Is User Calibration Still Necessary for Continuous Myoelectric Control? A Closed-Loop Comparison of Calibration-Free Controllers

Amir Reza Hariri; Kevin B. Englehart; Erik Scheme

eess.SPOct 17, 2026

Is User Calibration Still Necessary for Continuous Myoelectric Control? A Closed-Loop Comparison of Calibration-Free Controllers

Authors: Amir Reza Hariri, Kevin B. Englehart, Erik Scheme

Organizations: Institute of Biomedical Engineering and the Department of Electrical and Computer Engineering, University of New Brunswick, Fredericton, NB E3B 5A3, Canada.

Abstract

The need for user-specific calibration remains an often-cited barrier to widespread adoption of myoelectric control. Cross-user models trained on large multi-user datasets can now recognize gestures from unseen users without calibration, but they have been evaluated almost exclusively offline, leaving open whether calibration is still needed in closed-loop control. This study compared six calibration-free controllers, trained on 306 users of the EMG-EPN-612 dataset and used without any calibration data from the test participant, against three calibrated controllers in a closed-loop Fitts' law target-acquisition task with sixteen participants. The calibrated controllers achieved higher offline balanced accuracy (90.6% against 73.1% for the best controller of each paradigm), but completion rates did not differ significantly between paradigms, and the highest completion rate was achieved by a calibration-free controller. Calibrated controllers moved faster on successful acquisitions, partly because of their individually fitted speed mappings, though not significantly after correction for multiple comparisons. However, every calibration-free controller produced more direct and stable trajectories than every calibrated controller, even after adjusting for cursor speed. Offline accuracy did not predict completion rate across controllers or within participants, and across paradigms higher offline accuracy was associated with poorer trajectory quality in 15 of 16 participants. Without any calibration data from the end user, a model trained across a large population matched calibrated control in completion rate and exceeded it in trajectory quality. The offline accuracy gained through calibration should therefore not be taken as evidence of a closed-loop benefit.

Figures & tables

Panel of Figure 1 — Fig. 1: Overview of the study design. Calibration-free controllers were trained only on EMG-EPN-612, whereas calibrated controllers also used five screen-guided repetitions from each participant. All nine controllers were then evaluated by each participant, in randomized order, in a common closed-loop Fitts’ law task.

Fig. 2: Fitts’ law task layout, with the three difficulty conditions overlaid. Each condition is a ring of twelve targets around a central start point, with larger targets at shorter distances in the easy condition and smaller targets at longer distances in the hard condition. Shaded circles show example targets. A target was acquired by holding the cursor inside it for 0.75 s.

Condition	$W$ (px)	$A$ (px)	ID (bits)
Easy	60	600	3.46
Medium	42	750	4.24
Hard	24	900	5.27

TABLE I: Fitts’ law target-acquisition difficulty conditions.

A

denotes movement amplitude and

W

denotes target width.

Model	Balanced Accuracy (%)
Base	$71.3\pm 12.1$
Proto	$71.1\pm 12.1$
RestLoss	$71.2\pm 11.6$
Triplet	$73.1\pm 12.0$
RunNorm	$59.9\pm 4.4$
Segmented	$72.7\pm 11.7$

TABLE II: Offline performance of the models evaluated in the online study. Cross-user models were trained on EMG-EPN-612 and evaluated zero-shot using each participant’s held-out screen-guided training repetition. Calibrated models were trained or fine-tuned using participant-specific calibration data. Values are mean

\pm

standard deviation across the sixteen participants. All controllers, including Segmented, were scored on the same unsegmented repetition.

Model	CR (%)	MT (s)	MT P (s)	TP (b/s)	TP P (b/s)
Base	$65.1\pm 26.8$	$4.16\pm 0.87$	$5.25\pm 1.45$	$1.13\pm 0.35$	$1.01\pm 0.39$
Proto	$68.1\pm 26.2$	$4.17\pm 0.82$	$5.16\pm 1.39$	$1.11\pm 0.35$	$1.01\pm 0.39$
RestLoss	$70.8\pm 23.8$	$4.04\pm 0.85$	$4.96\pm 1.39$	$1.18\pm 0.36$	$1.07\pm 0.38$
Triplet	$71.0\pm 26.2$	$4.00\pm 0.74$	$4.96\pm 1.41$	$1.17\pm 0.34$	$1.06\pm 0.40$
RunNorm	$69.4\pm 23.1$	$4.06\pm 0.88$	$5.05\pm 1.35$	$1.18\pm 0.36$	$1.06\pm 0.40$
Segmented	$72.7\pm 25.5$	$4.32\pm 0.90$	$5.06\pm 1.39$	$1.12\pm 0.35$	$1.04\pm 0.38$

TABLE III: Online outcome metrics, reported as mean

\pm

standard deviation across the sixteen participants. Completion rate (CR) measures reliability, while movement time (MT) and throughput (TP) summarize speed and information transfer. Throughput is nominal throughput, and penalized metrics (subscript

P

) include failed acquisitions.

