Moment-to-Moment Continuous Attention Fluctuation Monitoring through Consumer-Grade EEG Device.

Shan Zhang,Wei Tsang Ooi,Shengdong Zhao,Zihan Yan,Shardul Sapkota

doi:10.3390/s21103419

Abstract

While numerous studies have explored using various sensing techniques to measure attention states, moment-to-moment attention fluctuation measurement is unavailable. To bridge this gap, we applied a novel paradigm in psychology, the gradual-onset continuous performance task (gradCPT), to collect the ground truth of attention states. GradCPT allows for the precise labeling of attention fluctuation on an 800 ms time scale. We then developed a new technique for measuring continuous attention fluctuation, based on a machine learning approach that uses the spectral properties of EEG signals as the main features. We demonstrated that, even using a consumer grade EEG device, the detection accuracy of moment-to-moment attention fluctuations was 73.49%. Next, we empirically validated our technique in a video learning scenario and found that our technique match with the classification obtained through thought probes, with an average F1 score of 0.77. Our results suggest the effectiveness of using gradCPT as a ground truth labeling method and the feasibility of using consumer-grade EEG devices for continuous attention fluctuation detection.

Highlights

Attention is a neurocognitive process critical to a wide variety of everyday tasks [1].Maintaining one’s attention for a period of time, and selectively concentrating on a stimulus or task while ignoring others require effort, and vary based on the individual’s ability to withstand cognitive load [2]
We first collected a dataset of EEG signals from 18 participants who completed three sessions of gradual-onset continuous performance task (gradCPT), built a classifier on attention fluctuation prediction based on EEG data
We proposed a technique to measure moment-to-moment continuous attention fluctuation with the consumer-grade EEG device

Summary

Introduction

Attention is a neurocognitive process critical to a wide variety of everyday tasks [1].Maintaining one’s attention for a period of time, and selectively concentrating on a stimulus or task while ignoring others require effort, and vary based on the individual’s ability to withstand cognitive load [2]. Attention is a neurocognitive process critical to a wide variety of everyday tasks [1]. Due to the lack of a reliable method of labeling attention states, moment-tomoment attention fluctuation measurement is unavailable in the current attention-related research in the computer science (CS) communities. Discrete data collection methods, such as thought probes, self-report questionnaires and surveys [6–9], have most often been used to establish an individual baseline for attention states. These methods only collect discrete data, i.e., the attention states at the moment, and cannot reflect the continuous nature of attention [10] as data concerning the changes from the start to the end of the attention states are unavailable

Methods

Results

Discussion

Conclusion