Journal of neural engineering最新文献

{"title":"Transcranial ultrasound stimulation modulates neural activity of paraventricular thalamus and prefrontal cortex in the propofol-anesthetized mice.","authors":"Guangying Cui, Yi Yuan, Qiaoxuan Wang, Li Zhao, Cheng Chi, Liqiang Zhao, Zhuo Liu","doi":"10.1088/1741-2552/ade28f","DOIUrl":"10.1088/1741-2552/ade28f","url":null,"abstract":"<p><p><i>Objective.</i>Transcranial ultrasound stimulation (TUS) has been reported to modulate neural activity and accelerate the recovery of consciousness (ROC) in the propofol-anesthetized mice. Both the thalamus and frontal cortex play critical roles in anesthetic-induced transition of consciousness (TOC).<i>Approach.</i>Twenty-one male BALB/c mice were randomly divided into the Sham group (<i>n</i>= 7), the TUS1 group (<i>n</i>= 7) and the TUS2 group (<i>n</i>= 7). The thalamus of mice in the two TUS groups were subjected to TUS before or after anesthesia, respectively. Local field potentials of paraventricular thalamus (PVT) and prefrontal cortex (PFC) were recorded using electrophysiological techniques. The relative change of mean absolute power and relative power in different frequency bands for each brain region were calculated and analyzed for correlation.<i>Main results.</i>Compared to the Sham group (33.14 ± 0.46 min), the time of ROC was shorter in both the TUS1 group (19.86 ± 0.59 min) and TUS2 group (17.86 ± 0.86 min). Besides, the results showed that TUS could directly induce neural activity in the PVT and indirectly in the PFC in the [60-100 Hz] frequency band. Furthermore, we also found that there were higher pearson correlation coefficients of neural activity between PVT and PFC in the [8-13 Hz] frequency band under TUS (<i>P</i>< 0.05).<i>Significance.</i>Both the PVT and PFC contribute to TOC in propofol-anesthetized mice, and they can be effectively modulated by TUS, which may provide a guidance for the modulation of consciousness in clinical anesthesia.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144259627","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":"Improving auditory attention decoding in noisy environments for listeners with hearing impairment through contrastive learning.","authors":"Gautam Sridhar, Sofía Boselli, Martin A Skoglund, Bo Bernhardsson, Emina Alickovic","doi":"10.1088/1741-2552/ade28a","DOIUrl":"10.1088/1741-2552/ade28a","url":null,"abstract":"<p><p><i>Objective</i>. This study aimed to investigate the potential of contrastive learning to improve auditory attention decoding (AAD) using electroencephalography (EEG) data in challenging cocktail-party scenarios with competing speech and background noise.<i>Approach</i>. Three different models were implemented for comparison: a baseline linear model (LM), a non-LM without contrastive learning (NLM), and a non-LM with contrastive learning (NLMwCL). The EEG data and speech envelopes were used to train these models. The NLMwCL model used SigLIP, a variant of CLIP loss, to embed the data. The speech envelopes were reconstructed from the models and compared with the attended and ignored speech envelopes to assess reconstruction accuracy, measured as the correlation between the reconstructed and actual speech envelopes. These reconstruction accuracies were then compared to classify attention. All models were evaluated in 34 listeners with hearing impairment.<i>Results</i>. The reconstruction accuracy for attended and ignored speech, along with attention classification accuracy, was calculated for each model across various time windows. The NLMwCL consistently outperformed the other models in both speech reconstruction and attention classification. For a 3-second time window, the NLMwCL model achieved a mean attended speech reconstruction accuracy of 0.105 and a mean attention classification accuracy of 68.0%, while the NLM model scored 0.096 and 64.4%, and the LM achieved 0.084 and 62.6%, respectively.<i>Significance</i>. These findings demonstrate the promise of contrastive learning in improving AAD and highlight the potential of EEG-based tools for clinical applications, and progress in hearing technology, particularly in the design of new neuro-steered signal processing algorithms.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144259623","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":"Evaluation of gold helical microwire structure electrode for long-term rodent nerve stimulation.","authors":"Danny V Lam, Kevin Yang, Derrick X Liu, Anna Lauricella, Yingyi Gao, Elizabeth S Fielding, Kyle Golobish, Stephan Nieuwoudt, Doug J Weber, Lee E Fisher, Scott F Lempka, Ashley N Dalrymple, Kip A Ludwig, Andrew J Shoffstall","doi":"10.1088/1741-2552/ade18a","DOIUrl":"10.1088/1741-2552/ade18a","url":null,"abstract":"<p><p><i>Objective.</i>The development of electrodes for chronic peripheral nerve stimulation faces several challenges, including complex compositions, intricate manufacturing processes, and high costs associated with the availability and fabrication of suitable materials. These limitations hinder the accessibility and feasibility of producing effective devices for chronic preclinical studies. This study evaluated the feasibility of a simple-to-manufacture gold helical microwire structure electrode (Au-HMSE) for peripheral nerve stimulation, electromyography (EMG) recording, and preliminary tissue response on the rat sciatic nerve.<i>Approach.</i>Manufactured electrodes were used for up to 8 weeks in rats for nerve stimulation and EMG recordings, with electrode-tissue impedances and motor thresholds measured to assess<i>in vivo</i>stability and feasibility. Evoked motor responses were measured via gastrocnemius muscle activity and ankle torque. Terminal histology was performed at 12 weeks to assess chronic tissue response to the implanted electrodes.