Decoding Stimulus Reconstruction-Based Auditory Attention Robustly in Unbalanced EEG Datasets
2026-05-25 • Machine Learning
Machine Learning
AI summaryⓘ
The authors looked at how deep neural networks are used to figure out where a person is paying attention by analyzing brain signals called EEG. They found that when the datasets they use are unbalanced, the networks seem to perform better than they actually do. To fix this, the authors created a new testing method called LOPEO that gives a more accurate measure of performance, especially for unbalanced datasets. This helps researchers understand results better and compare studies more fairly.
Deep Neural NetworksAuditory Attention DecodingElectroencephalogram (EEG)Stimulus ReconstructionDataset BalanceCross-ValidationLOPEODecoding PerformanceUnbalanced DatasetsBrain-Computer Interface
Authors
Yuanming Zhang, Yayun Liang, Zhibin Lin, Jing Lu
Abstract
In the past decade, numerous studies have applied deep neural networks (DNNs) to decode auditory attention (AAD) from Electroencephalogram (EEG) signals via stimulus reconstruction. However, the influence of dataset balance on the decoding performance of stimulus reconstruction-based AAD remains unexplored. In this study, three publicly available EEG-AAD datasets - KUL, DTU, and NJU cEEGrid - are used to construct both balanced and unbalanced experimental conditions. We hypothesize and demonstrate that stimulus reconstruction-based DNN decoders tend to produce overestimated decoding performance on unbalanced datasets. To address this issue, we propose a leave-one-paired-envelope-out (LOPEO) cross-validation protocol. Experimental results confirm that LOPEO effectively prevents inflated decoding accuracy on unbalanced datasets. While balanced datasets are generally preferred in experimental design, LOPEO provides a principled evaluation framework for unbalanced datasets that have already been published, filling an important gap in the field.