arXiv subjects

Dario Farina

Publications and source records attributed to Dario Farina.

At least 19 recordsLinked to original sources

arXiv2026

A Portable Multichannel Kilohertz Current Stimulator for Selective Peripheral Transcutaneous Stimulation

We present SineStim, a portable, 12-channel current stimulator for transcutaneous spinal cord stimulation and peripheral electrical stimulation at kilohertz frequencies. Each channel delivers independent, current-controlled sinusoidal waveforms with amplitudes from 0 to 50 mA (0.1 mA resolution) and frequencies from 0 to 50 kHz (0.1 Hz resolution), with burst modulation modes supported. A custom output stage with a high compliance voltage of $\pm$ 120 V was designed and developed, with galvanically isolated channels and independently programmable stimulation parameters for each channel. The stimulator performance was tested on both passive loads and human subjects. Benchtop characterisation on resistive and resistive-capacitive loads demonstrated a total harmonic distortion between 1 - 8 % across typical operating conditions. Multichannel functionality was demonstrated in two-channel human forearm stimulation experiments. Burst-modulated waveforms with differing channel amplitudes modulated inter-finger force ratios, and channels with small frequency offsets elicited temporal interference force patterns at the beat frequency. Smoothly enveloped bursts of kilohertz sinusoidal waveforms produced negligible stimulation artifacts at steady state in concurrent surface electromyography (sEMG) recordings at motor threshold, in contrast to conventional biphasic square wave stimulation. SineStim delivers precise, isolated, multichannel kilohertz stimulation through a portable device, with performance demonstrated on both benchtop loads and human participants. By combining multichannel spatial control with minimal-artifact sEMG compatibility, SineStim enables future precision non-invasive neural stimulation paradigms based on multichannel optimisation and real-time closed-loop control capabilities not available via existing single-channel stimulators.

eess.SP↗

arXiv2026

emgforge: an automated end-to-end pipeline for simulating surface EMG on MRI-based volume conductors

Simulated electromyograms are used to understand what an electrode records, to test decomposition and estimation algorithms on signals with known ground truth, and to train learning-based decoders. Most simulators fix the geometry to a cylinder or a slab, or stop at the lead field and leave the rest to the user. We present emgforge, an open pipeline that takes a labelled MRI segmentation of a limb to surface EMG in one command: a tetrahedral mesh with conductivity tensors aligned with each muscle's fibres; one reciprocal finite-element solve per electrode, valid for every fibre of every muscle; fibre beds that are straight or follow the muscle's shape; a motor-unit pool obeying the size principle; motor-unit action potentials on any electrode layout; and a motoneuron-pool and twitch layer that turns a drive or a movement into interference EMG and force. We describe the pipeline stage by stage, and at each stage we show, with an example, why the choice was made. The step that turns a lead field into a single-fibre action potential -- direct line-source synthesis -- is checked against a closed-form solution ($r = 1.0000$, zero lag), and the whole chain against fifty checks with numeric criteria from the physiological literature. We then use the pipeline for four studies: what an electrode sees as a function of depth, fat, spacing and montage; whether fibre geometry changes the signal; how much crosstalk a grid over one muscle receives from its neighbours; and how interference EMG scales with drive. The code, the validation suite and three datasets with ground truth are released.

cs.CE↗

arXiv2026

NeuroRVQ: Multi-Scale Biosignal Tokenization for Generative Foundation Models

Biosignals such as electroencephalography (EEG), electrocardiography (ECG), and electromyography (EMG) encode physiological activity across multiple temporal and spectral scales, yielding representations that are rich but challenging for machine learning. Foundation models trained to predict masked signal tokens have shown promise in learning generalizable biosignal representations, yet their performance depends on the tokenizer's ability to preserve high-frequency dynamics and reconstruct signals with high fidelity. We introduce NeuroRVQ, a modality-adaptive biosignal tokenizer family designed for high-fidelity signal reconstruction. To capture the full frequency spectrum, NeuroRVQ decomposes biosignals into frequency-specific representations via multi-scale temporal convolutions, each encoded into hierarchical RVQ codebooks to preserve high-frequency detail, combined with a novel phase-aware training loss that respects the circular topology of Fourier phase. By tuning the temporal resolution, number and size of temporal kernels and RVQ depth, this design adapts to the spectro-temporal characteristics of each biosignal modality. To validate that tokenizer quality drives downstream performance, we train a simple masked-token foundation model for each modality (NeuroRVQ-FM) using the corresponding NeuroRVQ tokenizer. The NeuroRVQ-FM family achieves competitive or superior downstream performance compared to existing modality-specific foundation models, demonstrating that high-fidelity tokenization is a critical factor for effective biosignal modeling.

