Attentiveness Assessment in Learning Based on Fuzzy Logic Analysis

Abstract

Learner attention affects learning efficiency. However, in many classes, teachers cannot assess the degree of attention of every student. When a teacher is capable of addressing inattentive students immediately, he can avoid situations in which students are inattentive. Many studies have analyzed student attentiveness by the applying of Image Detection Technologies. If this mechanism can be applied to inclass learning, it will help teachers keep students attentive, and reduce teacher load during class. This study mainly applies Fuzzy Logic analysis of student facial images when participating in class. Applying Fuzzy Logic can prevent erroneous judgments associated with a single term, and help teachers deal with student attentiveness

Assessment of affective state in distance learning based on image detection by using fuzzy fusion

“…A person with these behaviors is in a good mental state, but is not participating in the course. Additional detection mechanisms need to be added to the image recognition to apply it to distance learning [18].…”

Fuzzy Rule-based Alertness State Classification based on the Optimization of EEG Rhythm/Channel Combinations

“…The development of automatic alertness state classification has recently attracted an increased attention in a number of scientific disciplines. Most of the currently existing approaches for automatic alertness state classification are based on either physiological signals [2,4,5,6] or image sequences (video) [7,8]. The first category of methods uses physiological signals such as the electroencephalogram (EEG), electromyogram (EMG), electrooculogram (EOG), and electrocardiogram (ECG),separately or combined, for alertness identification.…”

“…These features were then fed to a classifier, such as artificial neural networks (ANN) [4,5] or support vector machines (SVM) [6] to be assigned to either two states (alert/drowsy) [6] or three states (alert/drowsy/asleep) [4] of alertness. A number of videobased methods have also been proposed in the literature, such as [7,8]. Video-based methods: Most of the proposed video-based methods follow a three-stage process: 1) Face detection, 2) eyes localizations, and 3) either eyelid movement detection (to compute the percentage of eye closure) or gaze tracking (using either ordinary or infrared cameras).…”