A comparison of subject-dependent and subject-independent channel selection strategies for single-trial P300 brain computer interfaces

Atum, Yanina; Pacheco, Marianela; Acevedo, Rubén; Tabernig, Carolina B.; Manresa, José Biurrun

doi:10.1007/s11517-019-02065-z

Cited by 7 publications

(4 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A brain-computer interface (BCI) is a communication channel between the brain and the outside world, and various types of thinking activities in the brain can be detected through EEG (Atum et al, 2019 ; Mebarkia and Reffad, 2019 ; Meziani et al, 2019 ). The application of BCI in rehabilitation training can help normal thinking patients with paralysis of the neuromuscular system interact with the outside world (Leeb et al, 2015 ; Rupp et al, 2015 ; Müller-Putz et al, 2017 ; Wang L. et al, 2019 ).…”

Section: Introductionmentioning

confidence: 99%

A Simplified CNN Classification Method for MI-EEG via the Electrode Pairs Signals

Lun

Chen

et al. 2020

Front. Hum. Neurosci.

View full text Add to dashboard Cite

A brain-computer interface (BCI) based on electroencephalography (EEG) can provide independent information exchange and control channels for the brain and the outside world. However, EEG signals come from multiple electrodes, the data of which can generate multiple features. How to select electrodes and features to improve classification performance has become an urgent problem to be solved. This paper proposes a deep convolutional neural network (CNN) structure with separated temporal and spatial filters, which selects the raw EEG signals of the electrode pairs over the motor cortex region as hybrid samples without any preprocessing or artificial feature extraction operations. In the proposed structure, a 5-layer CNN has been applied to learn EEG features, a 4-layer max pooling has been used to reduce dimensionality, and a fully-connected (FC) layer has been utilized for classification. Dropout and batch normalization are also employed to reduce the risk of overfitting. In the experiment, the 4 s EEG data of 10, 20, 60, and 100 subjects from the Physionet database are used as the data source, and the motor imaginations (MI) tasks are divided into four types: left fist, right fist, both fists, and both feet. The results indicate that the global averaged accuracy on group-level classification can reach 97.28%, the area under the receiver operating characteristic (ROC) curve stands out at 0.997, and the electrode pair with the highest accuracy on 10 subjects dataset is FC3-FC4, with 98.61%. The research results also show that this CNN classification method with minimal (2) electrode can obtain high accuracy, which is an advantage over other methods on the same database. This proposed approach provides a new idea for simplifying the design of BCI systems, and accelerates the process of clinical application.

show abstract

Section: Introductionmentioning

confidence: 99%

A Simplified CNN Classification Method for MI-EEG via the Electrode Pairs Signals

Lun

Chen

et al. 2020

Front. Hum. Neurosci.

View full text Add to dashboard Cite

show abstract

“…It can exchange information directly between the brain and the outside world without relying on conventional methods such as human muscle tissue or peripheral nerves [2]. Currently, for patients with paralysis, spinal cord injury, epilepsy, or brain nerve damage, the realization of an interaction with the external environment is a subject to be solved in the field of medicine and control [3][4][5][6][7]. In particular, the BCI system of the motor cortex has become a hot topic for domestic and foreign scholars [8].…”

Section: Introductionmentioning

confidence: 99%

A Combined Virtual Electrode-Based ESA and CNN Method for MI-EEG Signal Feature Extraction and Classification

Lun,

Zhang,

Zhu

et al. 2023

Sensors

View full text Add to dashboard Cite

A Brain–Computer Interface (BCI) is a medium for communication between the human brain and computers, which does not rely on other human neural tissues, but only decodes Electroencephalography (EEG) signals and converts them into commands to control external devices. Motor Imagery (MI) is an important BCI paradigm that generates a spontaneous EEG signal without external stimulation by imagining limb movements to strengthen the brain’s compensatory function, and it has a promising future in the field of computer-aided diagnosis and rehabilitation technology for brain diseases. However, there are a series of technical difficulties in the research of motor imagery-based brain–computer interface (MI-BCI) systems, such as: large individual differences in subjects and poor performance of the cross-subject classification model; a low signal-to-noise ratio of EEG signals and poor classification accuracy; and the poor online performance of the MI-BCI system. To address the above problems, this paper proposed a combined virtual electrode-based EEG Source Analysis (ESA) and Convolutional Neural Network (CNN) method for MI-EEG signal feature extraction and classification. The outcomes reveal that the online MI-BCI system developed based on this method can improve the decoding ability of multi-task MI-EEG after training, it can learn generalized features from multiple subjects in cross-subject experiments and has some adaptability to the individual differences of new subjects, and it can decode the EEG intent online and realize the brain control function of the intelligent cart, which provides a new idea for the research of an online MI-BCI system.

show abstract

“…Unsurprisingly, most existing literature focuses on subject-dependent channel selection strategies, where the specific subset of channels or the ranking of channels' importance is performed for each subject independently [2,[4][5][6][7][8][9] or at a group level, where the same set of channels is selected across an entire group of subjects, but the selection remains valid -and is evaluated -for new signals from the same group of subjects [6,[10][11][12]. Some attempts of cross-subject selection exist [7,13,14], but either performance is quite low or the number of selected channels high, or the methods tailored to specific EEG study paradigms. Despite the complexity of the task, it has become apparent that crucial medical applications call for automated EEG decoding via different Statistical and Machine Learning approaches [15], that in turn need strategies to reduce signal-to-noise ratio and improve classification accuracy of EEG recordings.…”

Section: Introductionmentioning

confidence: 99%

Learning Signal Representations for EEG Cross-Subject Channel Selection and Trial Classification

Massi

Ieva

2021

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)

View full text Add to dashboard Cite

EEG is a non-invasive powerful system that finds applications in several domains and research areas. Most EEG systems are multi-channel in nature, but multiple channels might include noisy and redundant information and increase computational times of automated EEG decoding algorithms. To reduce the signal-to-noise ratio, improve accuracy and reduce computational time, one may combine channel selection with feature extraction and dimensionality reduction. However, as EEG signals present high inter-subject variability, we introduce a novel algorithm for subject-independent channel selection through representation learning of EEG recordings. The algorithm exploits channel-specific 1D-CNNs as supervised feature extractors to maximize class separability and reduces a high dimensional multi-channel signal into a unique 1-Dimensional representation from which it selects the most relevant channels for classification. The algorithm can be transferred to new signals from new subjects and obtain novel highly informative trial vectors of controlled dimensionality to be fed to any kind of classifier.

show abstract

A comparison of subject-dependent and subject-independent channel selection strategies for single-trial P300 brain computer interfaces

Cited by 7 publications

References 45 publications

A Simplified CNN Classification Method for MI-EEG via the Electrode Pairs Signals

A Simplified CNN Classification Method for MI-EEG via the Electrode Pairs Signals

A Combined Virtual Electrode-Based ESA and CNN Method for MI-EEG Signal Feature Extraction and Classification

Learning Signal Representations for EEG Cross-Subject Channel Selection and Trial Classification

Contact Info

Product

Resources

About