Xuan Ma
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Xuan Ma has a total of 96 co-authors. Here are the top co-authors by number of shared publications:
- Lee E. Miller
Department of Biomedical Engineering, Northwestern University
12 shared publications - Fabio Rizzoglio
Department of Neuroscience, Northwestern University, Chicago, IL, USA
7 shared publications - Ann Kennedy
Department of Neuroscience, The Scripps Research Institute, La Jolla, USA
3 shared publications - Brianna M. Karpowicz
Wallace H. Coulter Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA, USA
3 shared publications - Chethan Pandarinath
Wallace H. Coulter Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, USA
3 shared publications - Kevin L. Bodkin
Northwestern University
3 shared publications
Latest Publications
- Open Access
A framework for quantifying the mechanics of dexterous grasp
A hallmark of primate behavior is the exceptional ability to dexterously grasp and manipulate objects, yet the investigation of the neural mechanisms that support manual dexterity has been hindered by technical challenges. Optical hand tracking is complicated by frequent occlusions, and contact forces are hard to measure with sufficient precision. Furthermore, while monitoring the kinematics during reaching phase, and the contact forces during object manipulation phase is difficult, joint torques are impossible to measure directly. While challenging, the ability to estimate joint torques in the complex primate hand could provide an invaluable continuous mechanical description spanning both phases. With this in mind, we have developed an experimental apparatus and data processing pipeline for quantifying these variables describing prehension. The apparatus presented objects of various sizes and orientations throughout the workspace, evoking different grasping strategies. Object surfaces were instrumented with thousands of pressure-sensitive elements, enabling high-resolution measurement of distributed contact forces. Simultaneously, eight high-speed cameras were used to reconstruct hand and arm movements with markerless tracking, triangulating 3D landmarks, and mapping them onto a musculoskeletal model, enabling estimation of time-varying joint angles. This posture quantification allowed contact forces to be automatically assigned to specific hand segments, in close agreement with manual human annotations. We used the reconstructed movements and contact forces with the musculoskeletal model of the hand to compute inverse dynamics, yielding joint torques throughout behavior, unifying the hand kinematics and grasp forces into a single physical description. Throughout the processing, we identified individual neurons in the motor cortex of monkeys that were related to grasp force, kinematics, and torques. Together, this framework enabled a comprehensive and precise physical characterization of primate manual behavior, providing a foundation for investigating the neural mechanisms of manual dexterity.
Open AccessA framework for quantifying the mechanics of dexterous grasp
A hallmark of primate behavior is the exceptional ability to dexterously grasp and manipulate objects, yet the investigation of the neural mechanisms that support manual dexterity has been hindered by technical challenges. Optical hand tracking is complicated by frequent occlusions, and contact forces are hard to measure with sufficient precision. Furthermore, while monitoring the kinematics during reaching phase, and the contact forces during object manipulation phase is difficult, joint torques are impossible to measure directly. While challenging, the ability to estimate joint torques in the complex primate hand could provide an invaluable continuous mechanical description spanning both phases. With this in mind, we have developed an experimental apparatus and data processing pipeline for quantifying these variables describing prehension. The apparatus presented objects of various sizes and orientations throughout the workspace, evoking different grasping strategies. Object surfaces were instrumented with thousands of pressure-sensitive elements, enabling high-resolution measurement of distributed contact forces. Simultaneously, eight high-speed cameras were used to reconstruct hand and arm movements with markerless tracking, triangulating 3D landmarks, and mapping them onto a musculoskeletal model, enabling estimation of time-varying joint angles. This posture quantification allowed contact forces to be automatically assigned to specific hand segments, in close agreement with manual human annotations. We used the reconstructed movements and contact forces with the musculoskeletal model of the hand to compute inverse dynamics, yielding joint torques throughout behavior, unifying the hand kinematics and grasp forces into a single physical description. Throughout the processing, we identified individual neurons in the motor cortex of monkeys that were related to grasp force, kinematics, and torques. Together, this framework enabled a comprehensive and precise physical characterization of primate manual behavior, providing a foundation for investigating the neural mechanisms of manual dexterity.
