Journal of neural engineering最新文献

{"title":"Deep brain stimulation-induced local evoked potentials outperform spectral features in spatial and clinical STN mapping.","authors":"Enrico Opri, Faical Isbaine, Seyyed Bahram Borgheai, Emily Bence, Roohollah Jafari Deligani, Jon T Willie, Robert E Gross, Nicholas Au Yong, Svjetlana Miocinovic","doi":"10.1088/1741-2552/adf99f","DOIUrl":"10.1088/1741-2552/adf99f","url":null,"abstract":"<p><p><i>Objective.</i>Deep brain stimulation (DBS) of the subthalamic nucleus (STN) is an established therapy for Parkinson's disease (PD). Yet, optimizing lead placement and stimulation programming remains challenging. Current techniques rely on imaging and intraoperative microelectrode recordings (MER), while programming relies on trial-and-error clinical testing, which can be time-consuming. DBS-induced local evoked potentials (DLEP), also known as evoked resonant neural activity, have emerged as a potential alternative electrophysiological marker for mapping. However, direct comparisons with traditional spectral features, such as beta-band, high-frequency oscillations (HFOs), and aperiodic component are lacking.<i>Approach.</i>We evaluated DLEP across 39 STN DBS leads in 31 subjects with PD undergoing DBS surgery, using both a single-pulse and high-frequency (HF) burst stimulation paradigms. We developed a novel artifact-removal method to enable monopolar DLEP recovery, including estimating the DLEP amplitudes at stimulated contacts, further enhancing spatial sampling of DLEP. We evaluated spectral features and DLEP in respect to imaging-based and MER-based localization, and its predictive power for post-operative programming.<i>Main results.</i>DLEP showed great spatial consistency, maximizing within STN with 100% accuracy for single-pulse and 84.62% for burst stimulation, surpassing spectral measures including beta (89.74%) and HFO (82.05%). DLEP better correlated with clinical outcomes (single-pulses<i>ρ</i>= -0.33, HF bursts<i>ρ</i>= -0.26), than spectral measures (beta<i>ρ</i>= -0.25, HFO<i>ρ</i>= 0.05). Furthermore, single-pulses at low-frequencies are sufficient for DLEP-based mapping.<i>Significance.</i>We show how DLEP provide higher STN-spatial specificity and correlation with postoperative programming compared to spectral features. To support clinical translation of DLEP, we developed two methods aimed to recover artifact-free DLEP and estimating DLEP amplitudes at stimulating contacts. DLEP appear distinct from beta and HFO activity, yet strongly tied to aperiodic spectral components, suggesting that DLEP amplitude reflects underlying STN excitability. This study highlights that DLEP are a robust and clinically valuable marker for DBS targeting and programming.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12395123/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144805526","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Towards a closed loop retinal prosthesis: measuring electrically evoked retinal responses using large electrodes.","authors":"Martin J Spencer, Suzanne Hosie, Wei Tong, Mohit N Shivdasani, David J Garrett, Sorel E De León, Emma K Brunton, Tatiana Kameneva, David B Grayden, James B Fallon, Michael R Ibbotson, Anthony N Burkitt, Hamish Meffin","doi":"10.1088/1741-2552/adfc9b","DOIUrl":"10.1088/1741-2552/adfc9b","url":null,"abstract":"<p><p><i>Objective.</i>Sensory prostheses use arrays of electrodes to stimulate neural tissue and restore a sense of vision or hearing. At perceptible levels of stimulation, the current from each electrode spreads and causes overlapping regions of neural activation. This lack of specificity results in perceptual deficits. Methods to overcome this reduced specificity, such as a closed loop stimulation approach require measurement of the neural response to stimulation. This investigation tests the possibility of using the large stimulating electrodes such as those required by some subretinal or suprachoroidal retinal implants to measure the neural response to stimulation, an approach similar to Evoked Compound Action Potentials measurements used in cochlear implants.<i>Approach. Ex vivo</i>tissue samples from Long Evans rats with healthy retinas and Royal College of Surgeon rats with retinal degeneration were used to investigate both stimulating and recording from electrodes of the same array. A hexagonal array was used with 20 platinum electrodes with 500<i>μ</i>m diameter and 700<i>μ</i>m pitch. Post-stimulus voltage decay was reduced with appropriate tuning of a triphasic stimulation pulse and in post-analysis with a high-pass filter. A method using alternating polarities of biphasic pulses was also trialed. A cocktail of synaptic and ion channel blockers was used to block all neural response including action potentials and thus confirm the biological origin of the signal.<i>Main Results.</i>It was found that a neural signal was observable on electrode that were sufficiently distant from the stimulating electrodes. The signal appeared to be due to direct activation of ganglion cells or possibly mediated via inner retinal neurons.