Benchmarking ERP Analysis: Manual Features, Deep Learning, and Foundation Models

2026-01-02

arXiv.org

AI Summary

This study addresses the lack of systematic evaluation of deep learning and foundation models in event-related potential (ERP) analysis, which has traditionally relied on handcrafted features. The authors establish a unified preprocessing and training pipeline to conduct the first comprehensive benchmark across 12 public ERP datasets, comparing three mainstream approaches: handcrafted features with linear classifiers, deep neural networks, and pretrained EEG foundation models. They also investigate Transformer-based embedding strategies tailored for ERP signals. By establishing a standardized benchmark framework, this work provides empirical guidance for method selection and model customization, revealing consistent cross-dataset performance differences among the evaluated methods in both stimulus classification and brain disorder detection tasks.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Event-related potential (ERP), a specialized paradigm of electroencephalographic (EEG), reflects neurological responses to external stimuli or events, generally associated with the brain's processing of specific cognitive tasks. ERP plays a critical role in cognitive analysis, the detection of neurological diseases, and the assessment of psychological states. Recent years have seen substantial advances in deep learning-based methods for spontaneous EEG and other non-time-locked task-related EEG signals. However, their effectiveness on ERP data remains underexplored, and many existing ERP studies still rely heavily on manually extracted features. In this paper, we conduct a comprehensive benchmark study that systematically compares traditional manual features (followed by a linear classifier), deep learning models, and pre-trained EEG foundation models for ERP analysis. We establish a unified data preprocessing and training pipeline and evaluate these approaches on two representative tasks, ERP stimulus classification and ERP-based brain disease detection, across 12 publicly available datasets. Furthermore, we investigate various patch-embedding strategies within advanced Transformer architectures to identify embedding designs that better suit ERP data. Our study provides a landmark framework to guide method selection and tailored model design for future ERP analysis. The code is available at https://github.com/DL4mHealth/ERP-Benchmark.

Problem

• Event-related potential
• ERP analysis
• deep learning
• foundation models
• manual features

Innovation

• ERP benchmarking
• deep learning
• EEG foundation models
• Transformer patch embedding
• manual feature comparison