- Open Access
Consistent EMG encoding during reach and grasp by neurons in motor cortex
Identifying what the activity of neurons in the primary motor cortex (M1) represents is essential for understanding motor computation. Yet the relation of M1 to muscles and movement remains unresolved, in part because the kinematic variables M1 appears to encode differ across the limb: hand velocity during reaching, but joint position during grasping. This discrepancy has been taken to imply fundamentally distinct control strategies for proximal and distal segments. Yet, here we show that a single, muscle-based control principle accounts well for both observations. We recorded neural activity, electromyographic (EMG) signals, and movement kinematics from macaque monkeys performing planar reaching, wrist movement, or free-form grasping tasks. Across behaviors, EMG-based encoding models explained M1 firing rates as accurately as the best-performing kinematic model: velocity for reaching, position for grasping, and either variable for wrist movements. Impulse response analysis revealed that these task-dependent kinematic relationships arise from the differences in mechanical impedance of each limb segment: the inertial and intersegmental coupling which dominate the dynamics of the proximal arm are far less important in the hand. These findings indicate that M1 output has a relatively simple, consistent relation to muscle activation and that the apparent divergence in kinematic encoding is a consequence of limb mechanics rather than distinct cortical strategies.
Open AccessConsistent EMG encoding during reach and grasp by neurons in motor cortex
Identifying what the activity of neurons in the primary motor cortex (M1) represents is essential for understanding motor computation. Yet the relation of M1 to muscles and movement remains unresolved, in part because the kinematic variables M1 appears to encode differ across the limb: hand velocity during reaching, but joint position during grasping. This discrepancy has been taken to imply fundamentally distinct control strategies for proximal and distal segments. Yet, here we show that a single, muscle-based control principle accounts well for both observations. We recorded neural activity, electromyographic (EMG) signals, and movement kinematics from macaque monkeys performing planar reaching, wrist movement, or free-form grasping tasks. Across behaviors, EMG-based encoding models explained M1 firing rates as accurately as the best-performing kinematic model: velocity for reaching, position for grasping, and either variable for wrist movements. Impulse response analysis revealed that these task-dependent kinematic relationships arise from the differences in mechanical impedance of each limb segment: the inertial and intersegmental coupling which dominate the dynamics of the proximal arm are far less important in the hand. These findings indicate that M1 output has a relatively simple, consistent relation to muscle activation and that the apparent divergence in kinematic encoding is a consequence of limb mechanics rather than distinct cortical strategies.
- Top Cited PapersOpen Access
- 19 May 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-17
Stabilizing brain-computer interfaces through alignment of latent dynamics
Intracortical brain-computer interfaces (iBCIs) restore motor function to people with paralysis by translating brain activity into control signals for external devices. In current iBCIs, instabilities at the neural interface result in a degradation of decoding performance, which necessitates frequent supervised recalibration using new labeled data. One potential solution is to use the latent manifold structure that underlies neural population activity to facilitate a stable mapping between brain activity and behavior. Recent efforts using unsupervised approaches have improved iBCI stability using this principle; however, existing methods treat each time step as an independent sample and do not account for latent dynamics. Dynamics have been used to enable high-performance prediction of movement intention, and may also help improve stabilization. Here, we present a platform for Nonlinear Manifold Alignment with Dynamics (NoMAD), which stabilizes decoding using recurrent neural network models of dynamics. NoMAD uses unsupervised distribution alignment to update the mapping of nonstationary neural data to a consistent set of neural dynamics, thereby providing stable input to the decoder. In applications to data from monkey motor cortex collected during motor tasks, NoMAD enables accurate behavioral decoding with unparalleled stability over weeks- to months-long timescales without any supervised recalibration.