<i>Significance.</i>This result confirms that recording usable neural signals from large electrodes is possible, which is an essential step in implementing a closed loop stimulation strategy for a subretinal or suprachoroidal retinal prosthesis.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144877646","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Computational analysis of optogenetic inhibition of CA1 neurons using a data-efficient and interpretable potassium and chloride conducting opsin model.","authors":"Laila Weyn, Thomas Tarnaud, Ruben Schoeters, Xavier De Becker, Wout Joseph, Robrecht Raedt, Emmeric Tanghe","doi":"10.1088/1741-2552/adf94a","DOIUrl":"10.1088/1741-2552/adf94a","url":null,"abstract":"<p><p><i>Objective.</i>Optogenetic inhibition of excitatory neuronal populations has emerged as a potential strategy for the treatment of refractory epilepsy. However, achieving effective seizure suppression in animal models using optogenetic techniques has proven challenging. This difficulty can be attributed to a suboptimal stimulation method that involves numerous complex variables. This study aims to examine how various stimulation parameters and opsin characteristics influence the efficacy of optogenetic inhibition protocols. Additionally, a new opsin model is introduced that permits easy implementation of the experimentally derived parameters describing the opsin's opening and closing dynamics.<i>Approach.</i>The mathematical description of a chloride and potassium conducting opsin was combined with a conductance-based model of a pyramidal CA1 neuron. Simulations with varying parameters were conducted to explore the effects of the stimulation paradigm and the neuronal environment on inhibition. A simplified, adaptable opsin model was used to test the robustness of these results and explore the impact of variations in opsin characteristics.<i>Main results.</i>Stronger inhibition was achieved with higher illumination intensities, pulse repetition frequencies, and duty cycles. Potassium conducting opsins were found to be more stable than chloride conducting ones. These findings were independent of the opsin's parameters. Additionally, changes in the opsin's dynamics had negligible impact when the opening and closing time constants were varied by factors between 0.5 and 2.<i>Significance.</i>This study provides key insights into the stimulation and physiological parameters that affect optogenetic inhibition. The findings highlight the importance of choosing the right stimulation protocol and opsin for optimizing optogenetic strategies. The newly developed opsin model also offers a new, valuable tool that will facilitate future research into the development of an improved optogenetic modulation protocol for seizure suppression.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144801357","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cross-person decomposition of surface electromyogram for efficient motor unit activity predictions.","authors":"Long Meng, Xiaogang Hu","doi":"10.1088/1741-2552/adfc99","DOIUrl":"10.1088/1741-2552/adfc99","url":null,"abstract":"<p><p><i>Objective.</i>Accurate prediction of motor unit (MU) discharge activity from surface electromyogram (sEMG) signals is critical for understanding neuromuscular control and for enabling practical neural interface applications. However, current MU decomposition approaches rely on person-specific data, limiting their generalizability.<i>Approach.</i>We developed a cross-person decomposition framework and validated the algorithm using synthesized high-density sEMG data by convoluting simulated MU firing spike trains with action potential templates derived from human experimental data. We first obtained separation matrix from multiple training subjects and applied them to decompose sEMG signals from unseen test subjects. This allowed us to obtain MU spike trains. The predicted outcomes were then compared with the ground truth across multiple metrics, including spike detection accuracy, MU firing rate (FR), waveform similarity of MU action potentials (MUAPs), and MU recruitment thresholds.<i>Main results</i>. Our results demonstrated strong agreement between predicted and true MU activity. Specifically, we found highR2values (⩾0.95) for the populational FR, and the coefficient of variation of FR remained stable across different MU retention thresholds. The MU similarity analyzes revealed that the predicted MUAPs closely matched ground truth counterparts both in waveform shape and spatial distribution. Furthermore, recruitment thresholds exhibited strong linear relation (R2=  0.98 ± 0.006) with minimal error.<i>Significance</i>. These findings demonstrate the feasibility of efficient cross-person MU decomposition with minimal accuracy loss, laying the groundwork for generalized, plug-and-play myoelectric systems in neurophysiology, neuroprosthetic, and rehabilitation applications.