Brain Computer Interfaces, a Review

Nicolás-Alonso, Luis F.; Gómez-Gil, Jaime

doi:10.3390/s120201211

Cited by 1,640 publications

(1,089 citation statements)

References 316 publications

Supporting

Mentioning

962

Contrasting

Unclassified

Order By: Relevance

“…LDA computes several hyperplanes (k-class problem, k > 2) which linearly separate data into the different classes [26]. In order to prevent errors due to bad estimation of covariance matrices (bias), a shrinkage regularization was implemented [27].…”

Section: Classification Stagementioning

confidence: 99%

Optimization of EMG-based hand gesture recognition: Supervised vs. unsupervised data preprocessing on healthy subjects and transradial amputees

Riillo

Quitadamo

Cavrini

et al. 2014

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

a b s t r a c tWe propose a methodological study for the optimization of surface EMG (sEMG)-based hand gesture classification, effective to implement a human-computer interaction device for both healthy subjects and transradial amputees. The widely commonly used unsupervised Principal Component Analysis (PCA) approach was compared to the promising supervised common spatial pattern (CSP) methodology to identify the best classification strategy and the related tuning parameters. A low density array of sEMG sensors was built to record the muscular activity of the forearm and classify five different hand gestures. Twenty healthy subjects were recruited to compute optimized parameters for ("within" analysis) and to compare between ("between" analysis) the two strategies. The system was also tested on a transradial amputee subject, in order to assess the robustness of the optimization in recognizing disabled users' gestures.Results show that RMS-WA/ANN is the best feature vector/classifier pair for the PCA approach (accuracy 88.81 ± 6.58%), whereas M-RMS-WA/ANN is the best pair for the CSP methodology (accuracy of 89.35 ± 6.16%). Statistical analysis on classification results shows no significant differences between the two strategies. Moreover we found out that the optimization computed for healthy subjects was proven to be sufficiently robust to be used on the amputee subject. This motivates further investigation of the proposed methodology on a larger sample of amputees. Our results are useful to boost EMG-based hand gesture recognition and constitute a step toward the definition of an efficient EMG-controlled system for amputees.

show abstract

Section: Classification Stagementioning

confidence: 99%

Optimization of EMG-based hand gesture recognition: Supervised vs. unsupervised data preprocessing on healthy subjects and transradial amputees

Riillo

Quitadamo

Cavrini

et al. 2014

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

show abstract

“…Many practical noninvasive BMIs have been developed, such as BMIs for communication, prosthetic control and wheelchair navigation [65][66][67][68]. Remarkably, severely impaired 'locked in' patients were able to communicate with the outside world using EEG based spelling devices [48,49].…”

Section: Noninvasive Bmismentioning

confidence: 99%

Brain-machine interfaces: an overview

Lebedev¹

2014

Translational Neuroscience

View full text Add to dashboard Cite

Brain-machine interfaces (BMIs) hold promise to treat neurological disabilities by linking intact brain circuitry to assistive devices, such as limb prostheses, wheelchairs, artificial sensors, and computers. BMIs have experienced very rapid development in recent years, facilitated by advances in neural recordings, computer technologies and robots. BMIs are commonly classified into three types: sensory, motor and bidirectional, which subserve motor, sensory and sensorimotor functions, respectively. Additionally, cognitive BMIs have emerged in the domain of higher brain functions. BMIs are also classified as noninvasive or invasive according to the degree of their interference with the biological tissue. Although noninvasive BMIs are safe and easy to implement, their information bandwidth is limited. Invasive BMIs hold promise to improve the bandwidth by utilizing multichannel recordings from ensembles of brain neurons. BMIs have a broad range of clinical goals, as well as the goal to enhance normal brain functions.

show abstract

“…Potential applications include: communication with totally locked-in patients, training of sustained attention, and ultra-secure password input. : human-computer interface, brain-computer interface, pupillometry, covert visual attention Manuscript in preparation [v1.1.4; Wed Sep 9 13:22:41 2015; There are many types of BCIs (reviewed in Donoghue, 2008;Nicolas-Alonso & Gomez-Gil, 2012) , which differ in the neural signal that they use (e.g., neural spikes or electroencephalography [EEG]), the way that neural activity is processed (e.g., through a classifier or by measuring overall activity in specific brain areas), and the actions that they perform (e.g. controlling a robotic limb, or writing text).…”

mentioning

confidence: 99%

The mind-writing pupil: A human-computer interface based on decoding of covert attention through pupillometry

Mathôt

Melmi

Linden

et al. 2015

Preprint

View full text Add to dashboard Cite

We present a new human-computer interface that is based on decoding of attention through pupillometry. Our method builds on the recent finding that covert visual attention affects the pupillary light response: Your pupil constricts when you covertly (without looking at it) attend to a bright, compared to a dark, stimulus. In our method, participants covertly attend to one of several letters with oscillating brightness. Pupil size reflects the brightness of the selected letter, which allows us-with high accuracy and in real time-to determine which letter the participant intends to select. The performance of our method is comparable to the best covert-attention brain-computer interfaces to date, and has several advantages: no movement other than pupil-size change is required; no physical contact is required (i.e. no electrodes); it is easy to use; and it is reliable. Potential applications include: communication with totally locked-in patients, training of sustained attention, and ultra-secure password input. : human-computer interface, brain-computer interface, pupillometry, covert visual attention Manuscript in preparation [v1.1.4; Wed Sep 9 13:22:41 2015; There are many types of BCIs (reviewed in Donoghue, 2008;Nicolas-Alonso & Gomez-Gil, 2012) , which differ in the neural signal that they use (e.g., neural spikes or electroencephalography [EEG]), the way that neural activity is processed (e.g., through a classifier or by measuring overall activity in specific brain areas), and the actions that they perform (e.g. controlling a robotic limb, or writing text). Here we present a new method, which uses pupil size, rather than brain activity, as the controlling signal. Our method is related to two existing methods: the P300 speller (Farwell & Donchin, 1988), which is functionally similar to our method but relies on a different controlling signal; and a recent pupillometry-based method (Stoll et al., 2013) , which is functionally different from our method but relies on the same controlling signal. P300 spellers are among the most successful BCIs (reviewed in Fazel-Rezai et al., 2012) . They exploit the fact that rare visual stimuli elicit positive deflections in the EEG signal about 300 ms after their appearance. This event-related-potential (ERP) component is called the P300, and is largest for stimuli that are overtly (while looking at them) or covertly (without looking at them) attended (e.g., Treder & Blankertz, 2010). In a classic P300 speller, the participant sees a grid of letters. One letter, or sometimes one full column or row of letters, is highlighted at a time. A P300 is elicited each time that a letter is highlighted. The participant selects a letter by attending to it, usually by looking at it directly (i.e. overt attention), which leads to an increased P300 when that letter is highlighted. In its simplest form, the letter that, when highlighted, elicits the highest P300 is selected; however, most P300 spellers now use sophisticated classification techniques, and pool information from mult...

show abstract

Brain Computer Interfaces, a Review

Cited by 1,640 publications

References 316 publications

Optimization of EMG-based hand gesture recognition: Supervised vs. unsupervised data preprocessing on healthy subjects and transradial amputees

Optimization of EMG-based hand gesture recognition: Supervised vs. unsupervised data preprocessing on healthy subjects and transradial amputees

Brain-machine interfaces: an overview

The mind-writing pupil: A human-computer interface based on decoding of covert attention through pupillometry

Contact Info

Product

Resources

About