- 19 May 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-17
Top Cited PapersOpen AccessStabilizing brain-computer interfaces through alignment of latent dynamics
Intracortical brain-computer interfaces (iBCIs) restore motor function to people with paralysis by translating brain activity into control signals for external devices. In current iBCIs, instabilities at the neural interface result in a degradation of decoding performance, which necessitates frequent supervised recalibration using new labeled data. One potential solution is to use the latent manifold structure that underlies neural population activity to facilitate a stable mapping between brain activity and behavior. Recent efforts using unsupervised approaches have improved iBCI stability using this principle; however, existing methods treat each time step as an independent sample and do not account for latent dynamics. Dynamics have been used to enable high-performance prediction of movement intention, and may also help improve stabilization. Here, we present a platform for Nonlinear Manifold Alignment with Dynamics (NoMAD), which stabilizes decoding using recurrent neural network models of dynamics. NoMAD uses unsupervised distribution alignment to update the mapping of nonstationary neural data to a consistent set of neural dynamics, thereby providing stable input to the decoder. In applications to data from monkey motor cortex collected during motor tasks, NoMAD enables accurate behavioral decoding with unparalleled stability over weeks- to months-long timescales without any supervised recalibration.
- Open Access
- 17 March 2025
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 22 (2) , 026018
Less is more: selection from a small set of options improves BCI velocity control
Objective. Decoding algorithms used in invasive brain–computer interfaces (iBCIs) typically convert neural activity into continuously varying velocity commands. We hypothesized that putting constraints on which decoded velocity commands are permissible could improve user performance. To test this hypothesis, we designed the discrete direction selection (DDS) decoder, which uses neural activity to select among a small menu of preset cursor velocities. Approach. We tested DDS in a closed-loop cursor control task against many common continuous velocity decoders in both a human-operated real-time iBCI simulator (the jaBCI) and in a monkey using an iBCI. In the jaBCI, we compared performance across four visits by each of 48 naïve, able-bodied human subjects using either DDS, direct regression with assist (an affine map from neural activity to cursor velocity, DR-A), ReFIT, or the velocity Kalman Filter (vKF). In a follow up study to verify the jaBCI results, we compared a monkey’s performance using an iBCI with either DDS or the Wiener filter decoder (a direct regression decoder that includes time history, WF). Main Result. In the jaBCI, DDS substantially outperformed all other decoders with 93% mean targets hit per visit compared to DR-A, ReFIT, and vKF with 56%, 39%, and 26% mean targets hit, respectively. With the iBCI, the monkey achieved a 61% success rate with DDS and a 37% success rate with WF. Significance. Discretizing the decoded velocity with DDS effectively traded high resolution velocity commands for less tortuous and lower noise trajectories, highlighting the potential benefits of discretization in simplifying online BCI control.
- 17 March 2025
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 22 (2) , 026018
Open AccessLess is more: selection from a small set of options improves BCI velocity control
Objective. Decoding algorithms used in invasive brain–computer interfaces (iBCIs) typically convert neural activity into continuously varying velocity commands. We hypothesized that putting constraints on which decoded velocity commands are permissible could improve user performance. To test this hypothesis, we designed the discrete direction selection (DDS) decoder, which uses neural activity to select among a small menu of preset cursor velocities. Approach. We tested DDS in a closed-loop cursor control task against many common continuous velocity decoders in both a human-operated real-time iBCI simulator (the jaBCI) and in a monkey using an iBCI. In the jaBCI, we compared performance across four visits by each of 48 naïve, able-bodied human subjects using either DDS, direct regression with assist (an affine map from neural activity to cursor velocity, DR-A), ReFIT, or the velocity Kalman Filter (vKF). In a follow up study to verify the jaBCI results, we compared a monkey’s performance using an iBCI with either DDS or the Wiener filter decoder (a direct regression decoder that includes time history, WF). Main Result. In the jaBCI, DDS substantially outperformed all other decoders with 93% mean targets hit per visit compared to DR-A, ReFIT, and vKF with 56%, 39%, and 26% mean targets hit, respectively. With the iBCI, the monkey achieved a 61% success rate with DDS and a 37% success rate with WF. Significance. Discretizing the decoded velocity with DDS effectively traded high resolution velocity commands for less tortuous and lower noise trajectories, highlighting the potential benefits of discretization in simplifying online BCI control.
