| 1. |
- Clarke, Alexander Kenneth, et al.
(författare)
-
Deep learning for robust decomposition of high-density surface EMG signals
- 2021
-
Ingår i: IEEE Transactions on Biomedical Engineering. - 0018-9294 .- 1558-2531. ; 68:2, s. 526-534
-
Tidskriftsartikel (refereegranskat)abstract
- Blind source separation (BSS) algorithms, such as gradient convolution kernel compensation (gCKC), can efficiently and accurately decompose high-density surface electromyography (HD-sEMG) signals into constituent motor unit (MU) action potential trains. Once the separation matrix is blindly estimated on a signal interval, it is also possible to apply the same matrix to subsequent signal segments. Nonetheless, the trained separation matrices are sub-optimal in noisy conditions and require that incoming data undergo computationally expensive whitening. One unexplored alternative is to instead use the paired HD-sEMG signal and BSS output to train a model to predict MU activations within a supervised learning framework. A gated recurrent unit (GRU) network was trained to decompose both simulated and experimental unwhitened HD-sEMG signal using the output of the gCKC algorithm. The results on the experimental data were validated by comparison with the decomposition of concurrently recorded intramuscular EMG signals. The GRU network outperformed gCKC at low signal-to-noise ratios, proving superior performance in generalising to new data. Using 12 seconds of experimental data per recording, the GRU performed similarly to gCKC, at rates of agreement of 92.5% (84.5%-97.5%) and 94.9% (88.8%-100.0%) respectively for GRU and gCKC against matched intramuscular sources.
|
|
| 2. |
- Sagastegui Alva, Patrick G., et al.
(författare)
-
Wearable multichannel haptic device for encoding proprioception in the upper limb
- 2020
-
Ingår i: Journal of Neural Engineering. - : IOP Publishing. - 1741-2560 .- 1741-2552. ; 17:5
-
Tidskriftsartikel (refereegranskat)abstract
- We present the design, implementation, and evaluation of a wearable multichannel haptic system. The device is a wireless closed-loop armband driven by surface electromyography (EMG) and provides sensory feedback encoding proprioception. The study is motivated by restoring proprioception information in upper limb prostheses. Approach. The armband comprises eight vibrotactile actuators that generate distributed patterns of mechanical waves around the limb to stimulate perception and to transfer proportional information on the arm motion. An experimental study was conducted to assess: the sensory threshold in eight locations around the forearm, the user adaptation to the sensation provided by the device, the user performance in discriminating multiple stimulation levels, and the device performance in coding proprioception using four spatial patterns of stimulation. Eight able-bodied individuals performed reaching tasks by controlling a cursor with an EMG interface in a virtual environment. Vibrotactile patterns were tested with and without visual information on the cursor position with the addition of a random rotation of the reference control system to disturb the natural control and proprioception. Main results. The sensation threshold depended on the actuator position and increased over time. The maximum resolution for stimuli discrimination was four. Using this resolution, four patterns of vibrotactile activation with different spatial and magnitude properties were generated to evaluate their performance in enhancing proprioception. The optimal vibration pattern varied among the participants. When the feedback was used in closed-loop control with the EMG interface, the task success rate, completion time, execution efficiency, and average target-cursor distance improved for the optimal stimulation pattern compared to the condition without visual or haptic information on the cursor position. Significance. The results indicate that the vibrotactile device enhanced the participants’ perceptual ability, suggesting that the proposed closed-loop system has the potential to code proprioception and enhance user performance in the presence of perceptual perturbation.
|
|
