skip to main content

Attention:

The NSF Public Access Repository (PAR) system and access will be unavailable from 11:00 PM ET on Thursday, February 13 until 2:00 AM ET on Friday, February 14 due to maintenance. We apologize for the inconvenience.


Title: Toward a generalizable deep CNN for neural drive estimation across muscles and participants
Abstract

Objective.High-density electromyography (HD-EMG) decomposition algorithms are used to identify individual motor unit (MU) spike trains, which collectively constitute the neural code of movements, to predict motor intent. This approach has advanced from offline to online decomposition, from isometric to dynamic contractions, leading to a wide range of neural-machine interface applications. However, current online methods need offline retraining when applied to the same muscle on a different day or to a different person, which limits their applications in a real-time neural-machine interface. We proposed a deep convolutional neural network (CNN) framework for neural drive estimation, which takes in frames of HD-EMG signals as input, extracts general spatiotemporal properties of MU action potentials, and outputs the number of spikes in each frame. The deep CNN can generalize its application without retraining to HD-EMG data recorded in separate sessions, muscles, or participants.Approach.We recorded HD-EMG signals from the vastus medialis and vastus lateralis muscles from five participants while they performed isometric contractions during two sessions separated by ∼20 months. We identified MU spike trains from HD-EMG signals using a convolutive blind source separation (BSS) method, and then used the cumulative spike train (CST) of these MUs and the HD-EMG signals to train and validate the deep CNN.Main results.On average, the correlation coefficients between CST from the BSS and that from deep CNN were0.983±0.006for leave-one-out across-sessions-and-muscles validation and0.989±0.002for leave-one-out across-participants validation. When trained with more than four datasets, the performance of deep CNN saturated at0.984±0.001for cross validations across muscles, sessions, and participants.Significance.We can conclude that the deep CNN is generalizable across the aforementioned conditions without retraining. We could potentially generate a robust deep CNN to estimate neural drive to muscles for neural-machine interfaces.

 
more » « less
PAR ID:
10391786
Author(s) / Creator(s):
; ; ; ; ;
Publisher / Repository:
IOP Publishing
Date Published:
Journal Name:
Journal of Neural Engineering
Volume:
20
Issue:
1
ISSN:
1741-2560
Page Range / eLocation ID:
Article No. 016006
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract

    Objective.In vivoimaging assessments of skeletal muscle structure and function allow for longitudinal quantification of tissue health. Magnetic resonance elastography (MRE) non-invasively quantifies tissue mechanical properties, allowing for evaluation of skeletal muscle biomechanics in response to loading, creating a better understanding of muscle functional health.Approach. In this study, we analyze the anisotropic mechanical response of calf muscles using MRE with a transversely isotropic, nonlinear inversion algorithm (TI-NLI) to investigate the role of muscle fiber stiffening under load. We estimate anisotropic material parameters including fiber shear stiffness (μ1), substrate shear stiffness (μ2), shear anisotropy (ϕ), and tensile anisotropy (ζ) of the gastrocnemius muscle in response to both passive and active tension.Main results. In passive tension, we found a significant increase inμ1,ϕ,andζwith increasing muscle length. While in active tension, we observed increasingμ2and decreasingϕandζduring active dorsiflexion and plantarflexion—indicating less anisotropy—with greater effects when the muscles act as agonist.Significance. The study demonstrates the ability of this anisotropic MRE method to capture the multifaceted mechanical response of skeletal muscle to tissue loading from muscle lengthening and contraction.

     
    more » « less
  2. Abstract

    We continue earlier efforts in computing the dimensions of tangent space cohomologies of Calabi–Yau manifolds using deep learning. In this paper, we consider the dataset of all Calabi–Yau four-folds constructed as complete intersections in products of projective spaces. Employing neural networks inspired by state-of-the-art computer vision architectures, we improve earlier benchmarks and demonstrate that all four non-trivial Hodge numbers can be learned at the same time using a multi-task architecture. With 30% (80%) training ratio, we reach an accuracy of 100% forh(1,1)and 97% forh(2,1)(100% for both), 81% (96%) forh(3,1), and 49% (83%) forh(2,2). Assuming that the Euler number is known, as it is easy to compute, and taking into account the linear constraint arising from index computations, we get 100% total accuracy.

