Block-As-Domain Adaptation for Workload Prediction from fNIRS Data

TL;DR

This paper introduces a novel domain adaptation method called CABA-DA for improving workload prediction from fNIRS data, addressing inter- and intra-subject variability to enhance generalization across different sessions and subjects.

Contribution

The paper proposes a class-aware-block-aware domain adaptation technique and an MLPMixer-based model for better cognitive workload classification from fNIRS data, improving cross-session and cross-subject performance.

Findings

CABA-DA outperforms baseline models on three datasets.

Contrastive learning enhances model performance.

Model generalizes well across different tasks and sessions.

Abstract

Functional near-infrared spectroscopy (fNIRS) is a non-intrusive way to measure cortical hemodynamic activity. Predicting cognitive workload from fNIRS data has taken on a diffuse set of methods. To be applicable in real-world settings, models are needed, which can perform well across different sessions as well as different subjects. However, most existing works assume that training and testing data come from the same subjects and/or cannot generalize well across never-before-seen subjects. Additional challenges imposed by fNIRS data include the high variations in inter-subject fNIRS data and also in intra-subject data collected across different blocks of sessions. To address these issues, we propose an effective method, referred to as the class-aware-block-aware domain adaptation (CABA-DA) which explicitly minimize intra-session variance by viewing different blocks from the same subject same session as different domains. We minimize the intra-class domain discrepancy and maximize the inter-class domain discrepancy accordingly. In addition, we propose an MLPMixer-based model for cognitive load classification. Experimental results demonstrate the proposed model has better performance compared with three different baseline models on three public-available datasets of cognitive workload. Two of them are collected from n-back tasks and one of them is from finger tapping. From our experiments, we also show the proposed contrastive learning method can also improve baseline models we compared with.