arXiv subjects

Elisa Donati

Publications and source records attributed to Elisa Donati.

At least 19 recordsLinked to original sources

arXiv2026

Neuromorphic Spiking Ring Attractor for Proprioceptive Joint-State Estimation

Maintaining stable internal representations of continuous variables is fundamental for effective robotic control. Continuous attractor networks provide a biologically inspired mechanism for encoding such variables, yet neuromorphic realizations have rarely addressed proprioceptive estimation under resource constraints. This work introduces a spiking ring-attractor network representing a robot joint angle through self-sustaining population activity. Local excitation and broad inhibition support a stable activity bump, while velocity-modulated asymmetries drive its translation and boundary conditions confine motion within mechanical limits. The network reproduces smooth trajectory tracking and remains stable near joint limits, showing reduced drift and improved accuracy compared to unbounded models. Such compact hardware-compatible implementation preserves multi-second stability demonstrating a near-linear relationship between bump velocity and synaptic modulation.

cs.RO↗

arXiv2026

Lightweight Test-Time Adaptation for EMG-Based Gesture Recognition

Reliable long-term decoding of gestures from surface electromyography (EMG) is hindered by signal drift caused by electrode displacement, muscle fatigue, and/or posture changes. Although modern models achieve high intra-session accuracy, their performance often degrades substantially across recording sessions. Existing approaches to mitigate this problem typically rely on large training datasets or computationally intensive pipelines that are unsuitable for energy-efficient wearable devices. We propose a lightweight test-time adaptation framework for EMG decoding. The framework includes three complementary adaptation strategies: (i) causal adaptive batch normalization for online statistical alignment, (ii) Gaussian Mixture Model alignment with experience replay to mitigate forgetting, and (iii) meta-learning for rapid few-shot calibration. We evaluate these methods on the multi-session NinaPro DB6 dataset. All approaches substantially improve inter-session robustness relative to a non-adaptive baseline while maintaining low computational overhead. Replay-regularized statistical alignment provides the most stable adaptation under limited data, while meta-learning achieves the highest accuracy when sparse calibration labels are available. Overall, our self-supervised test-time adaptation methods reach up to 82% inter-session accuracy, significantly improving upon prior approaches while maintaining resource-efficient operation. These results demonstrate that lightweight test-time adaptation can enable robust, long-term EMG decoding for wearable or prosthetic applications.

cs.LG↗

arXiv2025

Neuromorphic Deployment of Spiking Neural Networks for Cognitive Load Classification in Air Traffic Control

This paper presents a neuromorphic system for cognitive load classification in a real-world setting, an Air Traffic Control (ATC) task, using a hardware implementation of Spiking Neural Networks (SNNs). Electroencephalogram (EEG) and eye-tracking features, extracted from an open-source dataset, were used to train and evaluate both conventional machine learning models and SNNs. Among the SNN architectures explored, a minimalistic, single-layer model trained with a biologically inspired delta-rule learning algorithm achieved competitive performance (80.6%). To enable deployment on neuromorphic hardware, the model was quantized and implemented on the mixed-signal DYNAP-SE chip. Despite hardware constraints and analog variability, the chip-deployed SNN maintained a classification accuracy of up to 73.5% using spike-based input. These results demonstrate the feasibility of event-driven neuromorphic systems for ultra-low-power, embedded cognitive state monitoring in dynamic real-world scenarios.

cs.NE↗

arXiv2025

EEG-Based Cognitive Load Classification During Landmark-Based VR Navigation

Brain computer interfaces enable real-time monitoring of cognitive load, but their effectiveness in dynamic navigation contexts is not well established. Using an existing VR navigation dataset, we examined whether EEG signals can classify cognitive load during map-based wayfinding and whether classification accuracy depends more on task complexity or on individual traits. EEG recordings from forty-six participants navigating routes with 3, 5, or 7 map landmarks were analyzed with a nested cross-validation framework across multiple machine learning models. Classification achieved mean accuracies up to 90.8% for binary contrasts (3 vs. 7 landmarks) and 78.7% for the three-class problem, both well above chance. Demographic and cognitive variables (age, gender, spatial ability, working memory) showed no significant influence. These findings demonstrate that task demands outweigh individual differences in shaping classification performance, highlighting the potential for task-adaptive navigation systems that dynamically adjust map complexity in response to real-time cognitive states.