Model	Easy	Medium	Hard
Base	81.8	68.2	45.3
Proto	86.5	67.7	50.0
RestLoss	88.5	75.0	49.0
Triplet	88.0	68.8	56.2
RunNorm	83.3	75.0	50.0
Segmented	85.9	76.0	56.2

TABLE IV: Completion rate (%) by Fitts’ law difficulty condition. Values are averaged across the sixteen participants.

Fig. 3: Trajectories are from the median participant (rank 9 of 16) when participants were ranked by mean completion rate across all nine models. FT-5 (left) had the highest offline accuracy of the calibrated controllers, and Segmented (right) had the highest completion rate of the calibration-free controllers.

Model	Path Eff.	Dir. Ratio	Over.	Stop Dist.
Base	63.8	2.99	0.57	10.3
Proto	63.1	3.17	0.53	11.6
RestLoss	64.6	3.03	0.42	6.7
Triplet	66.2	2.70	0.44	7.7
RunNorm	65.0	2.86	0.37	6.1
Segmented	64.2	2.90	0.44	9.0

TABLE V: Trajectory-quality metrics. Higher path efficiency is better, while lower values are preferred for the remaining metrics.

Fig. 4: Path efficiency of each controller. Every calibration-free controller produced more direct trajectories than every calibrated controller, despite requiring no user-specific training. The other three trajectory-quality measures followed a similar pattern and are reported in Table V .

	Completion Rate			Quality Composite			Pen. Movement Time
Intervention	Diff.	$r_{rb}$	$p$	Diff.	$r_{rb}$	$p$	Diff.	$r_{rb}$	$p$
Segmented	$+7.6$	$0.59$	$0.18$	$+0.17$	$0.47$	$0.31$	$-0.19$	$-0.37$	$0.63$
Triplet	$+5.9$	$0.71$	$0.078$	$+0.28$	$0.60$	$0.13$	$-0.29$	$-0.79$	$0.017$
RestLoss	$+5.7$	$0.68$	$0.10$	$+0.23$	$0.68$	$0.078$	$-0.29$	$-0.57$	$0.18$
RunNorm	$+4.3$	$0.22$	$0.46$	$+0.33$	$0.47$	$0.31$	$-0.20$	$-0.37$	$0.63$
Proto	$+3.0$	$0.37$	$0.44$	$-0.04$	$-0.25$	$0.40$	$-0.09$	$-0.15$	$0.63$

TABLE VI: Family A contrasts comparing each calibration-free intervention against Base across the sixteen participants. Positive differences favour the intervention for completion rate and the quality composite; negative differences favour it for penalized movement time.

r_{rb}

: matched-pairs rank-biserial correlation.

p

-values are Holm–Bonferroni corrected within each outcome.

Metric	Diff.	$r_{rb}$	$d_{z}$	$p$	Holm $p$
Quality Composite	$+0.79$	$1.00$	$1.33$	$<0.001$	$<0.01$
Completion Rate (%)	$+1.8$	$-0.09$	$0.10$	$0.76$	$0.81$
Movement Time (s)	$+0.15$	$0.66$	$0.62$	$0.018$	$0.090$
MT Pen. (s)	$+0.06$	$0.32$	$0.10$	$0.27$	$0.81$
Throughput Eff. (b/s)	$-0.02$	$-0.32$	$-0.22$	$0.27$	$0.81$
Throughput Nom. Pen. (b/s)	$-0.05$	$-0.60$	$-0.43$	$0.034$	$0.136$

TABLE VII: Calibration-free versus calibrated control across the sixteen participants. Differences are calibration-free minus calibrated. Higher is better for completion rate, quality composite, and throughput; lower is better for movement time.

r_{rb}

: matched-pairs rank-biserial correlation;

d_{z}

: Cohen’s

d_{z}

. Holm

p

applies the Holm–Bonferroni correction across the six contrasts of Family B. For completion rate, the positive Diff. and negative

r_{rb}

reflect right-skewed paired differences.

Fig. 5: Proportional-control speed commands for FT-5 and Segmented, over all frames on which an active class was predicted. Left: distribution of the speed output $s$ before the paradigm velocity multiplier was applied, shown as a histogram normalized to unit area with a logarithmic vertical axis. FT-5 produced high outputs more often and reached full speed ( $s=1$ ) on 2.4% of frames, against 0.04% for Segmented. Right: mean speed command after the multiplier ( $\mu\cdot s$ , as a fraction of full speed) for each participant, with grey lines joining each participant’s values for the two controllers and the group mean in black. The multiplier applied to the calibration-free controllers ( $\mu=1.2$ ) raised Segmented’s mean command from 0.156 to 0.187, halving the gap to FT-5 (0.217) without closing it.

Fig. 6: Offline balanced accuracy against (a) online completion rate and (b) the trajectory-quality composite. Small markers are individual participant-by-controller cells, and large labelled markers are controller means. All controllers, including Segmented, were scored offline on the same unsegmented held-out repetition. Offline accuracy did not predict completion rate, and across paradigms the more accurate calibrated controllers produced poorer trajectories.

Continuous Control

Continuous control studies how agents choose real-valued actions to steer dynamic systems toward goals while meeting performance and safety constraints.

