Exploring Synergies in Brain-Machine Interfaces: Compression vs. Performance

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 3, 2025

Abstract Individuals with severe neurological injuries often rely on assistive technologies, but current methods have limitations in accurately decoding multi-degree-of-freedom (DoF) movements. Intracortical brain-machine interfaces (iBMIs) use neural signals to provide a more natural control method, currently struggle higher-DoF movements—something the brain handles effortlessly. It has been theorized that simplifies high-DoF movement through muscle synergies, which link multiple muscles function as single unit. These synergies studied using dimensionality reduction techniques like principal component analysis (PCA), non-negative matrix factorization (NMF), and demixed PCA (dPCA) successfully used reduce noise improve offline decoder stability non-invasive applications. However, their effectiveness improving generalizability for implanted recordings across varied tasks is unclear. Here, we evaluated if can enhance iBMI performance non-human primates performing two-DoF finger task. Specifically, tested PCA, dPCA, NMF could compress denoise data generalization tasks. Our results showed while all effectively compressed minimal loss accuracy, none improved denoising. Additionally, of enhanced findings suggest aid compression, alone it may not reveal “true” space needed or generalizability. Further research required determine whether are optimal framework alternative approaches robustness Significance Statement Many researchers believe represent fundamental strategy interface (BMI) performance. extracted techniques, thought simplify complex data, efficiency accuracy BMI systems. In our study, dexterous We found these high-dimensional they did denoising generalize well different contexts. Instead, highest was achieved when available suggesting although useful adaptability

Language: Английский

---

A flexible intracortical brain-computer interface for typing using finger movements

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: April 26, 2024

Keyboard typing with finger movements is a versatile digital interface for users diverse skills, needs, and preferences. Currently, such an does not exist people paralysis. We developed intracortical brain-computer (BCI) attempted flexion/extension of three groups on the right hand, or both hands, demonstrated its flexibility in two dominant paradigms. The first paradigm "point-and-click" typing, where BCI user selects one key at time using continuous real-time control, allowing selection arbitrary sequences symbols. During cued character this paradigm, human research participant paralysis achieved 30-40 selections per minute nearly 90% accuracy. second "keystroke" each by discrete movement without feedback, often giving faster speed natural language sentences. With 90 characters minute, decoding correcting errors model resulted more than Notably, paradigms matched state-of-the-art performance enabled further simultaneous multiple as well efficient decoder estimation across Overall, high-performance step towards wider accessibility technology addressing unmet needs flexibility.

Language: Английский

---

Unraveling EEG correlates of unimanual finger movements: insights from non-repetitive flexion and extension tasks

Journal of NeuroEngineering and Rehabilitation, Journal Year: 2024, Volume and Issue: 21(1)

Published: Dec. 26, 2024

The loss of finger control in individuals with neuromuscular disorders significantly impacts their quality life. Electroencephalography (EEG)-based brain-computer interfaces that actuate neuroprostheses directly via decoded motor intentions can help restore lost mobility. However, the extent to which movements exhibit distinct and decodable EEG correlates remains unresolved. This study aims investigate unimanual, non-repetitive flexion extension. Sixteen healthy, right-handed participants completed multiple sessions right-hand movement experiments. These included five individual (Thumb, Index, Middle, Ring, Pinky) four coordinated (Pinch, Point, ThumbsUp, Fist) flexions extensions, along a rest condition (None). High-density trajectories were simultaneously recorded analyzed. We examined low-frequency (0.3–3 Hz) time series movement-related cortical potentials (MRCPs), event-related desynchronization/synchronization (ERD/S) alpha- (8–13 beta (13–30 bands. A clustering approach based on Riemannian distances was used chart similarities between broadband responses (0.3–70 different scenarios. contribution state-of-the-art features identified across sub-bands, from low gamma (30–70 Hz), an ensemble pairwise classify single-trial rest. significant decrease amplitude observed contralateral frontal-central regions during Distinct MRCP patterns found pre-, ongoing-, post-movement stages. Additionally, strong ERD detected central brain both alpha bands extension, band showing stronger rebound (ERS) post-movement. Within repertoire, Thumb most distinctive, followed by Fist. Decoding results indicated time-domain better differentiates movements, while power detect versus Combining these yielded over 80% detection accuracy, classification accuracy exceeded 60% for other fingers. Our findings confirm whether or coordinated, be precisely EEG. differentiating specific is challenging due highly overlapping neural time, spectral, spatial domains. Nonetheless, certain such as those involving Thumb, responses, making them prime candidates dexterous neuroprostheses.

Language: Английский

---

Functional Electrical Stimulation and Brain-Machine Interfaces for Simultaneous Control of Wrist and Finger Flexion

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 12, 2024

Brain-machine interface (BMI) controlled functional electrical stimulation (FES) is a promising treatment to restore hand movements people with cervical spinal cord injury. Recent intracortical BMIs have shown unprecedented successes in decoding user intentions, however the restored by FES largely been limited predetermined grasps. Restoring dexterous will require continuous control of many biomechanically linked degrees-of-freedom hand, such as wrist and finger flexion, that would form basis those movements. Here we investigate ability simultaneous which enable grasping posture assist manipulating objects once grasped. We demonstrate intramuscular can monkeys temporarily paralyzed hands move their fingers across range motion, spanning an average 88.6 degrees at metacarpophalangeal joint flexion 71.3 both joints simultaneously real-time task. Additionally, monkey using BMI virtual before after paralyzed, even achieving success rates acquisition times equivalent able-bodied temporary paralysis two sessions. Together, this outlines method artificial brain-to-body could

Language: Английский

---

Few-shot Algorithms for Consistent Neural Decoding (FALCON) Benchmark

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 16, 2024

Abstract Intracortical brain-computer interfaces (iBCIs) can restore movement and communication abilities to individuals with paralysis by decoding their intended behavior from neural activity recorded an implanted device. While this yields high-performance over short timescales, data are often nonstationary, which lead decoder failure if not accounted for. To maintain performance, users must frequently recalibrate decoders, requires the arduous collection of new behavioral data. Aiming reduce burden, several approaches have been developed that either limit recalibration requirements (few-shot approaches) or eliminate explicit entirely (zero-shot approaches). However, progress is limited a lack standardized datasets comparison metrics, causing methods be compared in ad hoc manner. Here we introduce FALCON benchmark suite (Few-shot Algorithms for COnsistent Neural decoding) standardize evaluation iBCI robustness. curates five span tasks focus on behaviors interest modern-day iBCIs. Each dataset includes calibration data, optional few-shot private We implement flexible platform only user-submitted code return predictions unseen also seed applying baseline spanning classes possible approaches. aims provide rigorous selection criteria robust easing translation real-world devices. https://snel-repo.github.io/falcon/

Language: Английский

---

Motor imagery and execution activate similar finger representations that are spatially consistent over time

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 13, 2024

Abstract Finger representations in the sensorimotor cortex can be activated even absence of somatosensory input or motor output through mere top-down processes, such as imagery. While executed finger movements activate primary that are spatially consistent over time within participants, stability remains largely unexplored. Given increasing use to both plan implantation and control brain-computer interfaces, it is crucial understand these representations. Here, we investigated spatial consistency, thereby reliability, imagery time. To assess this, participants performed imagined individual two 3T fMRI sessions were ∼2 weeks apart. We observed highly univariate finger-selective activity clusters multivariate vertex-wise patterns execution task. Using a across-task decoding approach, further found similar cortex. This demonstrates used identify related movement execution. Our findings not only validate processes for interface planning control, but also open up new opportunities development training interventions do rely on overt movements.

Language: Английский

---