Functional Near Infrared Spectroscopy

Functional near-infrared spectroscopy (fNIRS) is a non-invasive neuroimaging technique used to study brain activity by measuring changes in blood oxygenation. Current research focuses on improving the accuracy and interpretability of fNIRS data analysis, employing machine learning models such as convolutional neural networks (CNNs), long short-term memory networks (LSTMs), and transformers, often combined with techniques like contrastive learning and metric learning to enhance performance and address challenges like cross-subject variability and motion artifacts. These advancements are enabling applications in diverse fields, including emotion recognition, cognitive workload assessment, and the development of brain-computer interfaces, ultimately contributing to a deeper understanding of human brain function and behavior.