Understanding Auditory Evoked Brain Signal via Physics-informed Embedding Network with Multi-Task Transformer

TL;DR

This paper introduces PEMT-Net, a physics-informed multi-task transformer model that significantly improves decoding of auditory brain signals from fMRI data, advancing understanding of neural processing of complex sounds.

Contribution

The paper presents a novel physics-informed embedding approach and a multi-task transformer architecture for enhanced auditory signal decoding from fMRI data.

Findings

PEMT-Net outperforms existing methods in decoding accuracy.

The physics-informed embedding captures both local and non-local neural information.

The model provides new insights into brain mechanisms for auditory processing.

Abstract

In the fields of brain-computer interaction and cognitive neuroscience, effective decoding of auditory signals from task-based functional magnetic resonance imaging (fMRI) is key to understanding how the brain processes complex auditory information. Although existing methods have enhanced decoding capabilities, limitations remain in information utilization and model representation. To overcome these challenges, we propose an innovative multi-task learning model, Physics-informed Embedding Network with Multi-Task Transformer (PEMT-Net), which enhances decoding performance through physics-informed embedding and deep learning techniques. PEMT-Net consists of two principal components: feature augmentation and classification. For feature augmentation, we propose a novel approach by creating neural embedding graphs via node embedding, utilizing random walks to simulate the physical diffusion of neural information. This method captures both local and non-local information overflow and proposes a position encoding based on relative physical coordinates. In the classification segment, we propose adaptive embedding fusion to maximally capture linear and non-linear characteristics. Furthermore, we propose an innovative parameter-sharing mechanism to optimize the retention and learning of extracted features. Experiments on a specific dataset demonstrate PEMT-Net's significant performance in multi-task auditory signal decoding, surpassing existing methods and offering new insights into the brain's mechanisms for processing complex auditory information.