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144877644","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Novel gait phases recognition framework leveraging the temporal structure of the myoelectric activity.","authors":"Rami Mobarak, Alessandro Mengarelli, Rami N Khushaba, Ali H Al-Timemy, Erik C Prinsen, Federica Verdini, Ruud A Leijendekkers, Sandro Fioretti, Laura Burattini, Andrea Tigrini","doi":"10.1088/1741-2552/adfc9a","DOIUrl":"10.1088/1741-2552/adfc9a","url":null,"abstract":"<p><p><i>Objective</i>. Reliable control of lower limb prostheses during gait using surface electromyography requires robust decoding of myoelectric signals to ensure safety and efficiency. Conventional myoelectric pattern recognition (PR) methods, which classify features extracted from each window, often yield inaccurate and unstable output, limiting their practical use.<i>Approach</i>. To deal with these issues, two novel temporal myoelectric-based gait phase recognition frameworks are presented. Temporal activation profile (TAP) considers a sequence of features extracted from consecutive windows, and dual activation shots (DAS) using features extracted from the current and a specific preceding window. These methods were tested on (1) publicly available SIAT-LLMD dataset of 40 healthy subjects under different locomotion conditions, and (2) two subjects with transfemoral amputation during normal walking.<i>Main results</i>. TAP and DAS significantly outperformed conventional PR methods, achieving accuracies of 88.50% and 87.97%, respectively, in healthy subjects during normal walking. TAP achieved optimal performance using features extracted from consecutive windows spanning 240 ms in the past, whereas DAS performed best when leveraging features from the current window combined with those from a window 160 ms prior. No significant differences were observed between TAP and DAS under optimal conditions. Both approaches effectively enhanced gait phase recognition performance when applied to transfemoral amputee gait data. The TAP framework achieved the highest performance, surpassing 87.80% accuracy with extended temporal context requirement, and outperforming the DAS approach (82.32%) under pathological conditions.<i>Significance</i>. Both TAP and DAS are robust solutions for gait phase recognition as they stabilize the decision output and reduce classification errors. DAS is more practically feasible due to lower temporal and computational demands, while TAP is more effective in the case of altered neuromuscular activation patterns. The findings of this paper highlight the potential of integrating these methods into real-time prosthetic controllers, ensuring safe and reliable use for patients.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144877645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimized AI-based neural decoding from BOLD fMRI signal for analyzing visual and semantic ROIs in the human visual system.","authors":"Lorenzo Veronese, Andrea Moglia, Nicolò Pecco, Pasquale Anthony Della Rosa, Paola Scifo, Luca Mainardi, Pietro Cerveri","doi":"10.1088/1741-2552/adfbc2","DOIUrl":"10.1088/1741-2552/adfbc2","url":null,"abstract":"<p><p><i>Objective</i>. AI-based neural decoding reconstructs visual perception by leveraging generative models to map brain activity measured through functional magnetic resonance imaging (fMRI) into the observed visual stimulus.<i>Approach</i>. Traditionally, ridge linear models transform fMRI into a latent space, which is then decoded using variational autoencoders (VAE) or LDMs. Owing to the complexity and noisiness of fMRI data, newer approaches split the reconstruction into two sequential stages, the first one providing a rough visual approximation using a VAE, the second one incorporating semantic information through the adoption of LDM guided by contrastive language-image pre-training (CLIP) embeddings. This work addressed some key scientific and technical gaps of the two-stage neural decoding by: (1) implementing a gated recurrent unit-based architecture to establish a non-linear mapping between the fMRI signal and the VAE latent space, (2) optimizing the dimensionality of the VAE latent space, (3) systematically evaluating the contribution of the first reconstruction stage, and (4) analyzing the impact of different brain regions of interest (ROIs) on reconstruction quality.<i>Main results</i>. Experiments on the NSD, containing 73 000 unique natural images, along with fMRI of eight subjects, demonstrated that the proposed architecture maintained competitive performance while reducing the complexity of its first stage by 85%. The sensitivity analysis showcased that the first reconstruction stage is essential for preserving high structural similarity in the final reconstructions. Restricting analysis to semantic ROIs, while excluding early visual areas, diminished visual coherence, preserving semantics though. The inter-subject repeatability across ROIs was about 92% and 98% for visual and sematic metrics, respectively.