cs.HC↗

arXiv2025

Queen Detection in Beehives via Environmental Sensor Fusion for Low-Power Edge Computing

Queen bee presence is essential for the health and stability of honeybee colonies, yet current monitoring methods rely on manual inspections that are labor-intensive, disruptive, and impractical for large-scale beekeeping. While recent audio-based approaches have shown promise, they often require high power consumption, complex preprocessing, and are susceptible to ambient noise. To overcome these limitations, we propose a lightweight, multimodal system for queen detection based on environmental sensor fusion-specifically, temperature, humidity, and pressure differentials between the inside and outside of the hive. Our approach employs quantized decision tree inference on a commercial STM32 microcontroller, enabling real-time, low-power edge computing without compromising accuracy. We show that our system achieves over 99% queen detection accuracy using only environmental inputs, with audio features offering no significant performance gain. This work presents a scalable and sustainable solution for non-invasive hive monitoring, paving the way for autonomous, precision beekeeping using off-the-shelf, energy-efficient hardware.

cs.LG↗

arXiv2025

Spiking Neural Networks for Mental Workload Classification with a Multimodal Approach

Accurately assessing mental workload is crucial in cognitive neuroscience, human-computer interaction, and real-time monitoring, as cognitive load fluctuations affect performance and decision-making. While Electroencephalography (EEG) based machine learning (ML) models can be used to this end, their high computational cost hinders embedded real-time applications. Hardware implementations of spiking neural networks (SNNs) offer a promising alternative for low-power, fast, event-driven processing. This study compares hardware compatible SNN models with various traditional ML ones, using an open-source multimodal dataset. Our results show that multimodal integration improves accuracy, with SNN performance comparable to the ML one, demonstrating their potential for real-time implementations of cognitive load detection. These findings position event-based processing as a promising solution for low-latency, energy efficient workload monitoring in adaptive closed-loop embedded devices that dynamically regulate cognitive load.

cs.NE↗

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

Finger Force Decoding from Motor Units Activity on Neuromorphic Hardware

Accurate finger force estimation is critical for next-generation human-machine interfaces. Traditional electromyography (EMG)-based decoding methods using deep learning require large datasets and high computational resources, limiting their use in real-time, embedded systems. Here, we propose a novel approach that performs finger force regression using spike trains from individual motor neurons, extracted from high-density EMG. These biologically grounded signals drive a spiking neural network implemented on a mixed-signal neuromorphic processor. Unlike prior work that encodes EMG into events, our method exploits spike timing on motor units to perform low-power, real-time inference. This is the first demonstration of motor neuron-based continuous regression computed directly on neuromorphic hardware. Our results confirm accurate finger-specific force prediction with minimal energy use, opening new possibilities for embedded decoding in prosthetics and wearable neurotechnology.

cs.NE↗

arXiv2025

A Realistic Simulation Framework for Analog/Digital Neuromorphic Architectures

Developing dedicated mixed-signal neuromorphic computing systems optimized for real-time sensory-processing in extreme edge-computing applications requires time-consuming design, fabrication, and deployment of full-custom neuromorphic processors. To ensure that initial prototyping efforts, exploring the properties of different network architectures and parameter settings, lead to realistic results, it is important to use simulation frameworks that match as best as possible the properties of the final hardware. This is particularly challenging for neuromorphic hardware platforms made using mixed-signal analog/digital circuits, due to the variability and noise sensitivity of their components. In this paper, we address this challenge by developing a software spiking neural network simulator explicitly designed to account for the properties of mixed-signal neuromorphic circuits, including device mismatch variability. The simulator, called ARCANA (A Realistic Simulation Framework for Analog/Digital Neuromorphic Architectures), is designed to reproduce the dynamics of mixed-signal synapse and neuron electronic circuits with autogradient differentiation for parameter optimization and GPU acceleration. We demonstrate the effectiveness of this approach by matching software simulation results with measurements made from an existing neuromorphic processor. We show how the results obtained provide a reliable estimate of the behavior of the spiking neural network trained in software, once deployed in hardware. This framework enables the development and innovation of new learning rules and processing architectures in neuromorphic embedded systems.

cs.NE↗

arXiv2025

Event-Driven Implementation of a Physical Reservoir Computing Framework for superficial EMG-based Gesture Recognition

