AbsoluteNet: A Deep Learning Neural Network to Classify Cerebral Hemodynamic Responses of Auditory Processing

TL;DR

AbsoluteNet is a novel deep learning model that effectively classifies auditory hemodynamic responses from fNIRS data, outperforming existing models in accuracy and sensitivity for brain-computer interface applications.

Contribution

Introduces AbsoluteNet, a deep learning architecture with spatio-temporal convolution and custom activation functions, achieving superior classification of fNIRS-based auditory responses.

Findings

AbsoluteNet achieved 87.0% accuracy in binary classification.

It outperformed existing models like fNIRSNET by 3.8% in accuracy.

The model demonstrated high sensitivity and specificity in decoding auditory responses.

Abstract

In recent years, deep learning (DL) approaches have demonstrated promising results in decoding hemodynamic responses captured by functional near-infrared spectroscopy (fNIRS), particularly in the context of brain-computer interface (BCI) applications. This work introduces AbsoluteNet, a novel deep learning architecture designed to classify auditory event-related responses recorded using fNIRS. The proposed network is built upon principles of spatio-temporal convolution and customized activation functions. Our model was compared against several models, namely fNIRSNET, MDNN, DeepConvNet, and ShallowConvNet. The results showed that AbsoluteNet outperforms existing models, reaching 87.0% accuracy, 84.8% sensitivity, and 89.2% specificity in binary classification, surpassing fNIRSNET, the second-best model, by 3.8% in accuracy. These findings underscore the effectiveness of our proposed deep learning model in decoding hemodynamic responses related to auditory processing and highlight the importance of spatio-temporal feature aggregation and customized activation functions to better fit fNIRS dynamics.