State and trajectory decoding of upper extremity movements from electrocorticogram

Wang, Po T.; Puttock, Eric J.; King, Christine; Schombs, Andrew; Lin, Jack J.; Sazgar, Mona; Hsu, Frank P.K.; Shaw, Susan; Millett, David; Liu, Charles Y.; Chui, Luis A.; An, Hongyu; Nenadic, Zoran

doi:10.1109/ner.2013.6696097

Cited by 11 publications

(14 citation statements)

References 20 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A first approach to integrate NC support into biomimetic kinematic decoders, namely post-processing, has been explored for both SUA/MUA (Aggarwal et al, 2013 ; Velliste et al, 2014 ) and ECoG signals (e.g., Wang et al, 2013b ) decoding. This consists in overwriting the output of the single kinematic model with null-velocity (neutral) estimates when a NC state is detected by a discrete NC/IC decoder.…”

Section: Discussionmentioning

confidence: 99%

“…It has since then provided users with MUA/SUA-based control over prostheses (Hochberg et al, 2012 ). It has additionally been applied for trajectory decoding from ECoG signals in online and offline studies (Pistohl et al, 2008 ; Kellis et al, 2012 ; Marathe and Taylor, 2013 ; Wang et al, 2013b ). KF applies to linear Gaussian state-space models (Bishop, 2006 ); that is, to state-space models with linear emission and transition models associated with Gaussian noises.…”

Section: Data-driven Decodersmentioning

confidence: 99%

“…Up to 7DoF have been reconstructed in offline feasibility studies led on primate (Chao et al, 2010 ; Shimoda et al, 2012 ) and human subjects (Schalk et al, 2007 ; Nakanishi et al, 2013 ). Meanwhile, Kalman filtering has permitted to reconstruct 2D kinematic parameters from ECoG signals (Pistohl et al, 2008 ; Kellis et al, 2012 ; Marathe and Taylor, 2013 ; Wang et al, 2013b ). In a comparative study performed on ECoG data (Eliseyev and Aksenova, 2016 ), static models outperformed Kalman filtering for the reconstruction of kinematic parameters from high-dimensional time-space-frequency feature representations.…”

Section: Data-driven Decodersmentioning

confidence: 99%

See 2 more Smart Citations

Data-Driven Transducer Design and Identification for Internally-Paced Motor Brain Computer Interfaces: A Review

Schaeffer

Aksenova

2018

Front. Neurosci.

View full text Add to dashboard Cite

Brain-Computer Interfaces (BCIs) are systems that establish a direct communication pathway between the users' brain activity and external effectors. They offer the potential to improve the quality of life of motor-impaired patients. Motor BCIs aim to permit severely motor-impaired users to regain limb mobility by controlling orthoses or prostheses. In particular, motor BCI systems benefit patients if the decoded actions reflect the users' intentions with an accuracy that enables them to efficiently interact with their environment. One of the main challenges of BCI systems is to adapt the BCI's signal translation blocks to the user to reach a high decoding accuracy. This paper will review the literature of data-driven and user-specific transducer design and identification approaches and it focuses on internally-paced motor BCIs. In particular, continuous kinematic biomimetic and mental-task decoders are reviewed. Furthermore, static and dynamic decoding approaches, linear and non-linear decoding, offline and real-time identification algorithms are considered. The current progress and challenges related to the design of clinical-compatible motor BCI transducers are additionally discussed.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Data-driven Decodersmentioning

confidence: 99%

Section: Data-driven Decodersmentioning

confidence: 99%

See 1 more Smart Citation

Data-Driven Transducer Design and Identification for Internally-Paced Motor Brain Computer Interfaces: A Review

Schaeffer

Aksenova

2018

Front. Neurosci.