- Open Access
A Generalist Intracortical Motor Decoder
Mapping the relationship between neural activity and motor behavior is a central aim of sensorimotor neuroscience and neurotechnology. While most progress to this end has relied on restricting complexity, the advent of foundation models instead proposes integrating a breadth of data as an alternate avenue for broadly advancing downstream modeling. We quantify this premise for motor decoding from intracortical microelectrode data, pretraining an autoregressive Transformer on 2000 hours of neural population spiking activity paired with diverse motor covariates from over 30 monkeys and humans. The resulting model is broadly useful, benefiting decoding on 8 downstream decoding tasks and generalizing to a variety of neural distribution shifts. However, we also highlight that scaling autoregressive Transformers seems unlikely to resolve limitations stemming from sensor variability and output stereotypy in neural datasets. Code: https://github.com/joel99/ndt3
Open AccessA Generalist Intracortical Motor Decoder
Mapping the relationship between neural activity and motor behavior is a central aim of sensorimotor neuroscience and neurotechnology. While most progress to this end has relied on restricting complexity, the advent of foundation models instead proposes integrating a breadth of data as an alternate avenue for broadly advancing downstream modeling. We quantify this premise for motor decoding from intracortical microelectrode data, pretraining an autoregressive Transformer on 2000 hours of neural population spiking activity paired with diverse motor covariates from over 30 monkeys and humans. The resulting model is broadly useful, benefiting decoding on 8 downstream decoding tasks and generalizing to a variety of neural distribution shifts. However, we also highlight that scaling autoregressive Transformers seems unlikely to resolve limitations stemming from sensor variability and output stereotypy in neural datasets. Code: https://github.com/joel99/ndt3
- Open Access
- 17 January 2025
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 22 (1)
Unsupervised, piecewise linear decoding enables an accurate prediction of muscle activity in a multi-task brain computer interface
Objective. Creating an intracortical brain-computer interface (iBCI) capable of seamless transitions between tasks and contexts would greatly enhance user experience. However, the nonlinearity in neural activity presents challenges to computing a global iBCI decoder. We aimed to develop a method that differs from a globally optimized decoder to address this issue. Approach. We devised an unsupervised approach that relies on the structure of a low-dimensional neural manifold to implement a piecewise linear decoder. We created a distinctive dataset in which monkeys performed a diverse set of tasks, some trained, others innate, while we recorded neural signals from the motor cortex (M1) and electromyographs (EMGs) from upper limb muscles. We used both linear and nonlinear dimensionality reduction techniques to discover neural manifolds and applied unsupervised algorithms to identify clusters within those spaces. Finally, we fit a linear decoder of EMG for each cluster. A specific decoder was activated corresponding to the cluster each new neural data point belonged to. Main results. We found clusters in the neural manifolds corresponding with the different tasks or task sub-phases. The performance of piecewise decoding improved as the number of clusters increased and plateaued gradually. With only two clusters it already outperformed a global linear decoder, and unexpectedly, it outperformed even a global recurrent neural network (RNN) decoder with 10-12 clusters. Significance. This study introduced a computationally lightweight solution for creating iBCI decoders that can function effectively across a broad range of tasks. EMG decoding is particularly challenging, as muscle activity is used, under varying contexts, to control interaction forces and limb stiffness, as well as motion. The results suggest that a piecewise linear decoder can provide a good approximation to the nonlinearity between neural activity and motor outputs, a result of our increased understanding of the structure of neural manifolds in motor cortex.