     
    more » « less
  3. Abstract

    We present the direct-imaging discovery of a giant planet orbiting the young star AF Lep, a 1.2Mmember of the 24 ± 3 MyrβPic moving group. AF Lep was observed as part of our ongoing high-contrast imaging program targeting stars with astrometric accelerations between Hipparcos and Gaia that indicate the presence of substellar companions. Keck/NIRC2 observations inLwith the vector vortex coronagraph reveal a point source, AF Lep b, at ≈340 mas, which exhibits orbital motion at the 6σlevel over the course of 13 months. A joint orbit fit yields precise constraints on the planet’s dynamical mass of3.20.6+0.7MJup, semimajor axis of8.41.3+1.1au, and eccentricity of0.240.15+0.27. AF Lep hosts a debris disk located at ∼50 au, but it is unlikely to be sculpted by AF Lep b, implying there may be additional planets in the system at wider separations. The stellar inclination (i*=549+11°) and orbital inclination (io=5012+9°) are in good agreement, which is consistent with the system having spin–orbit alignment. AF Lep b is the lowest-mass imaged planet with a dynamical mass measurement and highlights the promise of using astrometric accelerations as a tool to find and characterize long-period planets.

     
    more » « less
  4. Abstract

    We present13CO(J= 1 → 0) observations for the EDGE-CALIFA survey, which is a mapping survey of 126 nearby galaxies at a typical spatial resolution of 1.5 kpc. Using detected12CO emission as a prior, we detect13CO in 41 galaxies via integrated line flux over the entire galaxy and in 30 galaxies via integrated line intensity in resolved synthesized beams. Incorporating our CO observations and optical IFU spectroscopy, we perform a systematic comparison between the line ratio12/13I[12CO(J=10)]/I[13CO(J=10)]and the properties of the stars and ionized gas. Higher12/13values are found in interacting galaxies compared to those in noninteracting galaxies. The global12/13slightly increases with infrared colorF60/F100but appears insensitive to other host-galaxy properties such as morphology, stellar mass, or galaxy size. We also present azimuthally averaged12/13profiles for our sample up to a galactocentric radius of 0.4r25(∼6 kpc), taking into account the13CO nondetections by spectral stacking. The radial profiles of12/13are quite flat across our sample. Within galactocentric distances of 0.2r25, the azimuthally averaged12/13increases with the star formation rate. However, Spearman rank correlation tests show the azimuthally averaged12/13does not strongly correlate with any other gas or stellar properties in general, especially beyond 0.2r25from the galaxy centers. Our findings suggest that in the complex environments in galaxy disks,12/13is not a sensitive tracer for ISM properties. Dynamical disturbances, like galaxy interactions or the presence of a bar, also have an overall impact on12/13, which further complicates the interpretations of12/13variations.

     
    more » « less
  5. Abstract

    We report the temperature dependence of the Yb valence in the geometrically frustrated compoundYbB4from 12 to 300 K using resonant x-ray emission spectroscopy at the YbLα1transition. We find that the Yb valence,v, is hybridized between thev = 2 andv = 3 valence states, increasing fromv=2.61±0.01at 12 K tov=2.67±0.01at 300 K, confirming thatYbB4is a Kondo system in the intermediate valence regime. This result indicates that the Kondo interaction inYbB4is substantial, and is likely to be the reason whyYbB4does not order magnetically at low temperature, rather than this being an effect of geometric frustration. Furthermore, the zero-point valence of the system is extracted from our data and compared with other Kondo lattice systems. The zero-point valence seems to be weakly dependent on the Kondo temperature scale, but not on the valence change temperature scaleTv.

     
    more » « less