Result Details
Joint-Level Motor Imagery Decoding in fNIRS via a Unified Pairwise Machine Learning Framework
Jurkojć Jacek
Wodarski Piotr
Jawed Soyiba, Dr., MSc
Malik Aamir Saeed, prof., Ph.D., DCSY (FIT)
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
Neurorehabilitation
fNIRS-based BCI
Motor imagery
Upper-limb motor decoding
@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"
}