Functional Complex Networks Based on Operational Architectonics: Application on EEG-based Brain–computer Interface for Imagined Speech

Iliopoulos, A. C.; Papasotiriou, Ioannis

doi:10.1016/j.neuroscience.2021.11.045

Cited by 6 publications

(4 citation statements)

References 119 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several classical machine learning techniques have been used to approach imagined speech decoding for EEG-based BCI systems. Some on the most common algorithms include Linear Discriminant Analysis (LDA) (Chi et al, 2011 ; Song and Sepulveda, 2014 ; Lee et al, 2021b ), Support Vector Machines (SVM) (DaSalla et al, 2009 ; Garćıa et al, 2012 ; Kim et al, 2013 ; Riaz et al, 2014 ; Sarmiento et al, 2014 ; Zhao and Rudzicz, 2015 ; Arjestan et al, 2016 ; González-Castañeda et al, 2017 ; Hashim et al, 2017 ; Cooney et al, 2018 ; Moctezuma and Molinas, 2018 ; Agarwal and Kumar, 2021 ), Random Forests (RF) (González-Castañeda et al, 2017 ; Moctezuma and Molinas, 2018 ; Moctezuma et al, 2019 ), k-Nearest-Neighbors (kNN) (Riaz et al, 2014 ; Bakhshali et al, 2020 ; Agarwal and Kumar, 2021 ; Rao, 2021 ; Dash et al, 2022 ), Naive Bayes (Dash et al, 2020a ; Agarwal and Kumar, 2021 ; Iliopoulos and Papasotiriou, 2021 ; Lee et al, 2021b ), and Relevance Vector Machines (RVM) (Liang et al, 2006 ; Matsumoto and Hori, 2014 ). Furthermore, deep learning approaches have recently taken a huge role for imagined speech recognition.…”

Section: Classification Techniques In Literaturementioning

confidence: 99%

A State-of-the-Art Review of EEG-Based Imagined Speech Decoding

Lopez-Bernal

Balderas

Ponce

et al. 2022

Front. Hum. Neurosci.

View full text Add to dashboard Cite

Currently, the most used method to measure brain activity under a non-invasive procedure is the electroencephalogram (EEG). This is because of its high temporal resolution, ease of use, and safety. These signals can be used under a Brain Computer Interface (BCI) framework, which can be implemented to provide a new communication channel to people that are unable to speak due to motor disabilities or other neurological diseases. Nevertheless, EEG-based BCI systems have presented challenges to be implemented in real life situations for imagined speech recognition due to the difficulty to interpret EEG signals because of their low signal-to-noise ratio (SNR). As consequence, in order to help the researcher make a wise decision when approaching this problem, we offer a review article that sums the main findings of the most relevant studies on this subject since 2009. This review focuses mainly on the pre-processing, feature extraction, and classification techniques used by several authors, as well as the target vocabulary. Furthermore, we propose ideas that may be useful for future work in order to achieve a practical application of EEG-based BCI systems toward imagined speech decoding.

show abstract

Section: Classification Techniques In Literaturementioning

confidence: 99%

A State-of-the-Art Review of EEG-Based Imagined Speech Decoding

Lopez-Bernal

Balderas

Ponce

et al. 2022

Front. Hum. Neurosci.

View full text Add to dashboard Cite

show abstract

“…was achieved using different computational models Butson et al [2007], Butenko et al [2020], Rubin and Terman [2004], Popovych and Tass [2019], Spiliotis et al [2022], Fleming et al [2020]. However, due to the strongly heterogeneous nature of the connection topology and intrinsic complexity (stochastic and nonlinear large scale neuron, multiple scales) Spiliotis and Siettos [2011], Siettos and Starke [2016, Deco et al 2008, 2013], Bassett and Bullmore [2017], Iliopoulos and Papasotiriou [2022], DBS outcome is far from trivial to predict.…”

Section: Introductionmentioning

confidence: 99%

Utilising activity patterns of a complex biophysical network model to optimise intra-striatal deep brain stimulation

Spiliotis,

Appali,

Fontes Gomes

et al. 2024

Preprint

View full text Add to dashboard Cite

In this study, we develop a large-scale biophysical network model for the isolated striatal body to optimise potential intrastriatal deep brain stimulation applied in, e.g. obsessive-compulsive disorder by using spatiotemporal patterns produced by the network. The model uses modified Hodgkin-Huxley models on small-world connectivity, while the spatial information, i.e. the positions of neurons, is obtained from a detailed human atlas. The model produces neuronal activity patterns that segregate healthy from pathological conditions. Three indices were used for the optimisation of stimulation protocols regarding stimulation frequency, amplitude and localisation: the mean activity of the entire network, the mean activity of the ventral striatal area (emerging as a defined community using modularity detection algorithms), and the frequency spectrum of the entire network activity. By minimising the deviation of the aforementioned indices from the normal state, we guide the optimisation of deep brain stimulation parameters regarding position, amplitude and frequency.

show abstract

“…was achieved using different computational models [34][35][36][37][38][39] . However, due to the strongly heterogeneous nature of the connection topology and intrinsic complexity (stochastic and nonlinear large scale neuron, multiple scales) [40][41][42][43][44][45] , DBS outcome is far from trivial to predict.…”

Section: Introductionmentioning

confidence: 99%

Utilising activity patterns of a complex biophysical network model to optimise intra-striatal deep brain stimulation

Spiliotis,

Appali,

Gomes

et al. 2024

Preprint

View full text Add to dashboard Cite

In this study, we develop a large-scale biophysical network model for the isolated striatal body to optimise potential intrastriatal deep brain stimulation applied in, e.g. obsessive-compulsive disorder by using spatiotemporal patterns produced by the network. The model uses modified Hodgkin-Huxley models on small-world connectivity, while the spatial information, i.e. the positions of neurons, is obtained from a detailed human atlas. The model produces neuronal activity patterns segregating healthy from pathological conditions. Three indices were used for the optimisation of stimulation protocols regarding stimulation frequency, amplitude and localisation: the mean activity of the entire network, the mean activity of the ventral striatal area (emerging as a defined community using modularity detection algorithms), and the frequency spectrum of the entire network activity. By minimising the deviation of the aforementioned indices from the normal state, we guide the optimisation of deep brain stimulation parameters regarding position, amplitude and frequency.

show abstract

Functional Complex Networks Based on Operational Architectonics: Application on EEG-based Brain–computer Interface for Imagined Speech

Cited by 6 publications

References 119 publications

A State-of-the-Art Review of EEG-Based Imagined Speech Decoding

A State-of-the-Art Review of EEG-Based Imagined Speech Decoding

Utilising activity patterns of a complex biophysical network model to optimise intra-striatal deep brain stimulation

Utilising activity patterns of a complex biophysical network model to optimise intra-striatal deep brain stimulation

Contact Info

Product

Resources

About