<i>Main results.</i>Implanted electrodes with impedances <10 kΩ effectively evoked motor responses in monopolar and bipolar configurations and successfully recorded EMG activity. Gastrocnemius activation overlapped with off-target motor responses, likely due to the electrode's size relative to rat nerve anatomy and the absence of anchoring, which may have allowed migration. High impedance failure appeared related to interconnects between electrodes and tunneled leads and at solder joints in the stimulating and recording setup. Histology showed typical fibrotic encapsulation, with the helical design promoting tissue in-growth around the microwires, creating a high surface area electrode-tissue interface.<i>Significance.</i>This study evaluated the early feasibility of Au-HMSE for chronically implanted rodent nerve stimulation and EMG recordings. While gold electrodes are non-standard for chronic stimulation, the construction of these devices may be appropriate for the evaluation of chronic peripheral nerve stimulation in the preclinical setting due to their simple composition, manufacturing, and availability of gold microwire as a raw material. The findings provide valuable insights for developing future implantable leads used for peripheral nerve stimulation.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12175216/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144236304","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":"Identifying and predicting EEG microstates with sequence-to-sequence deep learning models for online applications.","authors":"Qinglin Zhao, Kunbo Cui, Lixin Zhang, Zhongqing Wu, Hua Jiang, Mingqi Zhao, Bin Hu","doi":"10.1088/1741-2552/ade1f8","DOIUrl":"10.1088/1741-2552/ade1f8","url":null,"abstract":"<p><p><i>Objective.</i>Electroencephalographic (EEG) microstates, as a non-invasive and high-temporal-resolution tool for analyzing time-space features of brain activity, have been validated and applied in various research domains. However, current methods for EEG microstate analysis rely on clustering algorithms, which require large-scale offline computations to obtain microstate labels and cluster centers. This offline approach is no longer sufficient for applications in cross-subject, cross-dataset, and multi-task scenarios.<i>Approach.</i>To address these limitations, we propose, for the first time, a novel sequence-to-sequence-based framework for microstate identification and prediction, enabling end-to-end online recognition and prediction from EEG signals to microstate labels. Specifically, we introduce a method for constructing training datasets for online identification and prediction, which includes microstate label calibration, EEG electrode mapping, and sequence data partitioning. We validate this approach using four different neural network models with varying computational mechanisms on two public datasets.<i>Main results.</i>Our results demonstrate that EEG microstates can be identified and predicted by trainable models. In cross-subject microstate recognition tasks, the recognition accuracy for four typical microstates reached up to 74.26%, outperforming k-nearest neighbor (KNN) by 21.91%. For seven typical microstates, the recognition accuracy peaked at 66.76%, surpassing KNN by 26.6%. In prediction tasks, the accuracy for four and seven typical microstates reached 70.49% and 62.71%, respectively.<i>Significance.</i>Our work advances EEG microstate analysis from an offline clustering-based paradigm to an online model-data hybrid computation paradigm, providing new insights and references for cross-subject and cross-dataset applications of EEG microstates.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144251628","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":"Prioritized learning of cross-population neural dynamics.","authors":"Trisha Jha, Omid G Sani, Bijan Pesaran, Maryam M Shanechi","doi":"10.1088/1741-2552/ade569","DOIUrl":"https://doi.org/10.1088/1741-2552/ade569","url":null,"abstract":"<p><strong>Objective: </strong>Improvements in recording technology for multi-region simultaneous recordings enable the study of interactions among distinct brain regions. However, a major computational challenge in studying cross-regional, or cross-population dynamics in general, is that the cross-population dynamics can be confounded or masked by within-population dynamics.</p><p><strong>Approach: </strong>Here, we propose cross-population prioritized linear dynamical modeling (CroP-LDM) to tackle this challenge. CroP-LDM learns the cross-population dynamics in terms of a set of latent states using a prioritized learning approach, such that they are not confounded by within-population dynamics. Further, CroP-LDM can infer the latent states both causally in time using only past neural activity and non-causally in time, unlike some prior dynamic methods whose inference is non-causal.</p><p><strong>Results: </strong>First, through comparisons with various LDM methods, we show that the prioritized learning objective in CroP-LDM is key for accurate learning of cross-population dynamics. Second, using multi-regional bilateral motor and premotor cortical recording during a naturalistic movement task, we demonstrate that CroP-LDM better learns cross-population dynamics compared to recent static and dynamic methods, even when using a low dimensionality. Finally, we demonstrate how CroP-LDM can quantify dominant interaction pathways across brain regions in an interpretable manner.