Effective BCI mental tasks classification with adaptively solved convolutional neural networks

Szajerman, Dominik; Smagur, Adrian; Opałka, Sławomir; Wojciechowski, Adam

doi:10.1109/isef.2017.8090699

Cited by 4 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of other types of mental tasks in BCI studies has received little attention in the literature. The papers that have studied non-motor imagery mental tasks along with the motor imagery tasks include [65][66][67][68][69][70][71][72][73][74][75][76][77][78][79][80][81][82][83][84]. Studies [85][86][87][88][89][90][91][92][93][94][95][96] have only considered non-motor imagery mental tasks.…”

Section: Introductionmentioning

confidence: 99%

“…The mental tasks considered in [82] are subtraction, navigation imagery, auditory recall, phone imagery, and motor imageries of the left and right hands. Hand movements and word imagination are the mental tasks used in [83]. Imagination of left and right hand movements, mental rotation of a 3D geometric figure, and mental subtraction of a two-digit number from a three-digit number are considered in [84].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Self-Paced Two-State Mental Task-Based Brain-Computer Interface with Few EEG Channels

Faradji¹,

Ward²,

Birch³

2020

New Frontiers in Brain - Computer Interfaces

View full text Add to dashboard Cite

A self-paced brain-computer interface (BCI) system that is activated by mental tasks is introduced. The BCI's output has two operational states, the active state and the inactive state, and is activated by designated mental tasks performed by the user. The BCI could be operated using several EEG brain electrodes (channels) or only few (i.e., five or seven channels) at a small loss in performance. The performance is evaluated on a dataset we have collected from four subjects while performing one of the four different mental tasks. The dataset contains the signals of 29 EEG electrodes distributed over the scalp. The five and seven highly discriminatory channels are selected using two different methods proposed in the paper. The signal processing structure of the interface is computationally simple. The features used are the scalar autoregressive coefficients. Classification is based on the quadratic discriminant analysis. Model selection and testing procedures are accomplished via cross-validation. The results are highly promising in terms of the rates of false and true positives. The false-positive rates reach zero, while the true-positive rates are sufficiently high, i.e., 54.60 and 59.98% for the 5-channel and 7-channel systems, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Self-Paced Two-State Mental Task-Based Brain-Computer Interface with Few EEG Channels

Faradji¹,

Ward²,

Birch³

2020

New Frontiers in Brain - Computer Interfaces

View full text Add to dashboard Cite

show abstract

“…Our previous work concentrated on developing a preliminary multi-channel architecture [ 13 ]. However, the previous solution suffered from a number of flaws.…”

Section: Introductionmentioning

confidence: 99%

Multi-Channel Convolutional Neural Networks Architecture Feeding for Effective EEG Mental Tasks Classification

Opałka

Stasiak

Szajerman

et al. 2018

Sensors

Self Cite

View full text Add to dashboard Cite

Mental tasks classification is increasingly recognized as a major challenge in the field of EEG signal processing and analysis. State-of-the-art approaches face the issue of spatially unstable structure of highly noised EEG signals. To address this problem, this paper presents a multi-channel convolutional neural network architecture with adaptively optimized parameters. Our solution outperforms alternative methods in terms of classification accuracy of mental tasks (imagination of hand movements and speech sounds generation) while providing high generalization capability (∼5%). Classification efficiency was obtained by using a frequency-domain multi-channel neural network feeding scheme by EEG signal frequency sub-bands analysis and architecture supporting feature mapping with two subsequent convolutional layers terminated with a fully connected layer. For dataset V from BCI Competition III, the method achieved an average classification accuracy level of nearly 70%, outperforming alternative methods. The solution presented applies a frequency domain for input data processed by a multi-channel architecture that isolates frequency sub-bands in time windows, which enables multi-class signal classification that is highly generalizable and more accurate (∼1.2%) than the existing solutions. Such an approach, combined with an appropriate learning strategy and parameters optimization, adapted to signal characteristics, outperforms reference single- or multi-channel networks, such as AlexNet, VGG-16 and Cecotti’s multi-channel NN. With the classification accuracy improvement of 1.2%, our solution is a clear advance as compared to the top three state-of-the-art methods, which achieved the result of no more than 0.3%.

show abstract

EEG-Based Mental Task Classification with Convolutional Neural Networks – Parallel vs 2D Data Representation

Stasiak

Opałka

Szajerman

et al. 2018

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Effective BCI mental tasks classification with adaptively solved convolutional neural networks

Cited by 4 publications

References 9 publications

A Self-Paced Two-State Mental Task-Based Brain-Computer Interface with Few EEG Channels

A Self-Paced Two-State Mental Task-Based Brain-Computer Interface with Few EEG Channels

Multi-Channel Convolutional Neural Networks Architecture Feeding for Effective EEG Mental Tasks Classification

EEG-Based Mental Task Classification with Convolutional Neural Networks – Parallel vs 2D Data Representation

Contact Info

Product

Resources

About