No abstract

Theories on the neural control of movement are largely based on movement-sensing devices that capture the dynamics of predefined anatomical landmarks. Neuromuscular interfaces, such as surface electromyography (sEMG), can in theory surpass the limitations imposed by motion-based technologies by sensing the motor commands transmitted by the final pathway of movement, the motor units. The recording of motor unit activity may allow the prediction of the kinetics and kinematics continuously in time and space, without being limited to several biological and physical boundaries that digital cameras or inertial sensors suffer. However, current sEMG decoding algorithms can only predict few degrees of freedom (<3). By combining markerless machine vision and high-density sEMG electrodes, we aimed to test the hypothesis that a physiologically inspired deep neural network can reconstruct the movement of the human hand as precise as digital cameras and with the additional benefit of predicting the underlying forces (i.e., grasping a cup of coffee). We demonstrate that our deep learning model can continuously predict all degrees of freedom of the hand with negligible errors during natural motion tasks from 320 sEMG sensors placed only on the extrinsic hand muscles. Our deep learning model was able to display the 3D hand kinematics and the full force range of the hand digits during isometric contractions. The current results demonstrate that deep learning applied to EMG signals gives access to an unprecedented representation of the final neural code of movement.

No abstract

During algorithm development and analysis researchers regularly use software libraries developed for their specific domain. With such libraries, complex analysis tasks can often be reduced to a couple of lines of code. This not only reduces the amount of implementation required but also prevents errors.The best developer experience is usually achieved when the entire analysis can be represented with the tools provided by a single library. For example, when an entire machine learning pipeline is represented by a scikit-learn pipeline (Pedregosa et al., 2018), it is extremely easy to switch out and train algorithms. Furthermore, train/test leaks and other methodological errors at various stages in the analysis are automatically prevented -even if the user might not be aware of these issue.However, if the performed analysis gets too complex, too specific to an application domain, or requires the use of tooling and algorithms from multiple frameworks, developers lose a lot of the benefits provided by individual libraries. In turn, the required skill level and the chance of methodological errors rise.With tpcp we attempt to overcome the issue by providing higher-level tooling and structure for algorithm development and evaluation that is independent of the frameworks required for the algorithm implementation.

<p>Surface electromyography (sEMG) is a non-invasive technique that measures the electrical activity generated by the muscles using sensors placed on the skin. It has been widely used in the field of prosthetics and other assistive systems because of the physiological connection between muscle electrical activity and movement dynamics. However, most existing sEMG-based decoding algorithms show a limited number of detectable degrees of freedom that can be proportionally and simultaneously controlled in real-time, which limits the use of EMG in a wide range of applications, including prosthetics and other consumer-level applications (e.g., human/machine interfacing). In this work, we surpass the current state of the art by developing a new deep learning method that can decode and map the electrophysiological activity of the forearm muscles into proportional and simultaneous control of > 20 degrees of freedom of the human hand with real-time resolution and with latency within the neuromuscular delays (< 50 ms). We recorded the kinematics of the human hand during grasping, pinching, individual digit movements and three gestures at slow (0.5 Hz) and fast (0.75 Hz) movement speeds in healthy participants.</p> <p>We demonstrate that our neural network can predict the kinematics of the hand in real-time at a constant 32 predictions per second. To achieve this, we employed transfer learning and created a prediction smoothing algorithm for the output of the neural network that reconstructed the full geometry of the hand in three-dimensional Cartesian space in real-time. Our results demonstrate that high-density EMG signals from the forearm muscles contain almost all the information that is needed to predict the kinematics of the human hand. The proposed method has the capability of predicting the full kinematics of the human hand in an unprecedented way and with real-time resolution with immediate translational impact in subjects with motor impairments. </p>