- 17 January 2025
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 22 (1)
Open AccessUnsupervised, piecewise linear decoding enables an accurate prediction of muscle activity in a multi-task brain computer interface
Objective. Creating an intracortical brain-computer interface (iBCI) capable of seamless transitions between tasks and contexts would greatly enhance user experience. However, the nonlinearity in neural activity presents challenges to computing a global iBCI decoder. We aimed to develop a method that differs from a globally optimized decoder to address this issue. Approach. We devised an unsupervised approach that relies on the structure of a low-dimensional neural manifold to implement a piecewise linear decoder. We created a distinctive dataset in which monkeys performed a diverse set of tasks, some trained, others innate, while we recorded neural signals from the motor cortex (M1) and electromyographs (EMGs) from upper limb muscles. We used both linear and nonlinear dimensionality reduction techniques to discover neural manifolds and applied unsupervised algorithms to identify clusters within those spaces. Finally, we fit a linear decoder of EMG for each cluster. A specific decoder was activated corresponding to the cluster each new neural data point belonged to. Main results. We found clusters in the neural manifolds corresponding with the different tasks or task sub-phases. The performance of piecewise decoding improved as the number of clusters increased and plateaued gradually. With only two clusters it already outperformed a global linear decoder, and unexpectedly, it outperformed even a global recurrent neural network (RNN) decoder with 10-12 clusters. Significance. This study introduced a computationally lightweight solution for creating iBCI decoders that can function effectively across a broad range of tasks. EMG decoding is particularly challenging, as muscle activity is used, under varying contexts, to control interaction forces and limb stiffness, as well as motion. The results suggest that a piecewise linear decoder can provide a good approximation to the nonlinearity between neural activity and motor outputs, a result of our increased understanding of the structure of neural manifolds in motor cortex.
- Open Access
Few-shot Algorithms for Consistent Neural Decoding (FALCON) Benchmark
Intracortical brain-computer interfaces (iBCIs) can restore movement and communication abilities to individuals with paralysis by decoding their intended behavior from neural activity recorded with an implanted device. While this activity yields high-performance decoding over short timescales, neural data are often nonstationary, which can lead to decoder failure if not accounted for. To maintain performance, users must frequently recalibrate decoders, which requires the arduous collection of new neural and behavioral data. Aiming to reduce this burden, several approaches have been developed that either limit recalibration data requirements (few-shot approaches) or eliminate explicit recalibration entirely (zero-shot approaches). However, progress is limited by a lack of standardized datasets and comparison metrics, causing methods to be compared in an ad hoc manner. Here we introduce the FALCON benchmark suite (Few-shot Algorithms for COnsistent Neural decoding) to standardize evaluation of iBCI robustness. FALCON curates five datasets of neural and behavioral data that span movement and communication tasks to focus on behaviors of interest to modern-day iBCIs. Each dataset includes calibration data, optional few-shot recalibration data, and private evaluation data. We implement a flexible evaluation platform which only requires user-submitted code to return behavioral predictions on unseen data. We also seed the benchmark by applying baseline methods spanning several classes of possible approaches. FALCON aims to provide rigorous selection criteria for robust iBCI decoders, easing their translation to real-world devices. https://snel-repo.github.io/falcon/
Open AccessFew-shot Algorithms for Consistent Neural Decoding (FALCON) Benchmark
Intracortical brain-computer interfaces (iBCIs) can restore movement and communication abilities to individuals with paralysis by decoding their intended behavior from neural activity recorded with an implanted device. While this activity yields high-performance decoding over short timescales, neural data are often nonstationary, which can lead to decoder failure if not accounted for. To maintain performance, users must frequently recalibrate decoders, which requires the arduous collection of new neural and behavioral data. Aiming to reduce this burden, several approaches have been developed that either limit recalibration data requirements (few-shot approaches) or eliminate explicit recalibration entirely (zero-shot approaches). However, progress is limited by a lack of standardized datasets and comparison metrics, causing methods to be compared in an ad hoc manner. Here we introduce the FALCON benchmark suite (Few-shot Algorithms for COnsistent Neural decoding) to standardize evaluation of iBCI robustness. FALCON curates five datasets of neural and behavioral data that span movement and communication tasks to focus on behaviors of interest to modern-day iBCIs. Each dataset includes calibration data, optional few-shot recalibration data, and private evaluation data. We implement a flexible evaluation platform which only requires user-submitted code to return behavioral predictions on unseen data. We also seed the benchmark by applying baseline methods spanning several classes of possible approaches. FALCON aims to provide rigorous selection criteria for robust iBCI decoders, easing their translation to real-world devices. https://snel-repo.github.io/falcon/