Wearable health devices have a strong demand in real-time biomedical signal processing. However traditional methods often require data transmission to centralized processing unit with substantial computational resources after collecting it from edge devices. Neuromorphic computing is an emerging field that seeks to design specialized hardware for computing systems inspired by the structure, function, and dynamics of the human brain, offering significant advantages in latency and power consumption. This paper explores a novel neuromorphic implementation approach for gesture recognition by extracting spatiotemporal spiking information from surface electromyography (sEMG) data in an event-driven manner. At the same time, the network was designed by implementing a simple-structured and hardware-friendly Physical Reservoir Computing (PRC) framework called Rotating Neuron Reservoir (RNR) within the domain of Spiking neural network (SNN). The spiking RNR (sRNR) is promising to pipeline an innovative solution to compact embedded wearable systems, enabling low-latency, real-time processing directly at the sensor level. The proposed system was validated by an open-access large-scale sEMG database and achieved an average classification accuracy of 74.6\% and 80.3\% using a classical machine learning classifier and a delta learning rule algorithm respectively. While the delta learning rule could be fully spiking and implementable on neuromorphic chips, the proposed gesture recognition system demonstrates the potential for near-sensor low-latency processing.

eess.SP↗

arXiv2025

Heterogeneous Population Encoding for Multi-joint Regression using sEMG Signals

Regression-based decoding of continuous movements is essential for human-machine interfaces (HMIs), such as prosthetic control. This study explores a feature-based approach to encoding Surface Electromyography (sEMG) signals, focusing on the role of variability in neural-inspired population encoding. By employing heterogeneous populations of Leaky Integrate-and- Fire (LIF) neurons with varying sizes and diverse parameter distributions, we investigate how population size and variability in encoding parameters, such as membrane time constants and thresholds, influence decoding performance. Using a simple linear readout, we demonstrate that variability improves robustness and generalizability compared to single-neuron encoders. These findings emphasize the importance of optimizing variability and population size for efficient and scalable regression tasks in spiking neural networks (SNNs), paving the way for robust, low-power HMI implementations.

cs.HC↗

arXiv2024

Neuromorphic Heart Rate Monitors: Neural State Machines for Monotonic Change Detection

Detecting monotonic changes in heart rate (HR) is crucial for early identification of cardiac conditions and health management. This is particularly important for dementia patients, where HR trends can signal stress or agitation. Developing wearable technologies that can perform always-on monitoring of HRs is essential to effectively detect slow changes over extended periods of time. However, designing compact electronic circuits that can monitor and process bio-signals continuously, and that can operate in a low-power regime to ensure long-lasting performance, is still an open challenge. Neuromorphic technology offers an energy-efficient solution for real-time health monitoring. We propose a neuromorphic implementation of a Neural State Machine (NSM) network to encode different health states and switch between them based on the input stimuli. Our focus is on detecting monotonic state switches in electrocardiogram data to identify progressive HR increases. This innovative approach promises significant advancements in continuous health monitoring and management.

cs.ET↗

arXiv2024

Evaluation of Encoding Schemes on Ubiquitous Sensor Signal for Spiking Neural Network

Spiking neural networks (SNNs), a brain-inspired computing paradigm, are emerging for their inference performance, particularly in terms of energy efficiency and latency attributed to the plasticity in signal processing. To deploy SNNs in ubiquitous computing systems, signal encoding of sensors is crucial for achieving high accuracy and robustness. Using inertial sensor readings for gym activity recognition as a case study, this work comprehensively evaluates four main encoding schemes and deploys the corresponding SNN on the neuromorphic processor Loihi2 for post-deployment encoding assessment. Rate encoding, time-to-first-spike encoding, binary encoding, and delta modulation are evaluated using metrics like average fire rate, signal-to-noise ratio, classification accuracy, robustness, and inference latency and energy. In this case study, the time-to-first-spike encoding required the lowest firing rate (2%) and achieved a comparative accuracy (89%), although it was the least robust scheme against error spikes (over 20% accuracy drop with 0.1 noisy spike rate). Rate encoding with optimal value-to-probability mapping achieved the highest accuracy (91.7%). Binary encoding provided a balance between information reconstruction and noise resistance. Multi-threshold delta modulation showed the best robustness, with only a 0.7% accuracy drop at a 0.1 noisy spike rate. This work serves researchers in selecting the best encoding scheme for SNN-based ubiquitous sensor signal processing, tailored to specific performance requirements.