<i>Significance</i>. This study represents a key step toward optimized neural decoding architectures leveraging non-linear models for stimulus prediction. Sensitivity analysis highlighted the interplay between the two reconstruction stages, while ROI-based analysis provided strong evidence that the two-stage AI model reflects the brain's hierarchical processing of visual information.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144857288","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"1.5 GHz non-invasive directional deep brain stimulation with improved focus size and minimized input power.","authors":"Chen Xue, Alex M H Wong","doi":"10.1088/1741-2552/adfab4","DOIUrl":"10.1088/1741-2552/adfab4","url":null,"abstract":"<p><p><i>Objective.</i>Temporal interference stimulation (TIS) has recently been introduced for non-invasive deep brain stimulation (NDBS). While numerous studies have highlighted its advantages over conventional technologies, TIS still encounters challenges such as limited resolution and a lack of validation using human-like models. This article introduces an innovative method for NDBS which alleviates the resolution limit.<i>Approach.</i>We utilize as our excitation a 1.5 GHz microwave carrier modulated by a 10 Hz envelope. The microwave carrier enables strong electromagnetic focusing while the envelope triggers neural activity. To form this excitation, two dipole antenna arrays are placed around the head for the generation of<i>y</i>- and<i>z</i>-directed electric fields (<i>E</i>-field). Current excitations to the antenna arrays are tuned to control (i) the<i>E</i>-field to the desired focality position and (ii) its direction at the focality position. Full-wave simulations with a realistic head model are conducted to demonstrate the method.<i>Main results.</i>In the deep brain region, the cross-sectional focality sizes (75% threshold) are 0.73 cm², 1.18 cm²and 2.45 cm²in the<i>XOY, YOZ</i>and<i>XOZ</i>planes, respectively. The focality is much smaller than previously reported in the conventional method with kHz carrier waves. Further, the<i>E</i>-field direction at the focality can be steered along the<i>yz</i>-plane by adjusting the excitation weights of the antenna arrays. Multiphysics simulations on temperature distribution and specific absorption rate (SAR) show that the maximum temperature increase within a 30-minute stimulation session is 0.76 °C and the maximum SAR_1gis 2.70 W kg^-1. Both measures are within commonly accepted safe operation ranges.<i>Significance.</i>Compared to conventional TIS methods that utilize kHz carrier signals, our proposed approach achieves drastically improved spatial resolution and enables precise steering of the<i>E</i>-field. The proposed work holds significant potential for clinical applications, offering enhanced resolution and reduced input power for NDBS.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144839435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Differential modulation of trunk muscle activation using thoracic epidural spinal stimulation.","authors":"Sydney M Schadan, Alexander G Steele, Amir H Faraji, Albert H Vette, Dimitry G Sayenko","doi":"10.1088/1741-2552/adf9a0","DOIUrl":"10.1088/1741-2552/adf9a0","url":null,"abstract":"<p><p><i>Objective</i>. Epidural spinal stimulation (ESS) has demonstrated promising functional improvements in trunk control following spinal cord injury (SCI). However, previous ESS studies targeting trunk muscle activation have been limited to stimulation over the eleventh thoracic to first lumbar vertebral levels, which may not be optimal based on anatomical evidence regarding trunk muscle innervation. In this light, the objective of this study was to investigate trunk muscle activity in response to ESS at varying stimulation locations above the thoracic spine.<i>Approach.</i>An electrode array was implanted above the thoracic spine of 13 participants. ESS-evoked responses in trunk muscles were quantified while stimulation location along the rostrocaudal and mediolateral axes of the spine was systematically manipulated.<i>Main results.</i>Ipsilateral ESS between the T6 and T10 vertebrae induced responses in all trunk muscles, resulting in average motor thresholds (MTs) and latencies of abdominal muscles ranging from 1.5 to 2.0<i>µ</i>C and 7.4 to 9.2 ms, respectively; however, stimulation between the T8 and T10 vertebrae demonstrated lower MTs and shorter latencies. Ipsilateral stimulation resulted in 2.4 times greater maximum response amplitudes, 30% lower MTs, and 0.9 ms shorter latencies compared to contralateral stimulation.<i>Significance</i>. Our study provides quantitative evidence on the differential effects of ESS amplitude and location on trunk muscle activity while also suggesting that both afferent and efferent pathways contribute to ESS-evoked muscle activation. The results enhance our fundamental understanding of ESS-induced trunk muscle activity and have the potential to guide electrode placement for future therapeutic or restorative applications toward improving trunk control following SCI.