A Channel Selection Approach Based on Convolutional Neural Network for Multi-channel EEG Motor Imagery Decoding

Mzurikwao, Deogratias; Samuel, Oluwarotimi Williams; Asogbon, Mojisola Grace; Li, Xiangxin; Li, Guanglin; Yeo, Woon‐Hong; Efstratiou, Christos; Ang, Chee Siang

doi:10.1109/aike.2019.00042

Cited by 11 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 15 presents the summary of all classifiers used in this paper. The implementation details of the classifier used in this study are mentioned for SVM [ 1 , 3 , 42 , 46 , 51 , 54 , 56 , 59 , 60 , 62 , 70 , 76 , 79 ], LDA [ 26 , 52 , 55 , 58 , 76 , 77 , 78 , 79 ], CNN [ 21 , 24 , 27 , 32 ], Fisher’s LDA [ 53 , 80 ], FDA [ 23 , 43 ], and other’s classifier [ 22 , 25 , 43 , 47 , 57 , 61 , 64 , 73 , 74 , 79 ].…”

Section: Discussion and Guidelinesmentioning

confidence: 99%

“…These methods employ a combination of spatial filters, correlation-based, sequential-based, and binary harmony search-based EEG channel selection, and various classifiers (e.g., CNN [ 24 ], MLP-NN [ 22 ], SVM [ 19 ], linear discriminant analysis (LDA) [ 26 ] on one or more BCI competition datasets. A CNN classifier is employed to predict the new hierarchical structure accurately [ 24 , 27 ]. DNN is now widely regarded as the most advanced algorithm for the BCI competition dataset, particularly CNN [ 21 ].…”

Section: Introductionmentioning

confidence: 99%

“…What effect does the channel selection have on the accuracy? Given that the EEG channel selection community no later addresses questions, it is surprising how a few new papers have overlooked the possibility of resolving EEG channel selection problems with pure learning algorithms [ 21 , 24 , 27 , 32 ]. A recent empirical study tested various EEG channel selection techniques on several MI datasets, none of which were deep learning models [ 10 ].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

EEG Channel Selection Techniques in Motor Imagery Applications: A Review and New Perspectives

2022

View full text Add to dashboard Cite

Communication, neuro-prosthetics, and environmental control are just a few applications for disabled persons who use robots and manipulators that use brain-computer interface (BCI) systems. The brain’s motor imagery (MI) signal is an essential input for a brain-related task in BCI applications. Due to their noninvasive, portability, and cost-effectiveness, electroencephalography (EEG) signals are the most widely used input in BCI systems. The EEG data are often collected from more than 100 different locations in the brain; channel selection techniques are critical for selecting the optimum channels for a given application. However, when analyzing EEG data, the principal purpose of channel selection is to reduce computational complexity, improve classification accuracy by avoiding overfitting, and reduce setup time. Several channel selection assessment algorithms, both with and without classification-based methods, extracted appropriate channel subsets using defined criteria. Therefore, based on the exhaustive analysis of the EEG channel selection, this manuscript analyses several existing studies to reduce the number of noisy channels and improve system performance. We review several existing works to find the most promising MI-based EEG channel selection algorithms and associated classification methodologies on various datasets. Moreover, we focus on channel selection methods that choose fewer channels with great precision. Finally, our main finding is that a smaller channel set, typically 10–30% of total channels, provided excellent performance compared to other existing studies.

show abstract

Section: Discussion and Guidelinesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

EEG Channel Selection Techniques in Motor Imagery Applications: A Review and New Perspectives

2022

View full text Add to dashboard Cite

show abstract

“…Next, we explored the use of different window sizes to gauge if priming resulted in motor imagery patterns that could be more quickly discriminated by the available processing pipeline. Lastly, using a fixed window of 5 s duration (as per suggestions by Mzurikwao et al, 2019 ; Garcia-Moreno et al, 2020 ; Leon-Urbano and Ugarte, 2020 ), we explored the impact of different post-task-cue starting points on overall accuracy. As the task involved reaching for an orange, grabbing the orange, moving the orange to the center of the table and squeezing, this analysis could shed some light on what parts of the task may be more discriminative, thus resulting in shorter experimental protocols in the future.…”