</p><p><strong>Significance: </strong>Overall, these results show that our approach can be a useful framework for addressing challenges associated with modeling dynamics across brain regions.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144319039","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":"Neurophysiological correlates of user engagement in mixed reality exergames.","authors":"F Garro, E Fenoglio, M Laffranchi, N Garcia-Hernandez, M Semprini","doi":"10.1088/1741-2552/addae7","DOIUrl":"10.1088/1741-2552/addae7","url":null,"abstract":"<p><p><i>Objective.</i>This study investigates the neurophysiological correlates of user engagement (UE) during upper-limb exercises in mixed reality (MR)-based exergames. It explores whether MR environments modulate brain activity differently than traditional exercises and whether physical object interaction affects engagement.<i>Methods.</i>High-density electroencephalography (EEG) was recorded from fifteen healthy adults performing bilateral arm exercises under four conditions-with and without MR and physical object interaction. Engagement indices were derived from spectral features (theta, alpha, and their ratios) at both source- and sensor-levels across predefined cortical regions. Time-course dynamics and subjective user experience were also evaluated.<i>Main results.</i>MR-based exergames significantly increased theta power and decreased alpha power compared to non-MR conditions, indicating greater cognitive and attentional engagement. These effects were consistent across frontal, sensorimotor, and parietal regions and remained stable over time. Physical object interaction had no significant effect on engagement. Subjectively, MR conditions were rated higher in stimulation, efficiency, and novelty.<i>Significance.</i>The effectiveness of MR in rehabilitation depends on sustained UE, which is typically assessed through subjective questionnaires. This study demonstrates that EEG-derived metrics-particularly theta and alpha activity-objectively reflect engagement. These results support EEG as a real-time monitoring tool for developing adaptive, brain-responsive rehabilitation technologies.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144113185","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":"Failure modes and mitigations for Bayesian optimization of neuromodulation parameters.","authors":"Evan M Dastin-van Rijn, Alik S Widge","doi":"10.1088/1741-2552/ade189","DOIUrl":"10.1088/1741-2552/ade189","url":null,"abstract":"<p><p><i>Objective.</i>Precision medicine holds substantial promise for tailoring neuromodulation techniques to the symptomatology of individual patients. Precise selection of stimulation parameters for individual patients requires the development of robust optimization techniques. However, standard optimization approaches, like Bayesian optimization, have historically been assessed and developed for applications with far less noise than is typical in neuro-psychiatric outcome measures and with minimal focus on parameter safety.<i>Approach.</i>We conducted a literature review of individual effects in neurological and psychiatric applications to build a series of simulated patient responses of varying signal to noise ratio. Using these simulations, we assessed whether existing standards in Bayesian optimization are sufficient for robustly optimizing such effects.<i>Main results.</i>For effect sizes below a Cohen's d of 0.3, standard Bayesian optimization methods failed to consistently identify optimal parameters. This failure primarily results from over-sampling of the boundaries of the space as the number of samples increases, because the variance on the edges becomes disproportionately greater than in the remainder of parameter space. Using a combination of an input warp and a boundary avoiding Iterated Brownian-bridge kernel we demonstrated robust Bayesian optimization performance for problems with a Cohen's d effect size as low as 0.1.<i>Significance.</i>Our results demonstrate that caution should be taken when applying standard Bayesian optimization in neuromodulation applications with potentially low effect sizes, as standard algorithms are at high risk of converging to local rather than global optima. Mitigating techniques, like boundary avoidance, are effective and should be used to improve robustness.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12164532/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144236305","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":"Artificial neural networks for magnetoencephalography: a review of an emerging field.","authors":"Arthur Dehgan, Hamza Abdelhedi, Vanessa Hadid, Irina Rish, Karim Jerbi","doi":"10.1088/1741-2552/addd4a","DOIUrl":"10.1088/1741-2552/addd4a","url":null,"abstract":"<p><p><i>Objective</i>. Magnetoencephalography (MEG) is a cutting-edge neuroimaging technique that measures the intricate brain dynamics underlying cognitive processes with an unparalleled combination of high temporal and spatial precision. While MEG data analytics have traditionally relied on advanced signal processing and mathematical and statistical tools, the recent surge in artificial intelligence has led to the growing use of machine learning (ML) methods for MEG data classification. An emerging trend in this field is the use of artificial neural networks (ANNs) to address various MEG-related tasks. This review aims to provide a comprehensive overview of the state of the art in this area.<i>Approach</i>. This topical review included studies that applied ANNs to MEG data. Studies were sourced from PubMed, Google Scholar, arXiv, and bioRxiv using targeted search queries. The included studies were categorized into three groups: 'Classification', 'Modeling', and 'Other'. Key findings and trends were summarized to provide a comprehensive assessment of the field.