cs.LG↗

arXiv2026

Quasi-Linear ICA for Motor Unit Decomposition during Dynamic Contractions

Decomposing surface electromyography (EMG) into the spike trains of individual motor neurons is a long-standing inverse problem and a key step toward motor-neuron-driven neural interfaces such as prosthetics and exoskeletons. The standard approach, independent component analysis (ICA) of the multichannel signal, assumes that the mixing from neurons to electrodes is stationary in time. This assumption fails during movement, when volume-conductor deformation makes the mixing time-varying, and current decomposition algorithms are correspondingly restricted to isometric contractions. We introduce a quasi-linear ICA formulation in which a static linear separator is preceded by a learned, low-rank, time-varying invertible transformation. The separator is trained with an independence loss on the uncompensated projection, and the transformation with a stationarity loss on the recovered source. Gradients are not shared between the two, so the source-extraction step reduces to classical linear ICA and inherits its identifiability guarantee, while non-stationary distortion is absorbed by the transformation. The closed-form inverse of the transformation enables per-spike subtraction with a time-varying template during sequential peel-off. On a public benchmark of dynamic high-density EMG with ground-truth spike trains, the method outperforms four adaptive ICA baselines at every recall threshold, recovering more units at a higher accuracy.

cs.HC↗

arXiv2026

Neural Control and Learning of Simulated Hand Movements With an EMG-Based Closed-Loop Interface

The standard engineering approach when facing uncertainty is modelling. Mixing data from a well-calibrated model with real recordings has led to breakthroughs in many applications of AI, from computer vision to autonomous driving. This type of model-based data augmentation is now beginning to show promising results in biosignal processing as well. However, while these simulated data are necessary, they are not sufficient for virtual neurophysiological experiments. Simply generating neural signals that reproduce a predetermined motor behaviour does not capture the flexibility, variability, and causal structure required to probe neural mechanisms during control tasks. In this study, we present an in silico neuromechanical model that combines a fully forward musculoskeletal simulation, reinforcement learning, and sequential, online electromyography synthesis. This framework provides not only synchronised kinematics, dynamics, and corresponding neural activity, but also explicitly models feedback and feedforward control in a virtual participant. In this way, online control problems can be represented, as the simulated human adapts its behaviour via a learned RL policy in response to a neural interface. For example, the virtual user can learn hand movements robust to perturbations or the control of a virtual gesture decoder. We illustrate the approach using a gesturing task within a biomechanical hand model, and lay the groundwork for using this technique to evaluate neural controllers, augment training datasets, and generate synthetic data for neurological conditions.

q-bio.QM↗

arXiv2026

Agonist-Antagonist Neural Coordination without Mechanical Coupling after Targeted Muscle Reinnervation

Following limb amputation and targeted muscle reinnervation (TMR), nerves that originally innervated agonist and antagonist muscles are rerouted into one or more residual target muscles. This rerouting profoundly alters the natural mechanical coupling and afferent signalling that normally link muscle groups in intact limbs. Despite this disruption, in this study we demonstrate, using high-density intramuscular microelectrode arrays implanted in reinnervated muscles of three TMR participants, that motor units (MUs) associated with agonist and antagonist tasks remain functionally coupled. Specifically, over 40% of motor units active during agonist tasks were also recruited during the corresponding antagonist tasks, even though no visual feedback on antagonist neural activity was provided. These motor units exhibited significantly different firing rates depending on their functional role. These results provide the first motor-unit-level evidence that the central nervous system preserves coordinated agonist-antagonist control after TMR and inform restorative surgical strategies and prosthetic systems capable of regulating both limb kinematics and dynamics based on agonist-antagonist commands interplay.

