Result Details

Joint-Level Motor Imagery Decoding in fNIRS via a Unified Pairwise Machine Learning Framework

NOSHEEN, T.; JURKOJĆ, J.; WODARSKI, P.; JAWED, S.; MALIK, A. Joint-Level Motor Imagery Decoding in fNIRS via a Unified Pairwise Machine Learning Framework. In Medical Image Computing and Computer Assisted Intervention – MICCAI 2026. Strasbourg, France: Springer Nature, 2026. p. 322-331. ISBN: 978-3-032-38260-3.
Type
conference paper
Language
English
Authors
Nosheen Tayyaba
Jurkojć Jacek
Wodarski Piotr
Jawed Soyiba, Dr., MSc
Malik Aamir Saeed, prof., Ph.D., DCSY (FIT)
Abstract

Precise decoding of intended joint movements from brain activity is essential for next-generation neurorehabilitation interfaces, yet most motor imagery studies focus on single joints or coarse movement categories rather than systematically evaluating all upper-limb joints. We present a joint-aware decoding framework that systematically quantifies joint-level separability across eight upper-limb motor imagery tasks through binary pairwise classification in a unified machine learning framework. All preprocessing, feature selection, dimensionality reduction, and hyperparameter optimization were performed within subject-wise nested cross-validation to eliminate any risk of data leakage. Evaluation on a public dataset of eighteen participants yielded consistent performance across all joint pairs with mean accuracies ranging from 83% to 88% (SD = 0.04). Logistic regression (LR) and linear discriminant analysis (LDA) achieved the strongest and most stable performance. Statistical testing using the Wilcoxon signed rank test confirmed that linear discriminant analysis significantly outperformed the baseline model with p

Keywords

Neurorehabilitation
fNIRS-based BCI
Motor imagery
Upper-limb motor decoding

URL
Published
2026
Pages
322–331
Proceedings
Medical Image Computing and Computer Assisted Intervention – MICCAI 2026
Conference
Medical Image Computing and Computer Assisted Intervention – MICCAI 2026
ISBN
978-3-032-38260-3
Publisher
Springer Nature
Place
Strasbourg, France
DOI
BibTeX
@inproceedings{BUT212603,
  author="Tayyaba {Nosheen} and  {} and  {} and Soyiba {Jawed} and Aamir Saeed {Malik}",
  title="Joint-Level Motor Imagery Decoding in fNIRS via a Unified Pairwise Machine Learning Framework",
  booktitle="Medical Image Computing and Computer Assisted Intervention – MICCAI 2026",
  year="2026",
  pages="322--331",
  publisher="Springer Nature",
  address="Strasbourg, France",
  doi="10.1007/978-3-032-38260-3\{_}31",
  isbn="978-3-032-38260-3",
  url="https://link.springer.com/chapter/10.1007/978-3-032-38260-3_31"
}
Projects
HATS - Home based Assessment & Tracking System for Early-Stage Stress, Anxiety & Depression, TAČR, 4. veřejná soutěž programu SIGMA - DÍLČÍ CÍL 1: PODPORA AKTIVIT „PROOF OF CONCEPT” VE VÝZKUMNÝCH ORGANIZACÍCH, TQ11000003, TQ11000003/1_04, start: 2025-03-01, end: 2026-02-28, completed
Departments
Back to top