<i>Main results</i>. We identified 119 relevant studies, with 70 focused on 'Classification', 16 on 'Modeling', and 33 in the 'Other' category. 'Classification' studies addressed tasks such as brain decoding, clinical diagnostics, and brain-computer interfaces implementations, often achieving high predictive accuracy. 'Modeling' studies explored the alignment between ANN activations and brain processes, offering insights into the neural representations captured by these networks. The 'Other' category demonstrated innovative uses of ANNs for artifact correction, preprocessing, and neural source localization.<i>Significance</i>. By establishing a detailed portrait of the current state of the field, this review highlights the strengths and current limitations of ANNs in MEG research. It also provides practical recommendations for future work, offering a helpful reference for seasoned researchers and newcomers interested in using ANNs to explore the complex dynamics of the human brain with MEG.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144164368","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":"Stimulus predictability has little impact on decoding of covert visual spatial attention.","authors":"Paul Schmid, Catherine M Sweeney-Reed, Stefan Dürschmid, Christoph Reichert","doi":"10.1088/1741-2552/addf81","DOIUrl":"10.1088/1741-2552/addf81","url":null,"abstract":"<p><p><i>Objective</i>. Brain-computer interfaces (BCI) that are aimed at supporting completely locked-in patients require independence from eye movements. Since visual spatial attention (VSA) shifts precede eye movements, they can be used for non-invasive, gaze-independent BCI control. In VSA tasks, stimuli locations and presentation onsets are commonly unpredictable. In this study we investigated the impact of predictability of potential target stimuli on the decoding accuracy of a BCI.<i>Approac</i>h. We presented visual stimuli simultaneously to the left and right visual fields while participants shifted attention to a target stimulus. Using canonical correlation analysis, we decoded the direction of attention under different combinations of temporal and spatial predictability and compared the performance.<i>Main results</i>. We found no variation in decoding accuracies with spatial predictability. In addition, jittered timing did not alter the decoding accuracy compared to a constant stimulus onset asynchrony (SOA). Finally, reducing the SOA enabled faster BCI communication without accuracy loss. Using time-resolved decoding and interpretable models, we show that a later positive difference wave (between 300 ms and 350 ms post-stimulus onset) at occipital sites, rather than the N2pc, primarily contributes to decoding the target receiving attention.<i>Significance</i>. Our results demonstrate that stimulus predictability has no beneficial impact on decoding accuracy, but the paradigm proved robust to alterations in various stimulus parameters, making VSA a promising cognitive process for use in non-invasive, gaze-independent BCI-based communication.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144210576","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":"POC-CSP: a novel parameterised and orthogonally-constrained neural network layer for learning common spatial patterns (CSP) in EEG signals.","authors":"Andi Partovi, David B Grayden, Anthony N Burkitt","doi":"10.1088/1741-2552/add8bc","DOIUrl":"10.1088/1741-2552/add8bc","url":null,"abstract":"<p><p><i>Objective</i>. Common spatial patterns (CSPs) has been established as a powerful feature extraction method in EEG signal processing with machine learning, but it has shortcomings including sensitivity to noise and rigidity in the value of the weights. Our goal was to transform CSP into a trainable machine learning model that can learn from data, be regularized, and be integrated into end-to-end classification networks.<i>Approach</i>. We developed a novel parameterised and orthogonally-constrained neural network layer for learning CSPs (POC-CSP) that maintains CSP's mathematical properties while allowing trainable weights. The layer uses parameterisation based on Lie Group theory to convert constrained optimisation into unconstrained optimisation, enabling integration with standard neural network (NN) training methods. We evaluated the approach on two public motor imagery datasets, focusing on both subject-specific and multi-subject paradigms.<i>Main results</i>. POC-CSP outperformed both conventional CSP and existing NN implementations in subject-specific classification tasks. In a novel multi-subject paradigm, POC-CSP achieved superior generalisation. When fine-tuned with just 50% of a new subject's data, POC-CSP achieved 0.95 average accuracy across subjects, substantially outperforming subject-specific models trained with more data.<i>Significance</i>. These findings demonstrate that combining CSP's proven effectiveness with NNs' flexibility can significantly improve EEG signal processing performance. The ability to generalize across subjects and achieve high accuracy with minimal subject-specific training data makes POC-CSP particularly valuable for practical brain-computer interface applications, where collecting large amounts of training data from each new user is often impractical or unfeasible.</p>","PeriodicalId":94096,"journal":{"name":"Journal of neural engineering","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144083012","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}