Brain-machine interfaces: assistive, thought-controlled devices

Niemeyer, James E.

doi:10.1038/laban.1115

Cited by 3 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Brain-machine interfaces (BMI) aim to translate brain signals into commands that allow the control of machines or computer interfaces (Niemeyer, 2016 ). One of BMI's best-known paradigms is motor imagery, which refers to the act of imagining a movement without executing it (Mulder, 2007 ).…”

Section: Introductionmentioning

confidence: 99%

Empirical comparison of deep learning methods for EEG decoding

Oliveira¹,

Rodrigues²

2023

Front. Neurosci.

View full text Add to dashboard Cite

Electroencephalography (EEG) is a technique that can be used in non-invasive brain-machine interface (BMI) systems to register brain electrical activity. The EEG signals are non-linear and non-stationary, making the decoding procedure a complex task. Deep learning techniques have been successfully applied in several research fields, often improving the results compared with traditional approaches. Therefore, it is believed that these techniques can also improve the process of decoding brain signals in BMI systems. In this work, we present the implementation of two deep learning-based decoders and we compared the results with other state of art deep learning methods. The first decoder uses long short-term memory (LSTM) recurrent neural network and the second, entitled EEGNet-LSTM, combines a well-known neural decoder based on convolutional neural networks, called EEGNet, with some LSTM layers. The decoders have been tested using data set 2a from BCI Competition IV, and the results showed that the EEGNet-LSTM decoder has been approximately 23% better than the competition-winning decoder. A Wilcoxon t-test showed a significant difference between the two decoders (Z = 2.524, p = 0.012). The LSTM-based decoder has been approximately 9% higher than the best decoder from the same competition. However, there was no significant difference (Z = 1.540, p = 0.123). In order to verify the replication of the EEGNet-LSTM decoder on another data, we performed a test with PhysioNet's Physiobank EEG Motor Movement/Imagery dataset. The EEGNet-LSTM presented a higher performance (0.85 accuracy) than the EEGNet (0.82 accuracy). The results of this work can be important for the development of new research, as well as EEG-based BMI systems, which can benefit from the high precision of neural decoders.

show abstract

Section: Introductionmentioning

confidence: 99%

Empirical comparison of deep learning methods for EEG decoding

Oliveira¹,

Rodrigues²

2023

Front. Neurosci.

View full text Add to dashboard Cite

show abstract

“…Brain-computer interfaces (BCIs) can also be used to promote neuroplasticity. Many BCIs in research are unidirectional, which means that they either send information from the brain via sensors to an external device (e.g., assistive devices or FES devices) (Crea et al, 2018 ; Cheng et al, 2020 ; Schwarz et al, 2020 ) or from the external device (e.g., sensor-based devices such as a Linderman et al's EMG glove) (Linderman and Rupasov, 2012 ; Bouton et al, 2016 ) to the brain through direct brain stimulation (Lobel and Lee, 2014 ; Niemeyer, 2016 ; Semprini et al, 2016 ). Research over the past decade has focused on the latter approach to provide proprioceptive feedback.…”

Section: Introductionmentioning

confidence: 99%

Hand-worn devices for assessment and rehabilitation of motor function and their potential use in BCI protocols: a review

Bates

Sunderam

2023

Front. Hum. Neurosci.

View full text Add to dashboard Cite

IntroductionVarious neurological conditions can impair hand function. Affected individuals cannot fully participate in activities of daily living due to the lack of fine motor control. Neurorehabilitation emphasizes repetitive movement and subjective clinical assessments that require clinical experience to administer.MethodsHere, we perform a review of literature focused on the use of hand-worn devices for rehabilitation and assessment of hand function. We paid particular attention to protocols that involve brain-computer interfaces (BCIs) since BCIs are gaining ground as a means for detecting volitional signals as the basis for interactive motor training protocols to augment recovery. All devices reviewed either monitor, assist, stimulate, or support hand and finger movement.ResultsA majority of studies reviewed here test or validate devices through clinical trials, especially for stroke. Even though sensor gloves are the most commonly employed type of device in this domain, they have certain limitations. Many such gloves use bend or inertial sensors to monitor the movement of individual digits, but few monitor both movement and applied pressure. The use of such devices in BCI protocols is also uncommon.DiscussionWe conclude that hand-worn devices that monitor both flexion and grip will benefit both clinical diagnostic assessment of function during treatment and closed-loop BCI protocols aimed at rehabilitation.

show abstract

Artificial Intelligence, New Human Technologies, and the Future of Mankind

Benedikter¹

2023

Challenge

View full text Add to dashboard Cite

Brain-machine interfaces: assistive, thought-controlled devices

Cited by 3 publications

References 8 publications

Empirical comparison of deep learning methods for EEG decoding

Empirical comparison of deep learning methods for EEG decoding

Hand-worn devices for assessment and rehabilitation of motor function and their potential use in BCI protocols: a review

Artificial Intelligence, New Human Technologies, and the Future of Mankind

Contact Info

Product

Resources

About