eess.SP↗

arXiv2023

Feed-forward and recurrent inhibition for compressing and classifying high dynamic range biosignals in spiking neural network architectures

Neuromorphic processors that implement Spiking Neural Networks (SNNs) using mixed-signal analog/digital circuits represent a promising technology for closed-loop real-time processing of biosignals. As in biology, to minimize power consumption, the silicon neurons' circuits are configured to fire with a limited dynamic range and with maximum firing rates restricted to a few tens or hundreds of Herz. However, biosignals can have a very large dynamic range, so encoding them into spikes without saturating the neuron outputs represents an open challenge. In this work, we present a biologically-inspired strategy for compressing this high-dynamic range in SNN architectures, using three adaptation mechanisms ubiquitous in the brain: spike-frequency adaptation at the single neuron level, feed-forward inhibitory connections from neurons belonging to the input layer, and Excitatory-Inhibitory (E-I) balance via recurrent inhibition among neurons in the output layer. We apply this strategy to input biosignals encoded using both an asynchronous delta modulation method and an energy-based pulse-frequency modulation method. We validate this approach in silico, simulating a simple network applied to a gesture classification task from surface EMG recordings.

eess.SP↗

arXiv2023

Long-term stable Electromyography classification using Canonical Correlation Analysis

Discrimination of hand gestures based on the decoding of surface electromyography (sEMG) signals is a well-establish approach for controlling prosthetic devices and for Human-Machine Interfaces (HMI). However, despite the promising results achieved by this approach in well-controlled experimental conditions, its deployment in long-term real-world application scenarios is still hindered by several challenges. One of the most critical challenges is maintaining high EMG data classification performance across multiple days without retraining the decoding system. The drop in performance is mostly due to the high EMG variability caused by electrodes shift, muscle artifacts, fatigue, user adaptation, or skin-electrode interfacing issues. Here we propose a novel statistical method based on canonical correlation analysis (CCA) that stabilizes EMG classification performance across multiple days for long-term control of prosthetic devices. We show how CCA can dramatically decrease the performance drop of standard classifiers observed across days, by maximizing the correlation among multiple-day acquisition data sets. Our results show how the performance of a classifier trained on EMG data acquired only of the first day of the experiment maintains 90% relative accuracy across multiple days, compensating for the EMG data variability that occurs over long-term periods, using the CCA transformation on data obtained from a small number of gestures. This approach eliminates the need for large data sets and multiple or periodic training sessions, which currently hamper the usability of conventional pattern recognition based approaches

cs.LG↗

arXiv2022

Neuromorphic implementation of ECG anomaly detection using delay chains

Real-time analysis and classification of bio-signals measured using wearable devices is computationally costly and requires dedicated low-power hardware. One promising approach is to use spiking neural networks implemented using in-memory computing architectures and neuromorphic electronic circuits. However, as these circuits process data in streaming mode without the possibility of storing it in external buffers, a major challenge lies in the processing of spatio-temporal signals that last longer than the time constants present in the network synapses and neurons. Here we propose to extend the memory capacity of a spiking neural network by using parallel delay chains. We show that it is possible to map temporal signals of multiple seconds into spiking activity distributed across multiple neurons which have time constants of few milliseconds. We validate this approach on an ECG anomaly detection task and present experimental results that demonstrate how temporal information is properly preserved in the network activity.

eess.SP↗

arXiv2022

Organic log-domain integrator synapse

Synapses play a critical role in memory, learning, and cognition. Their main functions include converting pre-synaptic voltage spikes to post-synaptic currents, as well as scaling the input signal. Several brain-inspired architectures have been proposed to emulate the behavior of biological synapses. While these are useful to explore the properties of nervous systems, the challenge of making biocompatible and flexible circuits with biologically plausible time constants and tunable gain remains. Here, a physically flexible organic log-domain integrator synaptic circuit is shown to address this challenge. In particular, the circuit is fabricated using organic-based materials that are electrically active, offer flexibility and biocompatibility, as well as time constants (critical in learning neural codes and encoding spatiotemporal patterns) that are biologically plausible. Using a 10 nF synaptic capacitor, the time constant reached 126 ms and 221 ms before and during bending, respectively. The flexible synaptic circuit is characterized before and during bending, followed by studies on the effects of weighting voltage, synaptic capacitance, and disparity in pre-synaptic signals on the time constant.

eess.SP↗