q-bio.NC↗

arXiv2026

Quantifying Ergonomics in the Elevate Soft Robotic Suit

Soft robotic suits have the potential to rehabilitate, assist, and augment the human body. The low weight, cost, and minimal form-factor of these devices make them ideal for daily use by both healthy and impaired individuals. However, challenges associated with data-driven, user-specific, and comfort-first design of human-robot interfaces using soft materials limit their widespread translation and adoption. In this work, we present the quantitative evaluation of ergonomics and comfort of the Elevate suit - a cable driven soft robotic suit that assists shoulder elevation. Using a motion-capture system and force sensors, we measured the suit's ergonomics during assisted shoulder elevation up to 70 degrees. Two 4-hour sessions were conducted with one subject, involving transmitting cable tensions of up to 200N with no discomfort reported. We estimated that the pressure applied to the shoulder during assisted movements was within the range seen in a human grasp (approximately 69.1-85.1kPa), and estimated volumetric compression of <3% and <8% across the torso and upper arm, respectively. These results provide early validation of Elevate's ergonomic design in preparation for future studies with patient groups.

cs.RO↗

arXiv2025

Intuitive control of supernumerary robotic limbs through a tactile-encoded neural interface

Brain-computer interfaces (BCIs) promise to extend human movement capabilities by enabling direct neural control of supernumerary effectors, yet integrating augmented commands with multiple degrees of freedom without disrupting natural movement remains a key challenge. Here, we propose a tactile-encoded BCI that leverages sensory afferents through a novel tactile-evoked P300 paradigm, allowing intuitive and reliable decoding of supernumerary motor intentions even when superimposed with voluntary actions. The interface was evaluated in a multi-day experiment comprising of a single motor recognition task to validate baseline BCI performance and a dual task paradigm to assess the potential influence between the BCI and natural human movement. The brain interface achieved real-time and reliable decoding of four supernumerary degrees of freedom, with significant performance improvements after only three days of training. Importantly, after training, performance did not differ significantly between the single- and dual-BCI task conditions, and natural movement remained unimpaired during concurrent supernumerary control. Lastly, the interface was deployed in a movement augmentation task, demonstrating its ability to command two supernumerary robotic arms for functional assistance during bimanual tasks. These results establish a new neural interface paradigm for movement augmentation through stimulation of sensory afferents, expanding motor degrees of freedom without impairing natural movement.

cs.RO↗

arXiv2025

Intramuscular microelectrode arrays enable highly-accurate neural decoding of hand movements

Decoding the activity of the nervous system is a critical challenge in neuroscience and neural interfacing. In this study, we present a neuromuscular recording system that enables large-scale sampling of muscle activity using microelectrode arrays with over 100 channels embedded in forearm muscles. These arrays captured intramuscular high-density signals that were decoded into patterns of activation of spinal motoneurons. In two healthy participants, we recorded high-density intramuscular activity during single- and multi-digit contractions, revealing distinct motoneuron recruitment patterns specific to each task. Based on these patterns, we achieved perfect classification accuracy (100%) for 12 single- and multi-digit tasks and over 96% accuracy for up to 16 tasks, significantly outperforming state-of-the-art EMG classification methods. This intramuscular high-density system and classification method represent an advancement in neural interfacing, with the potential to improve human-computer interaction and the control of assistive technologies, particularly for replacing or restoring impaired motor function.

q-bio.NC↗

arXiv2025

Spiking Neural Network Decoders of Finger Forces from High-Density Intramuscular Microelectrode Arrays

Restoring naturalistic finger control in assistive technologies requires the continuous decoding of motor intent with high accuracy, efficiency, and robustness. Here, we present a spike-based decoding framework that integrates spiking neural networks (SNNs) with motor unit activity extracted from high-density intramuscular microelectrode arrays. We demonstrate simultaneous and proportional decoding of individual finger forces from motor unit spike trains during isometric contractions at 15% of maximum voluntary contraction using SNNs. We systematically evaluated alternative SNN decoder configurations and compared two possible input modalities: physiologically grounded motor unit spike trains and spike-encoded intramuscular EMG signals. Through this comparison, we quantified trade-offs between decoding accuracy, memory footprint, and robustness to input errors. The results showed that shallow SNNs can reliably decode finger-level motor intent with competitive accuracy and minimal latency, while operating with reduced memory requirements and without the need for external preprocessing buffers. This work provides a practical blueprint for integrating SNNs into finger-level force decoding systems, demonstrating how the choice of input representation can be strategically tailored to meet application-specific requirements for accuracy, robustness, and memory efficiency.

cs.HC↗

arXiv2025

Peripheral brain interfacing: Reading high-frequency brain signals from the output of the nervous system

