Effective Brain Connectivity for fNIRS With Fuzzy Cognitive Maps in Neuroergonomics

Abstract

Effective connectivity (EC) amongst functional near-infrared spectroscopy (fNIRS) signals is a quantitative measure of the strength of influence between brain activity associated with different regions of the brain. Evidently, accurate deciphering of EC gives further insight into the understanding of the intricately complex nature of neuronal interactions in the human brain. This work presents a novel approach to estimate EC in the human brain signals using enhanced fuzzy cognitive maps (FCMs). The proposed method presents a regularized methodology of FCMs, called effective FCMs (E-FCMs), with improved accuracy for predicting EC between real, and synthetic fNIRS signals. Essentially, the revisions made in the FCM methodology include a more powerful prediction formula for FCM combined with independent tuning of the transformation function parameter. A comparison of EC in fNIRS signals obtained from E-FCM with that obtained from standard FCM, general linear model (GLM) parameters that power Dynamic Causal Modelling (DCM), and Granger Causality (GC) manifests the greater prowess of the proposed E-FCM over the aforementioned methods. For real fNIRS data, an empirical investigation is also made to gain an insight into the role of oxyhemoglobin and deoxyhemoglobin (oxy-Hb, deoxy-Hb) in representing the cognitive activity. We believe this work has profound implications for neuroergonomics research communities.

Single-Trial Recognition of Video Gamer’s Expertise from Brain Haemodynamic and Facial Emotion Responses

“…For six out of a total of seven classifiers, the H0 1 is rejected hence establishing that it is possible to recognise gamer's expertise level from fNIRS neural responses from the PFC with recognition performance better than a 95% confidence interval difference to the results from a baseline classifier. This is inline with previous studies which found professional on-line gamers to have an increased brain volume in the PFC [25], and from the literature we know that subjects at different 475 expertise levels have different patterns of activation in their PFC [28,31].…”

“…In this work, fNIRS is used to image participant’s brain activity owing to the superior spatial resolution and resistance to motion artifacts in comparison to EEG [ 30 ]. In addition, previous fNIRS studies from our group have aimed to gauge technical skill levels assessment for surgeons with varying levels of experience in the study by Andreu-Perez et al [ 28 ] and Kiani et al [ 31 ]. In Andreu-Perez et al [ 28 ] the surgeons perform a complex bi manual coordination task whilst their brain activity is recorded using fNIRS.…”

“…However, they garnered brain activity from only three customary surgical needling tasks resulting in a classification accuracy of 82% for time-course based networks, and 68% for session based networks. However, both studies [ 28 , 31 ] did not take into account any aspect of the emotional state of their participants whilst decoding levels of manual dexterity.…”

Towards Understanding Human Functional Brain Development With Explainable Artificial Intelligence: Challenges and Perspectives

“…An fNIRS study that estimated EC amongst fNIRS channels (corresponding anatomical regions in the cortex) based on fuzzy cognitive maps (FCMs) is proposed by Kiani et al [58]. A FCM is a cognitive mapping technique based on graph theory, with a formal mathematical definition given as follows in (1).…”

“…where N is the number of concepts (or fNIRS channels) in a given system, C j (t) is the value of a given concept C j at iteration t, e ij are the fuzzy weights or EC that concept C i exerts on concept C j and f is typically a sigmoid function that scales the weights to [-1,1] for comparative analysis such that a value of 1 means fully interconnected, a value of -1 means fully interconnected in the opposite direction, a value of 0 means disconnected, and a value between 0 and 1 (or -1) means interconnected to a certain extent. The optimal values of EC (e ij ) are typically found using an evolutionary algorithm such as Genetic algorithm (GA) (GA has also been used in the aforementioned study [58]).…”