Section: Methodsmentioning

confidence: 99%

Enhancing motor imagery detection efficacy using multisensory virtual reality priming

Gougeh

Falk

2023

Front. Neuroergonomics

View full text Add to dashboard Cite

Brain-computer interfaces (BCI) have been developed to allow users to communicate with the external world by translating brain activity into control signals. Motor imagery (MI) has been a popular paradigm in BCI control where the user imagines movements of e.g., their left and right limbs and classifiers are then trained to detect such intent directly from electroencephalography (EEG) signals. For some users, however, it is difficult to elicit patterns in the EEG signal that can be detected with existing features and classifiers. As such, new user control strategies and training paradigms have been highly sought-after to help improve motor imagery performance. Virtual reality (VR) has emerged as one potential tool where improvements in user engagement and level of immersion have shown to improve BCI accuracy. Motor priming in VR, in turn, has shown to further enhance BCI accuracy. In this pilot study, we take the first steps to explore if multisensory VR motor priming, where haptic and olfactory stimuli are present, can improve motor imagery detection efficacy in terms of both improved accuracy and faster detection. Experiments with 10 participants equipped with a biosensor-embedded VR headset, an off-the-shelf scent diffusion device, and a haptic glove with force feedback showed that significant improvements in motor imagery detection could be achieved. Increased activity in the six common spatial pattern filters used were also observed and peak accuracy could be achieved with analysis windows that were 2 s shorter. Combined, the results suggest that multisensory motor priming prior to motor imagery could improve detection efficacy.

show abstract

“…In [34], a MATLAB-based open-source toolbox that uses machine learning strategies based on neural networks to label and train models for detecting artefacts in invasive neuronal signals. The authors of [35] use CNN to select channels, after which multiple classes of motor imagery intentions are decoded. In [36], EEG decoding and visualization utilizing deep learning were exploited.…”

Section: Introductionmentioning

confidence: 99%

A Deep Neural Network-Based Spike Sorting With Improved Channel Selection and Artefact Removal

2023

View full text Add to dashboard Cite

In order to implement highly efficient brain-machine interface (BMI) systems, high-channel count sensing is often used to record extracellular action potentials. However, the extracellular recordings are typically severely contaminated by artefacts and various noise sources, rendering the separation of multiunit neural recordings an immensely challenging task. Removing artefact and noise from neural events can improve the spike sorting performance and classification accuracy. This paper presents a deep learning technique called deep spike detection (DSD) with a strong learning ability of high-dimensional vectors for neural channel selection and artefacts removal from the selected neural channel. The proposed method significantly improves spike detection compared to the conventional methods by sequentially diminishing the noise level and discarding the active artefacts in the recording channels. The simulated and experimental results show that there is considerably better performance when the extracellular raw recordings are cleaned prior to assigning individual spikes to the neurons that generated them. The DSD achieves an overall classification accuracy of 91.53% and outperformes Wave_clus by 3.38% on the simulated dataset with various noise levels and artefacts.INDEX TERMS Artefact removal, channel selection, convolutional neural network (CNN), deep earning, extracellular recordings, real-time sorting, spike sorting, .

show abstract

A Channel Selection Approach Based on Convolutional Neural Network for Multi-channel EEG Motor Imagery Decoding

Abstract: The version in the Kent Academic Repository may differ from the final published version. Users are advised to check http://kar.kent.ac.uk for the status of the paper. Users should always cite the published version of record.

Cited by 11 publications

References 27 publications

EEG Channel Selection Techniques in Motor Imagery Applications: A Review and New Perspectives

EEG Channel Selection Techniques in Motor Imagery Applications: A Review and New Perspectives

Enhancing motor imagery detection efficacy using multisensory virtual reality priming

A Deep Neural Network-Based Spike Sorting With Improved Channel Selection and Artefact Removal

Contact Info

Product

Resources

About