Unsupervised Accuracy Estimation for Correlation-based Stimulus Decoders in Selective Auditory Attention Decoding (AAD)
If this code has been useful to you, please cite [1].
This repository includes the MATLAB code for Algorithm 1 in [1], i.e., the unsupervised AAD accuracy estimation for correlation-based stimulus decoders.
Developed and tested in MATLAB R2021b.
Note: The Statistics and Machine Learning Toolbox in MATLAB is required to compute confidence intervals.
Simon Geirnaert
KU Leuven, Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics
KU Leuven, Department of Neurosciences, Research Group ExpORL
Leuven.AI - KU Leuven institute for AI
simon.geirnaert@esat.kuleuven.be
Miguel A. Lopez-Gordo
University of Granada, Department of Signal Theory, Telematics and Communications
University of Granada, NeuroEngineering and Computing Lab (NECOlab), Research Centre for Information and Communication Technologies
malg@ugr.es
Alexander Bertrand
KU Leuven, Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics
Leuven.AI - KU Leuven institute for AI
alexander.bertrand@esat.kuleuven.be
[1] M. A. Lopez-Gordo, S. Geirnaert and A. Bertrand, "Unsupervised Accuracy Estimation for Brain–Computer Interfaces Based on Selective Auditory Attention Decoding," in IEEE Transactions on Biomedical Engineering, vol. 72, no. 8, pp. 2388-2399, Aug. 2025, doi: 10.1109/TBME.2025.3542253.