Next Article in Journal
Real-Time Impedance Detection of Intra-Articular Space in a Porcine Model Using a Monopolar Injection Needle
Previous Article in Journal
A Priori-Based Subarray Selection Algorithm for DOA Estimation
Open AccessArticle

Evaluation of Hyperparameter Optimization in Machine and Deep Learning Methods for Decoding Imagined Speech EEG

1
Intelligent Systems Research Centre, Ulster University, Londonderry BT48 7JL, UK
2
Institute for Research in Social Sciences, Ulster University, Jordanstown BT37 0QB, UK
*
Author to whom correspondence should be addressed.
Sensors 2020, 20(16), 4629; https://doi.org/10.3390/s20164629
Received: 10 June 2020 / Revised: 10 August 2020 / Accepted: 13 August 2020 / Published: 17 August 2020
(This article belongs to the Special Issue Brain–Computer Interfaces: Advances and Challenges)
Classification of electroencephalography (EEG) signals corresponding to imagined speech production is important for the development of a direct-speech brain–computer interface (DS-BCI). Deep learning (DL) has been utilized with great success across several domains. However, it remains an open question whether DL methods provide significant advances over traditional machine learning (ML) approaches for classification of imagined speech. Furthermore, hyperparameter (HP) optimization has been neglected in DL-EEG studies, resulting in the significance of its effects remaining uncertain. In this study, we aim to improve classification of imagined speech EEG by employing DL methods while also statistically evaluating the impact of HP optimization on classifier performance. We trained three distinct convolutional neural networks (CNN) on imagined speech EEG using a nested cross-validation approach to HP optimization. Each of the CNNs evaluated was designed specifically for EEG decoding. An imagined speech EEG dataset consisting of both words and vowels facilitated training on both sets independently. CNN results were compared with three benchmark ML methods: Support Vector Machine, Random Forest and regularized Linear Discriminant Analysis. Intra- and inter-subject methods of HP optimization were tested and the effects of HPs statistically analyzed. Accuracies obtained by the CNNs were significantly greater than the benchmark methods when trained on both datasets (words: 24.97%, p < 1 × 10–7, chance: 16.67%; vowels: 30.00%, p < 1 × 10–7, chance: 20%). The effects of varying HP values, and interactions between HPs and the CNNs were both statistically significant. The results of HP optimization demonstrate how critical it is for training CNNs to decode imagined speech. View Full-Text
Keywords: electroencephalography (EEG); brain–computer interface (BCI); convolutional neural networks (CNN); deep learning; machine learning; hyperparameter optimization; imagined speech electroencephalography (EEG); brain–computer interface (BCI); convolutional neural networks (CNN); deep learning; machine learning; hyperparameter optimization; imagined speech
Show Figures

Figure 1

MDPI and ACS Style

Cooney, C.; Korik, A.; Folli, R.; Coyle, D. Evaluation of Hyperparameter Optimization in Machine and Deep Learning Methods for Decoding Imagined Speech EEG. Sensors 2020, 20, 4629.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop