Fast-Calibration-Based Control for an Upper-Limb Prosthesis

Zholtayev D. Riaz Khawaja A. Ozhikenov K. Ozhikenova A. Shylmyrza U. Abdikenov B.
2025 Institute of Electrical and Electronics Engineers Inc.

IEEE Access
2025 #13 202438 - 202453 pp.

Dexterous prosthetic control demands intent decoders that calibrate quickly and remain robust to arm-pose variation. We present a transfer-learning framework that advances the calibration-based family of algorithms via a dual-branch Transformer fusing surface electromyography (sEMG) and inertial measurement unit (IMU) signals. Training proceeds in three stages:1) SourceNet learns pose-robust, subject-agnostic features from a multi-subject cohort; 2) TargetNet adapts these features to a new user with only two repetitions per class; and 3) PFCNet (Parallel Feature Concatenation) combines SourceNet and TargetNet embeddings for final classification. To our knowledge, prior calibration-based methods have focused predominantly on sEMG-only pipelines and do not explicitly optimize the models using additional sensing modalities during calibration; our modality-aware design addresses this gap. On a held-out subject (9 subjects; held-out subject evaluation; two-repetition calibration), the Transformer decoder achieves 99.35% accuracy, surpassing a strong CNN baseline while using approximately five times fewer learnable parameters. This supports embedded, real-time deployment. This model comprises 3.71M parameters (≈ 14.84 MB in 32-bit float; ≈ 3.71 MB when 8-bit quantized). Accordingly, its embedded inference footprint and latency are small: we expect single-digit to low double-digit millisecond inference times depending on hardware (e.g., sub-10 ms with 8-bit quantization on an NPU, or tens of ms on a CPU-only platform), making the system compatible with real-time prosthetic control. Ablations confirm that 1) sEMG–IMU fusion is essential for accuracy under pose changes and 2) minimal, two-repetition calibration suffices for reliable personalization. To enable reproducibility, we release a systematically curated dataset of nine subjects with synchronized sEMG and IMU recordings. Collectively, the proposed framework delivers a more accurate, parameter-efficient, and rapidly calibratable solution for prosthetic hand control, extending the calibration-based algorithm family with a principled, multimodal optimization strategy.

Control , inertial measurement unit , machine learning , robotic hand prosthesis , surface electromyography signal processing , transfer learning , transformer neural network

Text of the article Перейти на текст статьи

Astana IT University, Astana, 010000, Kazakhstan
ReLive Research, Astana, 010000, Kazakhstan
Satbayev University, Almaty, 050000, Kazakhstan

Astana IT University
ReLive Research
Satbayev University

10 лет помогаем публиковать статьи Международный издатель

Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026