fNIRS Signal

fNIRS (functional near-infrared spectroscopy) signal analysis focuses on extracting meaningful information about brain activity from changes in blood oxygenation levels measured non-invasively. Current research emphasizes improving the accuracy and reliability of fNIRS data analysis through advanced machine learning techniques, including deep learning models like convolutional neural networks (CNNs) and transformers, often combined with recurrent neural networks (RNNs) such as LSTMs to capture temporal dependencies. These advancements are driving progress in diverse applications, such as emotion recognition, pain assessment, brain-computer interfaces, and decoding imagined speech, ultimately aiming to improve our understanding of cognitive processes and facilitate the development of novel neurotechnologies.