Accurate and robust recording and decoding from the central nervous system (CNS) is essential for advances in human-machine interfacing. However, technologies used to directly measure CNS activity are limited by their resolution, sensitivity to interferences, and invasiveness. Advances in muscle recordings and deep learning allow us to decode the spiking activity of spinal motor neurons (MNs) in real time and with high accuracy. MNs represent the motor output layer of the CNS, receiving and sampling signals originating in different regions in the nervous system, and generating the neural commands that control muscles. The input signals to MNs can be estimated from the MN outputs. Here we argue that peripheral neural interfaces using muscle sensors represent a promising, non-invasive approach to estimate some neural activity from the CNS that reaches the MNs but does not directly modulate force production. We also discuss the evidence supporting this concept, and the necessary advances to consolidate and test MN-based CNS interfaces in controlled and real-world settings.

q-bio.NC↗

arXiv2025

Imitation Learning for Adaptive Control of a Virtual Soft Exoglove

The use of wearable robots has been widely adopted in rehabilitation training for patients with hand motor impairments. However, the uniqueness of patients' muscle loss is often overlooked. Leveraging reinforcement learning and a biologically accurate musculoskeletal model in simulation, we propose a customized wearable robotic controller that is able to address specific muscle deficits and to provide compensation for hand-object manipulation tasks. Video data of a same subject performing human grasping tasks is used to train a manipulation model through learning from demonstration. This manipulation model is subsequently fine-tuned to perform object-specific interaction tasks. The muscle forces in the musculoskeletal manipulation model are then weakened to simulate neurological motor impairments, which are later compensated by the actuation of a virtual wearable robotics glove. Results shows that integrating the virtual wearable robotic glove provides shared assistance to support the hand manipulator with weakened muscle forces. The learned exoglove controller achieved an average of 90.5\% of the original manipulation proficiency.

cs.RO↗

arXiv2025

Design and Preliminary Evaluation of a Torso Stabiliser for Individuals with Spinal Cord Injury

Spinal cord injuries generally result in sensory and mobility impairments, with torso instability being particularly debilitating. Existing torso stabilisers are often rigid and restrictive. We present an early investigation into a non-restrictive 1 degree-of-freedom (DoF) mechanical torso stabiliser inspired by devices such as centrifugal clutches and seat-belt mechanisms. First, the paper presents a motion-capture (MoCap) and OpenSim-based kinematic analysis of the cable-based system to understand the requisite device characteristics. The evaluation in simulation resulted in the cable-based device to require 55-60\,cm of unrestricted travel, and to lock at a threshold cable velocity of 80-100\,cm/s. Next, the developed 1-DoF device is introduced. The proposed mechanical device is transparent during activities of daily living, and transitions to compliant blocking when incipient fall is detected. Prototype behaviour was then validated using a MoCap-based kinematic analysis to verify non-restrictive movement, reliable transition to blocking, and compliance of the blocking.

cs.RO↗

arXiv2025

Switch-based Independent Antagonist Actuation with a Single Motor for a Soft Exosuit

The use of a cable-driven soft exosuit poses challenges with regards to the mechanical design of the actuation system, particularly when used for actuation along multiple degrees of freedom (DoF). The simplest general solution requires the use of two actuators to be capable of inducing movement along one DoF. However, this solution is not practical for the development of multi-joint exosuits. Reducing the number of actuators is a critical need in multi-DoF exosuits. We propose a switch-based mechanism to control an antagonist pair of cables such that it can actuate along any cable path geometry. The results showed that 298.24ms was needed for switching between cables. While this latency is relatively large, it can reduced in the future by a better choice of the motor used for actuation.

cs.RO↗

arXiv2025

Spatial Adaptation Layer: Interpretable Domain Adaptation For Biosignal Sensor Array Applications

Machine learning offers promising methods for processing signals recorded with wearable devices such as surface electromyography (sEMG) and electroencephalography (EEG). However, in these applications, despite high within-session performance, intersession performance is hindered by electrode shift, a known issue across modalities. Existing solutions often require large and expensive datasets and/or lack robustness and interpretability. Thus, we propose the Spatial Adaptation Layer (SAL), which can be applied to any biosignal array model and learns a parametrized affine transformation at the input between two recording sessions. We also introduce learnable baseline normalization (LBN) to reduce baseline fluctuations. Tested on two HD-sEMG gesture recognition datasets, SAL and LBN outperformed standard fine-tuning on regular arrays, achieving competitive performance even with a logistic regressor, with orders of magnitude less, physically interpretable parameters. Our ablation study showed that forearm circumferential translations account for the majority of performance improvements.

