371/journal.pone.0234178
    as

    Download full text from publisher

    File URL: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0234178
    Download Restriction: no

    File URL: https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0234178&type=printable
    Download Restriction: no

    File URL: https://libkey.io/10.1371/journal.pone.0234178?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Leigh R. Hochberg & Mijail D. Serruya & Gerhard M. Friehs & Jon A. Mukand & Maryam Saleh & Abraham H. Caplan & Almut Branner & David Chen & Richard D. Penn & John P. Donoghue, 2006. "Neuronal ensemble control of prosthetic devices by a human with tetraplegia," Nature, Nature, vol. 442(7099), pages 164-171, July.
    2. Ali Oghabian & Sami Kilpinen & Sampsa Hautaniemi & Elena Czeizler, 2014. "Biclustering Methods: Biological Relevance and Application in Gene Expression Analysis," PLOS ONE, Public Library of Science, vol. 9(3), pages 1-10, March.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Benjamin I Rapoport & Lorenzo Turicchia & Woradorn Wattanapanitch & Thomas J Davidson & Rahul Sarpeshkar, 2012. "Efficient Universal Computing Architectures for Decoding Neural Activity," PLOS ONE, Public Library of Science, vol. 7(9), pages 1-13, September.
    2. Ujwal Chaudhary & Bin Xia & Stefano Silvoni & Leonardo G Cohen & Niels Birbaumer, 2017. "Brain–Computer Interface–Based Communication in the Completely Locked-In State," PLOS Biology, Public Library of Science, vol. 15(1), pages 1-25, January.
    3. Nuri F Ince & Rahul Gupta & Sami Arica & Ahmed H Tewfik & James Ashe & Giuseppe Pellizzer, 2010. "High Accuracy Decoding of Movement Target Direction in Non-Human Primates Based on Common Spatial Patterns of Local Field Potentials," PLOS ONE, Public Library of Science, vol. 5(12), pages 1-11, December.
    4. No-Sang Kwak & Klaus-Robert Müller & Seong-Whan Lee, 2017. "A convolutional neural network for steady state visual evoked potential classification under ambulatory environment," PLOS ONE, Public Library of Science, vol. 12(2), pages 1-20, February.
    5. Michael Riss, 2014. "FTSPlot: Fast Time Series Visualization for Large Datasets," PLOS ONE, Public Library of Science, vol. 9(4), pages 1-16, April.
    6. Yasuhiko Nakanishi & Takufumi Yanagisawa & Duk Shin & Ryohei Fukuma & Chao Chen & Hiroyuki Kambara & Natsue Yoshimura & Masayuki Hirata & Toshiki Yoshimine & Yasuharu Koike, 2013. "Prediction of Three-Dimensional Arm Trajectories Based on ECoG Signals Recorded from Human Sensorimotor Cortex," PLOS ONE, Public Library of Science, vol. 8(8), pages 1-9, August.
    7. Ke Yu & Hasan AI-Nashash & Nitish Thakor & Xiaoping Li, 2014. "The Analytic Bilinear Discrimination of Single-Trial EEG Signals in Rapid Image Triage," PLOS ONE, Public Library of Science, vol. 9(6), pages 1-10, June.
    8. Zheng Li & Joseph E O'Doherty & Timothy L Hanson & Mikhail A Lebedev & Craig S Henriquez & Miguel A L Nicolelis, 2009. "Unscented Kalman Filter for Brain-Machine Interfaces," PLOS ONE, Public Library of Science, vol. 4(7), pages 1-18, July.
    9. Tomislav Milekovic & Tonio Ball & Andreas Schulze-Bonhage & Ad Aertsen & Carsten Mehring, 2013. "Detection of Error Related Neuronal Responses Recorded by Electrocorticography in Humans during Continuous Movements," PLOS ONE, Public Library of Science, vol. 8(2), pages 1-20, February.
    10. Eric A Pohlmeyer & Babak Mahmoudi & Shijia Geng & Noeline W Prins & Justin C Sanchez, 2014. "Using Reinforcement Learning to Provide Stable Brain-Machine Interface Control Despite Neural Input Reorganization," PLOS ONE, Public Library of Science, vol. 9(1), pages 1-12, January.
    11. Josh Merel & David Carlson & Liam Paninski & John P Cunningham, 2016. "Neuroprosthetic Decoder Training as Imitation Learning," PLOS Computational Biology, Public Library of Science, vol. 12(5), pages 1-24, May.
    12. Andrés Úbeda & Enrique Hortal & Eduardo Iáñez & Carlos Perez-Vidal & Jose M Azorín, 2015. "Assessing Movement Factors in Upper Limb Kinematics Decoding from EEG Signals," PLOS ONE, Public Library of Science, vol. 10(5), pages 1-12, May.
    13. Ujwal Chaudhary & Ioannis Vlachos & Jonas B. Zimmermann & Arnau Espinosa & Alessandro Tonin & Andres Jaramillo-Gonzalez & Majid Khalili-Ardali & Helge Topka & Jens Lehmberg & Gerhard M. Friehs & Alain, 2022. "Spelling interface using intracortical signals in a completely locked-in patient enabled via auditory neurofeedback training," Nature Communications, Nature, vol. 13(1), pages 1-9, December.
    14. Hong Gi Yeom & June Sic Kim & Chun Kee Chung, 2014. "High-Accuracy Brain-Machine Interfaces Using Feedback Information," PLOS ONE, Public Library of Science, vol. 9(7), pages 1-7, July.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:plo:pone00:0234178. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: plosone (email available below). General contact details of provider: https://journals.plos.org/plosone/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.