Reconstruction of two-dimensional movement trajectories from selected magnetoencephalography cortical currents by combined sparse Bayesian methods

Toda, Akihiro; Imamizu, Hiroshi; Kawato, Mitsuo; Sato, Masa‐aki

doi:10.1016/j.neuroimage.2010.09.057

Cited by 68 publications

(51 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the number of possible voxel patterns should also be limited [66]. Second, functions used for decoders in DecNef are either pseudolinear [28] or linear [54] and monotonically increasing functions. In this case, reinforcement learning may become almost equal to supervised learning with stochastic gradient ascent [67].…”

Section: New Neurofeedback Techniques Resulting From the Integration mentioning

confidence: 99%

See 1 more Smart Citation

Advances in fMRI Real-Time Neurofeedback

Watanabe

Sasaki

Shibata

et al. 2017

Trends in Cognitive Sciences

Self Cite

232

211

View full text Add to dashboard Cite

Functional magnetic resonance imaging (fMRI) neurofeedback is a type of biofeedback in which real-time online fMRI signals are used to self-regulate brain function. Since its advent in 2003, significant progress has been made in fMRI neurofeedback techniques. Specifically, the use of implicit protocols, external rewards, multivariate analysis, and connectivity analysis have allowed neuroscientists to explore a possible causal involvement of modified brain activity in modified behavior. These techniques have also been integrated into groundbreaking new neurofeedback technologies, specifically decoded neurofeedback (DecNef) and functional-connectivity-based neurofeedback (FCNef). By modulating neural activity and behavior, DecNef and FCNef have substantially advanced both basic and clinical research.

show abstract

Section: New Neurofeedback Techniques Resulting From the Integration mentioning

confidence: 99%

“…A new trend of fMRI neurofeedback [20,29] is employment of multivariate analyses, or, decoded fMRI signals [24–28,54]. Conventional fMRI neurofeedback methods increase or decrease a one-dimensional amplitude of fMRI signals averaged across a region of interest (ROI) in the brain.…”

Section: Four Significant Aspects Of Progress Of Fmri Neurofeedbackmentioning

confidence: 99%

Advances in fMRI Real-Time Neurofeedback

Watanabe

Sasaki

Shibata

et al. 2017

Trends in Cognitive Sciences

Self Cite

232

211

View full text Add to dashboard Cite

show abstract

“…However, the literature about macroscale brain sources containing movement trajectory/direction information is not always consistent and shows also involvements of other brain regions. Toda et al [26] showed the involvement of primary sensorimotor, higher motor and parietal regions when decoding 2D finger trajectories from MEG. Lv et al [31] reported larger weights in motor, posterior parietal and occipital areas when decoding hand movement velocities during a drawing task.…”

Section: Discussionmentioning

confidence: 99%

“…The prediction of movement trajectories in a pentagon copying task with a 2D joystick has been reported by Georgopoulos et al in [24], and Bradberry et al [25] decoded hand velocities in a center-out drawing task. Toda et al [26] reconstructed two-dimensional index fingertip trajectories during pointing movements. Also, 3D velocity decoding of movements in a center-out task has already been reported by Yeom et al [27].…”

Section: Introductionmentioning

confidence: 99%

Using a Noninvasive Decoding Method to Classify Rhythmic Movement Imaginations of the Arm in Two Planes

Ofner

Müller-Putz

2015

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

A brain-computer interface (BCI) can help to overcome movement deficits in persons with spinal-cord injury. Ideally, such a BCI detects detailed movement imaginations, i.e., trajectories, and transforms them into a control signal for a neuroprosthesis or a robotic arm restoring movement. Robotic arms have already been controlled successfully by means of invasive recording techniques, and executed movements have been reconstructed using noninvasive decoding techniques. However, it is unclear if detailed imagined movements can be decoded noninvasively using electroencephalography (EEG). We made progress toward imagined movement decoding and successfully classified horizontal and vertical imagined rhythmic movements of the right arm in healthy subjects using EEG. Notably, we used an experimental design which avoided muscle and eye movements to prevent classification results being affected. To classify imagined movements of the same limb, we decoded the movement trajectories and correlated them with assumed movement trajectories (horizontal and vertical). We then assigned the decoded movements to the assumed movements with the higher correlation. To train the decoder, we applied partial least squares, which allowed us to interpret the classifier weights although channels were highly correlated. To conclude, we showed the classification of imagined movements of one limb in two different movement planes in seven out of nine subjects. Furthermore, we found a strong involvement of the supplementary motor area. Finally, as our classifier was based on the decoding approach, we indirectly showed the decoding of imagined movements.

show abstract

“…From a methodological perspective, future studies will focus on improving non-invasive BCI approaches by improving the decoding algorithms and classification methods for MEG and EEG data [89,90] and by applying various spatial filtering techniques and inverse-solution approaches that allow for BCI investigations in MEG or EEG source space [91][92][93][94][95][96][97][98]. Finally, freely available BCI platforms will continue to play a pivotal role in the community's effort for joint developments and the exchange of methodological and neuroscience expertise, for example, through open software projects such as OpenViBE [99], FieldTrip (http://fieldtrip.fcdonders.nl) or BCI 2000 [100].…”

Section: Future Trendsmentioning

confidence: 99%