View full text Add to dashboard Cite

show abstract

“…Efforts to decode neural activity are typically accomplished by training algorithms on tightly controlled experimental data with repeated trials. Much progress has been made to decode arm trajectories (Wang et al, 2012 ; Nakanishi et al, 2013 ; Wang et al, 2013a ) and finger movements (Miller et al, 2009 ; Wang et al, 2010 ), to control robotic arms (Yanagisawa et al, 2011 ; Fifer et al, 2014 ; McMullen et al, 2014 ), and to construct ECoG BCIs (Leuthardt et al, 2006 ; Schalk et al, 2008 ; Miller et al, 2010 ; Vansteensel et al, 2010 ; Leuthardt et al, 2011 ; Wang et al, 2013b ). Speech detection and decoding from ECoG has been studied at the level of voice activity (Kanas et al, 2014b ), phoneme (Blakely et al, 2008 ; Leuthardt et al, 2011 ; Kanas et al, 2014a ; Mugler et al, 2014 ), vowels and consonants (Pei et al, 2011 ), whole words (Towle et al, 2008 ; Kellis et al, 2010 ), and sentences (Zhang et al, 2012 ).…”

Section: Background and Related Workmentioning

confidence: 99%

Unsupervised Decoding of Long-Term, Naturalistic Human Neural Recordings with Automated Video and Audio Annotations

Wang

Olson

Ojemann

et al. 2016

Front. Hum. Neurosci.

View full text Add to dashboard Cite

Fully automated decoding of human activities and intentions from direct neural recordings is a tantalizing challenge in brain-computer interfacing. Implementing Brain Computer Interfaces (BCIs) outside carefully controlled experiments in laboratory settings requires adaptive and scalable strategies with minimal supervision. Here we describe an unsupervised approach to decoding neural states from naturalistic human brain recordings. We analyzed continuous, long-term electrocorticography (ECoG) data recorded over many days from the brain of subjects in a hospital room, with simultaneous audio and video recordings. We discovered coherent clusters in high-dimensional ECoG recordings using hierarchical clustering and automatically annotated them using speech and movement labels extracted from audio and video. To our knowledge, this represents the first time techniques from computer vision and speech processing have been used for natural ECoG decoding. Interpretable behaviors were decoded from ECoG data, including moving, speaking and resting; the results were assessed by comparison with manual annotation. Discovered clusters were projected back onto the brain revealing features consistent with known functional areas, opening the door to automated functional brain mapping in natural settings.

show abstract

“…Several studies have shown that arm and finger trajectories [1], [2], [3], [4], [5], [6], [7] can be decoded from ECoG signals. However, the performance of these decoders has been modest.…”

Section: Introductionmentioning

confidence: 99%

Electrocorticogram encoding of upper extremity movement duration

Wang

King

McCrimmon

et al. 2014

2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society

Self Cite

View full text Add to dashboard Cite

Electrocorticogram (ECoG) is a promising long-term signal acquisition platform for brain-computer interface (BCI) systems such as upper extremity prostheses. Several studies have demonstrated decoding of arm and finger trajectories from ECoG high-gamma band (80-160 Hz) signals. In this study, we systematically vary the velocity of three elementary movement types (pincer grasp, elbow and shoulder flexion/extension) to test whether the high-gamma band encodes for the entirety of the movements, or merely the movement onset. To this end, linear regression models were created for the durations and amplitudes of high-gamma power bursts and velocity deflections. One subject with 8×8 high-density ECoG grid (4 mm center-to-center electrode spacing) participated in the experiment. The results of the regression models indicated that the power burst durations varied directly with the movement durations (e.g. R(2)=0.71 and slope=1.0 s/s for elbow). The persistence of power bursts for the duration of the movement suggests that the primary motor cortex (M1) is likely active for the entire duration of a movement, instead of providing a marker for the movement onset. On the other hand, the amplitudes were less co-varied. Furthermore, the electrodes of maximum R(2) conformed to somatotopic arrangement of the brain. Also, electrodes responsible for flexion and extension movements could be resolved on the high-density grid. In summary, these findings suggest that M1 may be directly responsible for activating the individual muscle motor units, and future BCI may be able to utilize them for better control of prostheses.

show abstract

State and trajectory decoding of upper extremity movements from electrocorticogram

Cited by 11 publications

References 20 publications

Data-Driven Transducer Design and Identification for Internally-Paced Motor Brain Computer Interfaces: A Review

Data-Driven Transducer Design and Identification for Internally-Paced Motor Brain Computer Interfaces: A Review

Unsupervised Decoding of Long-Term, Naturalistic Human Neural Recordings with Automated Video and Audio Annotations

Electrocorticogram encoding of upper extremity movement duration

Contact Info

Product

Resources

About