- Open Access
Unsupervised, piecewise linear decoding enables an accurate prediction of muscle activity in a multi-task brain computer interface
Objective Creating an intracortical brain-computer interface (iBCI) capable of seamless transitions between tasks and contexts would greatly enhance user experience. However, the nonlinearity in neural activity presents challenges to computing a global iBCI decoder. We aimed to develop a method that differs from a globally optimized decoder to address this issue. Approach We devised an unsupervised approach that relies on the structure of a low-dimensional neural manifold to implement a piecewise linear decoder. We created a distinctive dataset in which monkeys performed a diverse set of tasks, some trained, others innate, while we recorded neural signals from the motor cortex (M1) and electromyographs (EMGs) from upper limb muscles. We used both linear and nonlinear dimensionality reduction techniques to discover neural manifolds and applied unsupervised algorithms to identify clusters within those spaces. Finally, we fit a linear decoder of EMG for each cluster. A specific decoder was activated corresponding to the cluster each new neural data point belonged to. Main results We found clusters in the neural manifolds corresponding with the different tasks or task sub-phases. The performance of piecewise decoding improved as the number of clusters increased and plateaued gradually. With only two clusters it already outperformed a global linear decoder, and unexpectedly, it outperformed even a global recurrent neural network (RNN) decoder with 10-12 clusters. Significance This study introduced a computationally lightweight solution for creating iBCI decoders that can function effectively across a broad range of tasks. EMG decoding is particularly challenging, as muscle activity is used, under varying contexts, to control interaction forces and limb stiffness, as well as motion. The results suggest that a piecewise linear decoder can provide a good approximation to the nonlinearity between neural activity and motor outputs, a result of our increased understanding of the structure of neural manifolds in motor cortex.
Open AccessUnsupervised, piecewise linear decoding enables an accurate prediction of muscle activity in a multi-task brain computer interface
Objective Creating an intracortical brain-computer interface (iBCI) capable of seamless transitions between tasks and contexts would greatly enhance user experience. However, the nonlinearity in neural activity presents challenges to computing a global iBCI decoder. We aimed to develop a method that differs from a globally optimized decoder to address this issue. Approach We devised an unsupervised approach that relies on the structure of a low-dimensional neural manifold to implement a piecewise linear decoder. We created a distinctive dataset in which monkeys performed a diverse set of tasks, some trained, others innate, while we recorded neural signals from the motor cortex (M1) and electromyographs (EMGs) from upper limb muscles. We used both linear and nonlinear dimensionality reduction techniques to discover neural manifolds and applied unsupervised algorithms to identify clusters within those spaces. Finally, we fit a linear decoder of EMG for each cluster. A specific decoder was activated corresponding to the cluster each new neural data point belonged to. Main results We found clusters in the neural manifolds corresponding with the different tasks or task sub-phases. The performance of piecewise decoding improved as the number of clusters increased and plateaued gradually. With only two clusters it already outperformed a global linear decoder, and unexpectedly, it outperformed even a global recurrent neural network (RNN) decoder with 10-12 clusters. Significance This study introduced a computationally lightweight solution for creating iBCI decoders that can function effectively across a broad range of tasks. EMG decoding is particularly challenging, as muscle activity is used, under varying contexts, to control interaction forces and limb stiffness, as well as motion. The results suggest that a piecewise linear decoder can provide a good approximation to the nonlinearity between neural activity and motor outputs, a result of our increased understanding of the structure of neural manifolds in motor cortex.
