Active upper limb prostheses: A review on current state and upcoming breakthroughs

A Marinelli, N Boccardo, F Tessari… - Progress in …, 2023 - iopscience.iop.org
The journey of a prosthetic user is characterized by the opportunities and the limitations of a
device that should enable activities of daily living (ADL). In particular, experiencing a bionic …

Transformers in biosignal analysis: A review

A Anwar, Y Khalifa, JL Coyle, E Sejdic - Information Fusion, 2024 - Elsevier
Transformer architectures have become increasingly popular in healthcare applications.
Through outstanding performance in natural language processing and superior capability to …

Marsellus: A heterogeneous RISC-V AI-IoT end-node SoC with 2–8 b DNN acceleration and 30%-boost adaptive body biasing

F Conti, G Paulin, A Garofalo, D Rossi… - IEEE Journal of Solid …, 2023 - ieeexplore.ieee.org
Emerging artificial intelligence-enabled Internet-of-Things (AI-IoT) system-on-chip (SoC) for
augmented reality, personalized healthcare, and nanorobotics need to run many diverse …

Electromyography based decoding of dexterous, in-hand manipulation motions with temporal multichannel vision transformers

RV Godoy, A Dwivedi… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Electromyography (EMG) signals have been used in designing muscle-machine interfaces
(MuMIs) for various applications, ranging from entertainment (EMG controlled games) to …

Eegformer: Transformer-based epilepsy detection on raw eeg traces for low-channel-count wearable continuous monitoring devices

P Busia, A Cossettini, TM Ingolfsson… - … Circuits and Systems …, 2022 - ieeexplore.ieee.org
The development of a device for long-term and continuous monitoring of epilepsy is a very
challenging objective, due to the high accuracy standards and nearly zero false alarms …

Plinio: a user-friendly library of gradient-based methods for complexity-aware DNN optimization

DJ Pagliari, M Risso, BA Motetti… - 2023 Forum on …, 2023 - ieeexplore.ieee.org
Accurate yet efficient Deep Neural Networks (DNNs) are in high demand, especially for
applications that require their execution on constrained edge devices. Finding such DNNs in …

Reducing false alarms in wearable seizure detection with eegformer: A compact transformer model for mcus

P Busia, A Cossettini, TM Ingolfsson… - … Circuits and Systems, 2024 - ieeexplore.ieee.org
The long-term, continuous analysis of electroencephalography (EEG) signals on wearable
devices to automatically detect seizures in epileptic patients is a high-potential application …

Efficient deep learning models for privacy-preserving people counting on low-resolution infrared arrays

C Xie, F Daghero, Y Chen, M Castellano… - IEEE Internet of …, 2023 - ieeexplore.ieee.org
Ultralow-resolution infrared (IR) array sensors offer a low cost, energy efficient, and privacy-
preserving solution for people counting, with applications, such as occupancy monitoring …

Online transformers with spiking neurons for fast prosthetic hand control

N Leroux, J Finkbeiner, E Neftci - 2023 IEEE Biomedical …, 2023 - ieeexplore.ieee.org
Fast and accurate online processing is essential for smooth prosthetic hand control with
Surface Electromyography signals (sEMG). Although transformers are state-of-the-art deep …

A Long Short-Term Memory-based interconnected architecture for classification of grasp types using surface-Electromyography signals

A Erazo, SB Ko - IEEE Transactions on Artificial Intelligence, 2023 - ieeexplore.ieee.org
Reliable classification of grasp types from human limbs has become an important aspect
used by applications with humanoid robotic systems, because of their high-accuracy …