Fast attainment of computer cursor control with noninvasively acquired brain signals

Bradberry, Trent J.; Gentili, Rodolphe J.; Contreras-Vidal, José L.

doi:10.1088/1741-2560/8/3/036010

Cited by 79 publications

(93 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To assess a potential contribution of the movement of the eyes to decoding, the decoding process was also carried out by adding the standardized vertical electrooculogram (VEOG) activity to the optimal set of electrodes used for decoding (Bradberry et al 2011). The r values and the regression weights were calculated in this new condition.…”

Section: Methodsmentioning

confidence: 99%

Neural decoding of treadmill walking from noninvasive electroencephalographic signals

Presacco

Goodman²,

Forrester

et al. 2011

Journal of Neurophysiology

191

199

View full text Add to dashboard Cite

Here we show that the linear and angular kinematics of the ankle, knee, and hip joints during both normal and precision (attentive) human treadmill walking can be inferred from noninvasive scalp electroencephalography (EEG) with decoding accuracies comparable to those from neural decoders based on multiple single-unit activities (SUAs) recorded in nonhuman primates. Six healthy adults were recorded. Participants were asked to walk on a treadmill at their self-selected comfortable speed while receiving visual feedback of their lower limbs (i.e., precision walking), to repeatedly avoid stepping on a strip drawn on the treadmill belt. Angular and linear kinematics of the left and right hip, knee, and ankle joints and EEG were recorded, and neural decoders were designed and optimized with cross-validation procedures. Of note, the optimal set of electrodes of these decoders were also used to accurately infer gait trajectories in a normal walking task that did not require subjects to control and monitor their foot placement. Our results indicate a high involvement of a fronto-posterior cortical network in the control of both precision and normal walking and suggest that EEG signals can be used to study in real time the cortical dynamics of walking and to develop brain-machine interfaces aimed at restoring human gait function. brain computer interface; brain-machine interface; electroencephalography LITTLE IS KNOWN about the organization, neural network mechanisms, and computations underlying the control of walking in humans (Choi and Bastian 2007). Although central pattern generators for locomotion are important in the control of walking, supraspinal networks, including the brain stem, cerebellum, and cortex, must be critical, as demonstrated by the changing motor and cognitive (i.e., spatial attention) demands imposed by bipedal walking in unknown or cluttered dynamic environments (Choi and Bastian 2007;Grillner et al. 2008;Nielsen 2003;Rossignol et al. 2007). Neuroimaging studies show that rhythmic foot or leg movements recruit primary motor cortex (Christensen et al. 2001;Dobkin et al. 2004;Heuninckx et al. 2005Heuninckx et al. , 2008Luft et al. 2002;Sahyoun et al. 2004), whereas electrophysiological investigations demonstrate electrocortical potentials related to lower limb movements (Wieser et al. 2010), as well as a greater involvement of human cortex during steady-speed locomotion than previously thought (Gwin et al. , 2011. In this regard, studies using functional near-infrared spectroscopy (fNIRS) show involvement of frontal, premotor, and supplementary motor areas during walking (Harada et al. 2009;Miyai et al. 2001;Suzuki et al. 2004Suzuki et al. , 2008. That primary sensorimotor cortices carry information about bipedal locomotion has been directly proven by the work of Nicolelis and colleagues (Fitzsimmons et al. 2009), who demonstrated that chronic recordings from ensembles of cortical neurons in primary motor (M1) and primary somatosensory (S1) cortices can be used to predict the kinematics of bipedal wa...

show abstract

Section: Methodsmentioning

confidence: 99%

Neural decoding of treadmill walking from noninvasive electroencephalographic signals

Presacco

Goodman²,

Forrester

et al. 2011

Journal of Neurophysiology

191

199

View full text Add to dashboard Cite

show abstract

“…Many BMI training paradigms involve an initial period of parameter tuning. In this period, parameters of a neural signal model are adjusted to relate observed neural signals with overt movements (Santhanam, Ryu, Yu, Afshar, & Shenoy, 2006;Serruya, Hatsopoulos, Paninski, Fellows, & Donoghue, 2002), or instructed motor imagery (Bradberry, Gentili, & Contreras-Vidal, 2011;Hochberg et al, 2006;Kim, Simeral, Hochberg, Donoghue, & Black, 2008). During this initial period, the user is not directly operating the BMI.…”

