MétaCan
Menu
Back to cohort

Toward personalized human-in-the-loop training: Real-time estimation of individual motor learning dynamics using the dual-rate model

2025· article· en· W4414991488 on OpenAlexafffund
Arash Salemi, Amirhossein Afkhami Ardekani, Albert H. Vette, Milad Nazarahari

Bibliographic record

VenueComputers in Biology and Medicine · 2025
Typearticle
Languageen
FieldNeuroscience
TopicMotor Control and Adaptation
Canadian institutionsGlenrose Rehabilitation HospitalUniversity of Alberta HospitalUniversity of Alberta
FundersNatural Sciences and Engineering Research Council of CanadaAlberta InnovatesCanada Foundation for Innovation
KeywordsForgettingRobustness (evolution)Kalman filterOnline modelEstimation theoryProcess (computing)Monte Carlo methodSensitivity (control systems)Task (project management)

Abstract

fetched live from OpenAlex

Previous studies have shown that the dual-rate model, a stochastic framework comprising a multi-state slow-learning, slow-forgetting process and a single-state fast-learning, fast-forgetting process, can predict motor outputs in paradigms including spontaneous recovery and anterograde interference. However, existing methods for estimating the model's states and parameters, including the Expectation Maximization algorithm, operate offline and require the entire behavioural dataset. Furthermore, prior work has typically used average group performance, neglecting individual differences in learning and forgetting rates. Here, we have developed online system identification approaches using Joint Extended Kalman Filter (JEKF) and Moving Horizon Estimation (MHE) to estimate dual-rate model states and parameters in real-time while accounting for individual learning differences. We also introduced adaptive versions that dynamically adjust sensitivity based on motor output noise. For validation, we first used Monte Carlo simulations to demonstrate the accuracy and robustness of these frameworks across varying learning profiles, training schedules, and initial conditions. We then conducted a visuomotor adaptation experiment comprising well-established schedules: block, alternating, and random schedules. Our results confirm that JEKF and MHE can effectively obtain personalized models in real-time, achieving average parameter estimation errors below 11 % across all parameters and simulations. Notably, both methods captured how learning and forgetting rates evolved with task transitions and scheduling changes, trends that offline methods missed. Overall, JEKF is efficient for predictable schedules (e.g., block), whereas MHE, though more than two times slower due to its optimization, provides more reliable estimates in unpredictable environments, achieving up to 26 % lower parameter estimation errors and demonstrating no significant degradation under poor initialization. These findings highlight the potential of the proposed frameworks for real-time, personalized motor learning modelling and online decision-making.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.003
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.009
Threshold uncertainty score0.017

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.003
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.084
GPT teacher head0.349
Teacher spread0.265 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations1
Published2025
Admission routes2
Has abstractyes

Explore more

Same venueComputers in Biology and MedicineSame topicMotor Control and AdaptationFrench-language works237,207