Hybrid System for Engagement Recognition During Cognitive Tasks Using a CFS + KNN Algorithm

Abstract

Engagement is described as a state in which an individual involved in an activity can ignore other influences. The engagement level is important to obtaining good performance especially under study conditions. Numerous methods using electroencephalograph (EEG), electrocardiograph (ECG), and near-infrared spectroscopy (NIRS) for the recognition of engagement have been proposed. However, the results were either unsatisfactory or required many channels. In this study, we introduce the implementation of a low-density hybrid system for engagement recognition. We used a two-electrode wireless EEG, a wireless ECG, and two wireless channels NIRS to measure engagement recognition during cognitive tasks. We used electrooculograms (EOG) and eye tracking to record eye movements for data labeling. We calculated the recognition accuracy using the combination of correlation-based feature selection and k-nearest neighbor algorithm. Following that, we did a comparative study against a stand-alone system. The results show that the hybrid system had an acceptable accuracy for practical use (71.65 ± 0.16%). In comparison, the accuracy of a pure EEG system was (65.73 ± 0.17%), pure ECG (67.44 ± 0.19%), and pure NIRS (66.83 ± 0.17%). Overall, our results demonstrate that the proposed method can be used to improve performance in engagement recognition.

Quantitative Formula of Blink Rates-Pupillometry for Attention Level Detection in Supervised Machine Learning

“…Classification based on CFS+KNN has been chose after doing several comparison with other classification method such as support vector machine (SVM). Similar method was developed in previous study [9]. WEKA 3.8 [15] data mining for machine learning has been used.…”

“…First experiment is done for investigating the blink rates and pupilometri based on participant self-assessment. First experiment session is content contain Three types of task loads were used: backward digit span (BDS) [9], [10], forward digit span (FDS) [9], [10], and arithmetic (AR) [9]. These tasks are consisted of three level.…”

“…EEG data was recorded by using 10/20 systems placement on the Fz and Pz, referenced on A1 (left earlobe). These areas are correlated for cognitive activities [9], [13], [14]. The ECG was recorded on the chest (2-lead placement) [9], [13], [14].…”

Strengthening Tourists’ Engagement in Guided Hiking and Trekking

“…In addition to guides' skills to unobtrusively retrieve such information, one could consider using sensors of some kind to recognise engagement. There is a variety of attempts to retrieve emotion by using cameras (Nezami et al 2018;Terzis et al 2010), sensors such as electrocardiograph (ECG), electroencephalograph (EEG) or electrooculograph (EOG) (Zennifa et al 2018), motion sensors (inertial, gyroscope, magnetometer), positioning devices (Mautz 2012) or combinations of these. However, most of these sensor technologies work sufficiently only in controlled settings, as experiments in museums and science centres have shown (Leister et al 2018, p. 69).…”

Strengthening Tourists’ Engagement in Guided Hiking and Trekking

“…Instead, one could consider to use sensors of some kind to recognise engagement. There is a variety of attempts to retrieve emotion by using cameras [15,22], sensors such as electro-cardiograph (ECG), electro-encephalograph (EEG), or electro-oculograph (EOG) [26], motion sensors (inertial, gyroscope, magnetometer), positioning devices [14], or combinations of these. However, most of these sensor technologies work sufficiently only in controlled settings, as experiments in museums and science centres have shown [8, p.69].…”