Section: Definition and Categorization Of Naive Adaptive Brain-machinementioning

confidence: 99%

“…These stages can be reversed. The design philosophy underlying lockstep estimation, called certainty equivalence, is the pervasive approach in BMI algorithm design, including all methods based on training data that use overt movements (Santhanam et al, 2006;Serruya et al, 2002), or instructed motor imagery (Bradberry et al, 2011;Hochberg et al, 2006;Kim et al, 2008), as well as previously developed naive adaptive control methods Gage et al, 2005;Orsborn et al, 2012). Certainty equivalence means that when parameters are estimated, the current estimate of intent is assumed to be the true intent (i.e., equivalent to being known with certainty), and vice versa (Bertsekas, 2005).…”

Section: Joint Estimation Versus Lockstep Estimationmentioning

confidence: 99%

Dynamic Analysis of Naive Adaptive Brain-Machine Interfaces

Kowalski

Srinivasan

2013

Neural Computation

View full text Add to dashboard Cite

The closed-loop operation of brain-machine interfaces (BMI) provides a context to discover foundational principles behind human-computer interaction, with emerging clinical applications to stroke, neuromuscular diseases, and trauma. In the canonical BMI, a user controls a prosthetic limb through neural signals that are recorded by electrodes and processed by a decoder into limb movements. In laboratory demonstrations with able-bodied test subjects, parameters of the decoder are commonly tuned using training data that include neural signals and corresponding overt arm movements. In the application of BMI to paralysis or amputation, arm movements are not feasible, and imagined movements create weaker, partially unrelated patterns of neural activity. BMI training must begin naive, without access to these prototypical methods for parameter initialization used in most laboratory BMI demonstrations.Naive adaptive BMI refer to a class of methods recently introduced to address this problem. We first identify the basic elements of existing approaches based on adaptive filtering and define a decoder, ReFIT-PPF to represent these existing approaches. We then present Joint RSE, a novel approach that logically extends prior approaches. Using recently developed human-and synthetic-subjects closed-loop BMI simulation platforms, we show that Joint RSE significantly outperforms ReFIT-PPF and nonadaptive (static) decoders. Control experiments demonstrate the critical role of jointly estimating neural parameters and user intent. In addition, we show that nonzero sensorimotor delay in the user significantly degrades ReFIT-PPF but not Joint RSE, owing to differences in the prior on intended velocity. Paradoxically, substantial differences in the nature of sensory feedback between these methods do not contribute to differences in performance between Joint RSE and ReFIT-PPF. Instead, BMI performance improvement is driven by machine learning, which outpaces rates of human learning in the human-subjects simulation platform. In this regime, nuances of error-related feedback to the human user are less relevant to rapid BMI mastery.

show abstract

“…Thus, the next step is to decode imagined movements. Bradberry et al [12] showed already the control of a computer cursor with imagined movements, but the conclusiveness of the results is questionable [13].…”

Section: Introductionmentioning

confidence: 99%

EEG-Based Classification of Imagined Arm Trajectories

Ofner

Müller-Putz

2014

Biosystems &Amp; Biorobotics

View full text Add to dashboard Cite

Abstract. A brain-computer interface (BCI) in combination with a neuroprosthesis can be used to restore movement functionalities in paralyzed persons. The BCI detects the movement imagination (MI) and the neuroprosthesis transforms it into a real movement. Today's BCIs can detect the process of MI, but not the actual imagined trajectories of, e.g., the arm. Users' control of a BCI would become more intuitive and natural when the detailed MI, i.e., trajectories, are detected. This is called movement decoding. We made a first attempt to decode MIs, and notably, we did not provoke task depended artefacts like eye movements in our paradigm design. However, that made it necessary to restrict the MIs to movements in two orthogonal planes. We classified the movement plane using a decoding method. For this purpose, we decoded the imagined trajectory and correlated it with two assumed movement trajectories, and then assigned the MI to the assumed movement with the higher correlation. That way, we reached a significant classification accuracy in 7 out of 9 subjects, and showed indirectly the decoding of imagined movements.

show abstract

Fast attainment of computer cursor control with noninvasively acquired brain signals

Cited by 79 publications

References 22 publications

Neural decoding of treadmill walking from noninvasive electroencephalographic signals

Neural decoding of treadmill walking from noninvasive electroencephalographic signals

Dynamic Analysis of Naive Adaptive Brain-Machine Interfaces

EEG-Based Classification of Imagined Arm Trajectories

Contact Info

Product

Resources

About