- 1 January 2024
- Published by American Physiological Society in Journal of Neurophysiology
- Vol. 131 (1) , 75-87
Highlights from the 32nd Annual Meeting of the Society for the Neural Control of Movement
- 1 January 2024
- Published by American Physiological Society in Journal of Neurophysiology
- Vol. 131 (1) , 75-87
Highlights from the 32nd Annual Meeting of the Society for the Neural Control of Movement
- Open Access
- 1 October 2023
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 20 (5) , 056040
From monkeys to humans: observation-based EMG brain–computer interface decoders for humans with paralysis
Objective. Intracortical brain–computer interfaces (iBCIs) aim to enable individuals with paralysis to control the movement of virtual limbs and robotic arms. Because patients’ paralysis prevents training a direct neural activity to limb movement decoder, most iBCIs rely on ‘observation-based’ decoding in which the patient watches a moving cursor while mentally envisioning making the movement. However, this reliance on observed target motion for decoder development precludes its application to the prediction of unobservable motor output like muscle activity. Here, we ask whether recordings of muscle activity from a surrogate individual performing the same movement as the iBCI patient can be used as target for an iBCI decoder. Approach. We test two possible approaches, each using data from a human iBCI user and a monkey, both performing similar motor actions. In one approach, we trained a decoder to predict the electromyographic (EMG) activity of a monkey from neural signals recorded from a human. We then contrast this to a second approach, based on the hypothesis that the low-dimensional ‘latent’ neural representations of motor behavior, known to be preserved across time for a given behavior, might also be preserved across individuals. We ‘transferred’ an EMG decoder trained solely on monkey data to the human iBCI user after using Canonical Correlation Analysis to align the human latent signals to those of the monkey. Main results. We found that both direct and transfer decoding approaches allowed accurate EMG predictions between two monkeys and from a monkey to a human. Significance. Our findings suggest that these latent representations of behavior are consistent across animals and even primate species. These methods are an important initial step in the development of iBCI decoders that generate EMG predictions that could serve as signals for a biomimetic decoder controlling motion and impedance of a prosthetic arm, or even muscle force directly through functional electrical stimulation.
- 1 October 2023
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 20 (5) , 056040
Open AccessFrom monkeys to humans: observation-based EMG brain–computer interface decoders for humans with paralysis
Objective. Intracortical brain–computer interfaces (iBCIs) aim to enable individuals with paralysis to control the movement of virtual limbs and robotic arms. Because patients’ paralysis prevents training a direct neural activity to limb movement decoder, most iBCIs rely on ‘observation-based’ decoding in which the patient watches a moving cursor while mentally envisioning making the movement. However, this reliance on observed target motion for decoder development precludes its application to the prediction of unobservable motor output like muscle activity. Here, we ask whether recordings of muscle activity from a surrogate individual performing the same movement as the iBCI patient can be used as target for an iBCI decoder. Approach. We test two possible approaches, each using data from a human iBCI user and a monkey, both performing similar motor actions. In one approach, we trained a decoder to predict the electromyographic (EMG) activity of a monkey from neural signals recorded from a human. We then contrast this to a second approach, based on the hypothesis that the low-dimensional ‘latent’ neural representations of motor behavior, known to be preserved across time for a given behavior, might also be preserved across individuals. We ‘transferred’ an EMG decoder trained solely on monkey data to the human iBCI user after using Canonical Correlation Analysis to align the human latent signals to those of the monkey. Main results. We found that both direct and transfer decoding approaches allowed accurate EMG predictions between two monkeys and from a monkey to a human. Significance. Our findings suggest that these latent representations of behavior are consistent across animals and even primate species. These methods are an important initial step in the development of iBCI decoders that generate EMG predictions that could serve as signals for a biomimetic decoder controlling motion and impedance of a prosthetic arm, or even muscle force directly through functional electrical stimulation.