A Non-parametric Approach to the Overall Estimate of Cognitive Load Using NIRS Time Series.

Soheil Keshmiri,Ryuji Yamazaki,Hiroshi Ishiguro,Hidenobu Sumioka

doi:10.3389/fnhum.2017.00015

Abstract

We present a non-parametric approach to prediction of the n-back n ∈ {1, 2} task as a proxy measure of mental workload using Near Infrared Spectroscopy (NIRS) data. In particular, we focus on measuring the mental workload through hemodynamic responses in the brain induced by these tasks, thereby realizing the potential that they can offer for their detection in real world scenarios (e.g., difficulty of a conversation). Our approach takes advantage of intrinsic linearity that is inherent in the components of the NIRS time series to adopt a one-step regression strategy. We demonstrate the correctness of our approach through its mathematical analysis. Furthermore, we study the performance of our model in an inter-subject setting in contrast with state-of-the-art techniques in the literature to show a significant improvement on prediction of these tasks (82.50 and 86.40% for female and male participants, respectively). Moreover, our empirical analysis suggest a gender difference effect on the performance of the classifiers (with male data exhibiting a higher non-linearity) along with the left-lateralized activation in both genders with higher specificity in females.

Highlights

The advent of intelligent systems, capable of communicating with human (Yamazaki et al, 2007), introduces a tremendous opportunity to further explore some of most fundamental aspects of human society, thereby fathoming the intricacies exhibited in human behaviors pragmatically (Ogawa et al, 2011)
We introduce the potential that the utilization of differential entropy (DE) as a feature can offer to the solution concept of Near Infrared Spectroscopy (NIRS)-based mental workload classification
We introduce a non-parametric approach to prediction of n-back task as a proxy measure of mental workload of human subjects using NIRS data

Summary

Introduction

The advent of intelligent systems, capable of communicating with human (Yamazaki et al, 2007), introduces a tremendous opportunity to further explore some of most fundamental aspects of human society, thereby fathoming the intricacies exhibited in human behaviors pragmatically (Ogawa et al, 2011) Such systems have been increasingly proven to be of formidable potentials in investigation of foundational societal building blocks such as epigenetics (Prince and Gogate, 2007) and early child development (Lungarella et al, 2003; Tanaka et al, 2007). It is necessary to devise agents with mathematical models that are trained on basic cognitive activities, thereby providing them with adequate means to detect and/or measure such activities during interaction with human

Results

Discussion

Conclusion