SEMA5B
PulseAugur coverage of SEMA5B — every cluster mentioning SEMA5B across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
PhysioWave-T: Efficient Foundation Models for Biosignal Analysis
Researchers have introduced PhysioWave-T, a family of foundation models designed for efficient processing of biosignals like EEG, ECG, and sEMG. The models utilize a technique called Dynamic Scale Folding to significant…
-
Transformer model optimizes robot rehab using muscle activation data
Researchers have developed a novel transformer-based model designed to optimize robot-mediated rehabilitation by prescribing trajectories based on individual muscle activations. This model maps surface electromyography …
-
Neuromotor Hierarchy Network improves sEMG decoding with physiological biases
Researchers have developed the Neuromotor Hierarchy Network (NHN), a novel architecture designed to improve the decoding of surface electromyography (sEMG) signals for human-computer interaction. NHN learns a compact la…
-
EFormer network enhances hand pose tracking using sEMG signals
Researchers have developed EFormer, a novel network designed to improve continuous hand pose tracking using surface electromyography (sEMG) signals. This system builds upon a frozen tracking backbone and incorporates a …
-
Koopman operator theory predicts grip force from EMG signals
Researchers have developed a novel method using Koopman operator theory to predict grip force from surface electromyography (sEMG) signals. This approach aims to improve robotic rehabilitation by accurately estimating a…
-
Spiking Neural Networks Offer Energy-Efficient Muscle Fatigue Detection
Researchers have developed an energy-efficient framework for detecting muscle fatigue using Spiking Neural Networks (SNNs). This approach leverages sparse, event-driven computation and temporal modeling, making it suita…
-
SonoRank uses ultrasound for calibration-free prosthetic finger control
Researchers have developed SonoRank, a novel method for detecting finger flexion using forearm ultrasound sequences, aiming to overcome the limitations of current prosthetic hand technology. Unlike existing ultrasound-b…
-
New PGUDA framework boosts sEMG gesture recognition accuracy
Researchers have developed a novel framework called PGUDA (Pressure-Guided Unsupervised Domain Adaptation) to improve the accuracy of gesture recognition using surface electromyography (sEMG) signals. This method addres…
-
Memorization indicators may help detect overfitting in sEMG deep learning
Researchers have explored the use of memorization indicators to detect overfitting in deep learning models used for surface electromyography (sEMG) decoders, particularly when limited sample sizes are available for subj…
-
Peking University team secures funding for new embodied AI data acquisition tech
SnowOrigin, a team with roots at Peking University, has secured investment from notable figures like Gong Hongjia and Lu Qi, along with overseas institutions. The company is developing a new generation of data acquisiti…
-
Silent speech synthesis uses sEMG and lipreading with masking
Researchers have developed a new framework for silent speech synthesis that combines surface electromyography (sEMG) and lipreading data. This approach uses modality masking during training to improve robustness against…
-
New wave modeling framework offers continuous temporal representations for event-based signals
Researchers have developed a novel framework for modeling continuous temporal representations of event-based signals, such as those from biological processes like sEMG. This approach maps input signals into a complex-va…
-
New study compares sEMG encoding accuracy across speech modes
A new research paper explores the effectiveness of Speech Articulatory Coding (SPARC) features for predicting surface electromyography (sEMG) envelopes across different speech modes. The study found that SPARC features …