Spiking Neural Networks for sEMG-Based Hand Gesture Recognition
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Given the recent surge of significant interest in implementing intelligent hand gesture recognition methods in human-machine interface systems, a wide variety of Deep Neural Networks (DNNs) have been proposed in the literature. In this paper, we introduce a novel and compact Spiking Neural Network (SNN) model for hand gesture recognition using High-Density surface Electromyogram (HD-sEMG) signals. Capitalizing on their ability to extract spatiotemporal features of HD-sEMG signals along with their proven strength in imitating human brain's neural activity using event-driven data processing, we used SNNs as the main building block of our proposed hand gesture recognition model. We show that our proposed model can efficiently differentiate 14 hand movements by considering each sample of the HD-sEMG data as a single time step for the SNN architecture. Moreover, we show that the proposed SNN model does not require huge pre-processing, spike encoding and feature extraction tasks and works effectively on Min-Max normalized continuous-value sEMG signals. We evaluate our SNN model using a 5-fold cross-validation scheme and categorize different participants based on the range of classification accuracy we obtained for them. The following results are acquired by segmenting HD-sEMG signals into windows of size 62.5ms with no overlap. The proposed method led to 6 out of 19 subjects achieving average classification accuracy of ≥ 80% with maximum accuracy of 98% associated with 3 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">rd</sup> session of the sEMG dataset as the test set.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it