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144805527","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multifractal spatiotemporal dynamics in human epileptiform stereoelectroencephalography recordings.","authors":"Neha Sara John, Juan C Bulacio, Andreas V Alexopoulos, William Bingaman, Imad Najm, Balu Krishnan, Demitre Serletis","doi":"10.1088/1741-2552/adf66a","DOIUrl":"10.1088/1741-2552/adf66a","url":null,"abstract":"<p><p><i>Objective.</i>Multifractal formalism introduces an invaluable framework for the investigation of nonlinear, scale-invariant features across multiple time scales in non-stationary time series data.<i>Approach.</i>In this context, we sought to explore multifractal features defining spatiotemporal correlations in seizure activity, by applying multifractal detrended fluctuation analysis (MFDFA) to stereoelectroencephalography (sEEG) recordings from five patients with refractory, focal temporal epilepsy, who underwent subsequent surgical removal of the temporal lobe and achieved seizure freedom.<i>Main results.</i>To the best of our knowledge, we are the first to report evidence for a multifractal architecture underscoring sEEG-recorded epileptiform signals<i>in vivo</i>, suggesting a fundamental propensity for scale-invariance in electrophysiological human brain recordings. Importantly, dynamical MFDFA-derived features captured altered spatiotemporal trends through the pre-ictal, ictal and post-ictal states, and also across anatomical brain regions. Larger fluctuations (deviations) in these metrics were observed to varying extents across resected temporal lobe structures, as compared to more constrained dynamics in non-resected networks.<i>Significance.</i>MFDFA-derived metrics were statistically analyzed and found to capture unique features from the sEEG data, with temporal variations across anatomical brain networks offering a potentially useful tool for the visualization, quantification and interpretation of network involvement in the onset and evolution of seizure activity. These results underscore the importance of investigating high-complexity dynamics in intracranial sEEG recordings and their potential utility towards surgical decision-making in patients with medically intractable epilepsy.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144762877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MyoPose: position-limb-robust neuromechanical features for enhanced hand gesture recognition in colocated sEMG-pFMG armbands.","authors":"Rami Mobarak, Shen Zhang, Hao Zhou, Alessandro Mengarelli, Federica Verdini, Laura Burattini, Andrea Tigrini, Gursel Alici","doi":"10.1088/1741-2552/adf888","DOIUrl":"10.1088/1741-2552/adf888","url":null,"abstract":"<p><p><i>Objective</i>. Surface electromyography (sEMG) and pressure-based force myography (pFMG) are two complementary modalities adopted in hand gesture recognition due to their ability to capture muscle electrical and mechanical activity, respectively. While sEMG carries rich neural information about the intended gestures and has long been established as the primary control signal in myoelectric interfaces, pFMG has recently emerged as a stable modality that is less sensitive to sweat and can indicate motion onset earlier than sEMG, making their fusion promising for robust pattern recognition. However, gesture classification systems based on these signals often suffer from performance degradation due to limb position changes, which affect signal characteristics.<i>Approach</i>. To address this, we introduce MyoPose, a novel and lightweight spatial synergy-based feature set for enhancing neuromechanical control. MyoPose works on effectively decoding colocated sEMG-pFMG information to improve hand gesture recognition under limb position variability while remaining computationally efficient for resource-constrained hardware.<i>Main results</i>. The proposed MyoPose feature combined with linear discriminant analysis, achieved 87.7% accuracy (ACC) in a nine-hand gesture recognition task, outperforming standard myoelectric feature sets and comparable to a state-of-the-art decision-level multimodal fusion parallel convolutional neural network. Notably, MyoPose maintained computational efficiency, achieving real-time feasibility with an estimated controller delay of 110.62 ms, well within the operational requirement of 100-125 ms, as well as ultra-light memory requirement of 0.011 KB.<i>Significance</i>. The novelty of this study lies in providing an effective feature set for multimodal driven hand gesture recognition, handling limb position variations with robust ACC, and showing potential for real-time feasibility for human-machine interfaces without the need for deep learning.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144796552","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}