See all 55 papers

Jul 30, 2026

A Montage-Agnostic Encoder for Calibration-Light Cross-User Gesture Recognition from Surface Electromyography

Pattern-recognition control promises a myoelectric prosthesis that responds to many intended gestures rather than one or two, but the promise has stayed in the laboratory. A recogniser trained on one person rarely transfers to the next, and useful performance usually demands a fresh round of labelled calibration from the end user. A montage-agnostic encoder is introduced that reads each electrode with shared weights and locates it by its physical coordinate rather than its index, so one architecture ingests any channel count without montage-specific parameters. Trained across users, it exceeds a per-user Hudgins and linear-discriminant classifier by 0.234 macro-F1 on DB1 for every held-out subject and by 0.108 on DB2, and falls below it on the ten-subject DB5. Each of the encoder's three key components individually accounts for more than half of its 3-shot macro F1 in an otherwise budget-matched ablation study. A controlled subject-count sweep shows the margin is close to flat from nine training subjects to thirty-nine, so the training pool binds only as a stability floor below which cross-user training fails to converge; what tracks the direction of the comparison across the three databases is instead the strength of the per-user baseline, which signal fidelity sets. Comparing against an LDA baseline depends on budget spent training models and on how good that baseline is, and self-supervised pretraining had no benefits once a supervised model was adequately trained.

Jethro Odeyemi, W. J. Zhang

Division of Biomedical Engineering, University of Saskatchewan, 57 Campus Drive, Saskatoon, SK, S7N 5A9, Canada

EMG-Based Gesture Recognition Few-Shot Learning Invariant Representation Learning Surface Electromyography

Ask PDF

Jul 30, 2026

Recognition and Label-Free Adaptation Across Recording Sessions in Surface-EMG Gesture Decoding

Recognition accuracy obtained during a recording session does not persist when a user puts on the electrodes again after the electrodes had previously been removed. The electrodes may have moved slightly, the skin may be drier or wetter, or the elbow may be positioned differently; these factors all contribute to day-to-day variability and therefore represent a major obstacle to implementing successful pattern-recognition based myoelectric control systems in daily practice. However, simply recalibrating a user's hand for 20 min at every doff/don event is a clearly unrealistic expectation. A montage-agnostic encoder built for cross-user, cross-montage transfer is trained here using data collected during a particular recording session, and then applied to data collected later in a different recording session without adjusting anything, on the ten intact subjects of NinaPro DB6. The performance of this approach is compared to that of a per-user LDA classification pipeline, and to that of two published approaches that only rely on source data collected from the same recording session. Carried unchanged across recording sessions, the encoder retains 0.688 macro-F1 against 0.540 for the per-user pipeline, and, on the per-window metric the published baselines use, sits above both published source-only results, a band of two points that locates the encoder rather than ranking it. Of five label-free test-time adaptations, only feature-statistic alignment improves every subject; batch-normalisation re-estimation, a standard method in the domain-adaptation literature, collapses this architecture entirely. Aligning the encoder's feature statistics to the new session recovers about what a single labelled calibration repetition would.

Jethro Odeyemi, W. J. Zhang

Division of Biomedical Engineering, University of Saskatchewan, 57 Campus Drive, Saskatoon, SK, S7N 5A9, Canada

EMG-Based Gesture Recognition Test-Time Adaptation Domain Adaptation Representation Alignment Surface Electromyography

Ask PDF

Sep 28, 2026

Separating personal from population gains when calibrating EEG foundation models for new users

Foundation models are increasingly adapted to individual users, but an apparent personalization gain can simply reflect a stronger population model. This distinction matters for brain-computer interfaces, where every new user must be calibrated. We evaluated personal adaptation of three frozen EEG foundation models (CBraMod, REVE and LaBraM) in 235 held-out subjects from three motor-imagery datasets, comparing each subject's adapter with the population model and with adapters fitted to other subjects. Using all first-half session labels, personal adapters improved mean balanced accuracy over the population model by 1.5-5.4 percentage points and outperformed exchanged adapters by 2.3-7.3 points in all nine model-dataset combinations. The size of this benefit depended on population training: with four times the original budget, median gains remained positive (1.0-2.0 points) but were smaller for every model, and no population model reached a confirmed plateau. Acquiring the benefit cheaply was unreliable: few-label calibration was consistently non-negative on only one dataset, and in CBraMod neither unlabeled context nor meta-learned initialization outperformed matched controls. Personalization should therefore be evaluated against both a population reference and exchanged parameters, across population-training budgets.

Xilin Tao, Kani Chen

Department of Mathematics, The Hong Kong University of Science and Technology, Hong Kong SAR, China · Department of Industrial Engineering and Decision Analytics, The Hong Kong University of Science and Technology, Hong Kong SAR, China

Cross-Subject EEG Decoding MI Classification Brain-Computer Interfaces EEG Decoding EEG Foundation Models

Ask PDF

Abstract

Continuous Control

Explore similar work

A Montage-Agnostic Encoder for Calibration-Light Cross-User Gesture Recognition from Surface Electromyography

Recognition and Label-Free Adaptation Across Recording Sessions in Surface-EMG Gesture Decoding

Separating personal from population gains when calibrating EEG foundation models for new users