The Deep-Match Framework for Event-Related Potential Detection in EEG

Abstract

Reliable detection of event-related potentials (ERPs) at the single-trial level remains a major challenge due to the low signal-to-noise ratio EEG recordings. In this work, we investigate whether incorporating prior knowledge about ERP templates into deep learning models can improve detection performance. We employ the Deep-Match framework for ERP detection using multi-channel EEG signals. The model is trained in two stages. First, an encoder-decoder architecture is trained to reconstruct input EEG signals, enabling the network to learn compact signal representations. In the second stage, the decoder is replaced with a detection module, and the network is fine-tuned for ERP identification. Two model variants are evaluated: a standard model with randomly initialized filters and a Deep-MF model in which input kernels are initialized using ERP templates. Model performance is assessed on a single-trial ERP detection task using leave-one-subject-out validation. The proposed Deep-MF model slightly outperforms the detector with standard kernel initialization for most held-out subjects. Despite substantial inter-subject variability, Deep-MF achieves a higher average F1-score (0.37) compared to the standard network (0.34), indicating improved robustness to cross-subject differences. The best performance obtained by Deep-MF reaches an F1-score of 0.71, exceeding the maximum score achieved by the standard model (0.59). These results demonstrate that ERP-informed kernel initialization can provide consistent improvements in subject-independent single-trial ERP detection. Overall, the findings highlight the potential of integrating domain knowledge with deep learning architectures for EEG analysis. The proposed approach represents a step toward practical wearable EEG and passive brain-computer interface systems capable of real-time monitoring of cognitive processes.

Figures (3)

• Figure 1: Architecture of the model. The model was trained in two stages. In the first stage, the encoder–decoder network was trained to reconstruct the input signal. Two models were trained: Deep-MF, with input filters initialized using ERP templates, and a standard model with random initialization. In the second stage, the decoder part of the network was replaced with a detector, and the models were fine-tuned for ERP detection.
• Figure 2: Grand-average event-related potentials (ERPs) for representative EEG leads across subjects. Clear ERP components are visible over central electrodes (C3, Cz, Pz, and C4), whereas more distant electrodes show weaker or absent responses. Only a subset of leads is displayed for clarity; similar symmetrical patterns were observed across contra-lateral electrodes.
• Figure 3: F1-scores obtained for each subject using leave-one-subject-out cross-validation. Deep-MF consistently outperformed the standard network on the majority of subjects and achieved a higher mean F1-score (0.37 vs. 0.34). The lowest performance for both methods occurred for Subject 10 (F1 = 0.01).