cs.LG↗

arXiv2025

Space Physiology and Technology: Musculoskeletal Adaptations, Countermeasures, and Opportunities for Wearable Systems

Space poses significant challenges for humans, leading to physiological adaptations in response to an environment vastly different from Earth. A comprehensive understanding of these physiological adaptations is needed to devise effective countermeasures to support human life in space. This narrative review first focuses on the impact of the environment in space on the musculoskeletal system. It highlights the complex interplay between bone and muscle adaptations and their implications on astronaut health. Despite advances in current countermeasures, such as resistive exercise and pharmacological interventions, they remain partially effective, bulky, and resource-intensive, posing challenges for future missions aboard compact spacecraft. This review proposes wearable sensing and robotic technology as a promising alternative to overcome these limitations. Wearable systems, such as sensor-integrated suits and (soft) exoskeletons, can provide real-time monitoring, dynamic loading, and exercise protocols tailored to individual needs. These systems are lightweight, modular, and capable of operating in confined environments, making them ideal for long-duration missions. In addition to space applications, wearable technologies hold significant promise for terrestrial uses, supporting rehabilitation and assistance for the ageing population, individuals with musculoskeletal disorders, and enhance physical performance in healthy users. By integrating advanced materials, sensors and actuators, and intelligent and energy-efficient control, these technologies can bridge gaps in current countermeasures while offering broader applications on Earth.

cs.RO↗

arXiv2024

Learning Cortico-Muscular Dependence through Orthonormal Decomposition of Density Ratios

The cortico-spinal neural pathway is fundamental for motor control and movement execution, and in humans it is typically studied using concurrent electroencephalography (EEG) and electromyography (EMG) recordings. However, current approaches for capturing high-level and contextual connectivity between these recordings have important limitations. Here, we present a novel application of statistical dependence estimators based on orthonormal decomposition of density ratios to model the relationship between cortical and muscle oscillations. Our method extends from traditional scalar-valued measures by learning eigenvalues, eigenfunctions, and projection spaces of density ratios from realizations of the signal, addressing the interpretability, scalability, and local temporal dependence of cortico-muscular connectivity. We experimentally demonstrate that eigenfunctions learned from cortico-muscular connectivity can accurately classify movements and subjects. Moreover, they reveal channel and temporal dependencies that confirm the activation of specific EEG channels during movement. Our code is available at https://github.com/bohu615/corticomuscular-eigen-encoder.

q-bio.NC↗

arXiv2024

Unlocking the Full Potential of High-Density Surface EMG: Novel Non-Invasive High-Yield Motor Unit Decomposition

The decomposition of high-density surface electromyography (HD-sEMG) signals into motor unit discharge patterns has become a powerful tool for investigating the neural control of movement, providing insights into motor neuron recruitment and discharge behavior. However, current algorithms, while very effective under certain conditions, face significant challenges in complex scenarios, as their accuracy and motor unit yield are highly dependent on anatomical differences among individuals. This can limit the number of decomposed motor units, particularly in challenging conditions. To address this issue, we recently introduced Swarm-Contrastive Decomposition (SCD), which dynamically adjusts the separation function based on the distribution of the data and prevents convergence to the same source. Initially applied to intramuscular EMG signals, SCD is here adapted for HD-sEMG signals. We demonstrated its ability to address key challenges faced by existing methods, particularly in identifying low-amplitude motor unit action potentials and effectively handling complex decomposition scenarios, like high-interference signals. We extensively validated SCD using simulated and experimental HD-sEMG recordings and compared it with current state-of-the-art decomposition methods under varying conditions, including different excitation levels, noise intensities, force profiles, sexes, and muscle groups. The proposed method consistently outperformed existing techniques in both the quantity of decoded motor units and the precision of their firing time identification. For instance, under certain experimental conditions, SCD detected more than three times as many motor units compared to previous methods, while also significantly improving accuracy. These advancements represent a major step forward in non-invasive EMG technology for studying motor unit activity in complex scenarios.

q-bio.NC↗