Taking a Deeper Look at the Brain: Predicting Visual Perceptual and Working Memory Load From High-Density fNIRS Data
| Autor: | Jiyang Wang, Trevor Grant, Senem Velipasalar, Baocheng Geng, Leanne Hirshfield |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Brain
02 engineering and technology 030218 nuclear medicine & medical imaging Computer Science Applications 03 medical and health sciences 0302 clinical medicine Cognition Memory Short-Term Health Information Management 0202 electrical engineering electronic engineering information engineering Visual Perception Humans 020201 artificial intelligence & image processing Electrical and Electronic Engineering Biotechnology |
| Zdroj: | IEEE journal of biomedical and health informatics. 26(5) |
| ISSN: | 2168-2208 |
| Popis: | Predicting workload using physiological sensors has taken on a diffuse set of methods in recent years. However, the majority of these methods train models on small datasets, with small numbers of channel locations on the brain, limiting a model's ability to transfer across participants, tasks, or experimental sessions. In this paper, we introduce a new method of modeling a large, cross-participant and cross-session set of high density functional near infrared spectroscopy (fNIRS) data by using an approach grounded in cognitive load theory and employing a Bi-Directional Gated Recurrent Unit (BiGRU) incorporating attention mechanism and self-supervised label augmentation (SLA). We show that our proposed CNN-BiGRU-SLA model can learn and classify different levels of working memory load (WML) and visual processing load (VPL) across participants. Importantly, we leverage a multi-label classification scheme, where our models are trained to predict simultaneously occurring levels of WML and VPL. We evaluate our model using leave-one-participant-out (LOOCV) as well as 10-fold cross validation. Using LOOCV, for binary classification (off/on), we reached an F1-score of 0.9179 for WML and 0.8907 for VPL across 22 participants (each participant did 2 sessions). For multi-level (off, low, high) classification, we reached an F1-score of 0.7972 for WML and 0.7968 for VPL. Using 10-fold cross validation, for multi-level classification, we reached an F1-score of 0.7742 for WML and 0.7741 for VPL. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|