Subject-independent decoding of affective states using functional near-infrared spectroscopy

Abstract

Multivariate brain decoding (MBD) can be applied to estimate mental states using brain signal measurements. In the best scenario, a MBD model should be trained in a first set of volunteers and then validated in a new and independent dataset. Here, we aimed to evaluate whether functional near-infrared spectroscopy (fNIRS) signals from frontal and occipital areas provide enough information to discriminate affective states. For this purpose, a linear discriminant analysis classifier was trained in a first database (49 participants, 24.65±3.23 years) and tested in an independent database (20 participants, 24.00±3.92 years). Significant accuracies were found for positive vs. negative (64.50±12.44%, p<0.01) and negative vs. neutral (67.75±14.45%, p<0.01) affect during a passive elicitation condition, consisting in viewing pre-validated images with emotional content. For the active elicitation condition, in which volunteers were instructed to recollect personal affective experiences, significant accuracy was found for positive vs. neutral affect (71.00±17.93%, p<0.01). In this last case, only three fNIRS channels were sufficient to discriminate between those affective states: two positioned over the left ventrolateral prefrontal area and one over the right lateral orbitofrontal cortex. In conclusion, our results show that fNIRS is a feasible technique for intersubject affective decoding, reaching significant classification accuracies using a few and biologically consistent features.

A pediatric near-infrared spectroscopy brain-computer interface based on the detection of emotional valence

“…This study is the first, to the authors' knowledge, to investigate an affective BCI for children using fNIRS, and the classification accuracies 2012) (mean accuracy 71.9%). Tai and Chau (2009) and Trambaiolli et al (2018b) achieved higher classification accuracies (mean 84.6% emotion vs. neutral, and 89.9% positive vs. neutral, 81.5% negative vs. neutral, respectively), although the classification task in these studies was between a presumably more distinct set of classes-i.e., emotional vs. a neutral/rest state, rather than positive vs. negative. Heger et al (2014) reported lower classification accuracies, but were investigating the multi-class discrimination of emotional arousal in addition to valence.…”

“…An online interface has also been designed where users could interact with a virtual character through positive emotions (Aranyi et al, 2016) or anger (Aranyi et al, 2015). In a series of studies, Trambaiolli et al used fNIRS to differentiate emotional states both passively (viewing emotionally salient images) and actively (self-generating emotional memories), both offline (Trambaiolli et al, 2018b) and exploring the effects of online neurofeedback (Trambaiolli et al, 2018a).…”

Functional near-infrared spectroscopy-based affective neurofeedback: feedback effect, illiteracy phenomena, and whole-connectivity profiles

“…For example, motor imagery studies have found O 2 Hb as the most robust features, 57,74 whereas in a similar affective experiment our group also reported a predominance of HHb features among the most relevant ones. 75,76 Previous studies describe different advantages for each measure.…”