Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Biometrics and Behavior Analysis for Detecting Distractions in e-Learning

Álvaro Becerra, Javier Irigoyen, Roberto Daza, Ruth Cobos, Aythami Morales, Julian Fierrez, Mutlu Cukurova

TL;DR

The hypothesis suggests that head posture undergoes significant changes when learners interact with a mobile phone, contrasting with the typical behavior seen when learners face a computer during e-Iearning sessions.

Abstract

In this article, we explore computer vision approaches to detect abnormal head pose during e-learning sessions and we introduce a study on the effects of mobile phone usage during these sessions. We utilize behavioral data collected from 120 learners monitored while participating in a MOOC learning sessions. Our study focuses on the influence of phone-usage events on behavior and physiological responses, specifically attention, heart rate, and meditation, before, during, and after phone usage. Additionally, we propose an approach for estimating head pose events using images taken by the webcam during the MOOC learning sessions to detect phone-usage events. Our hypothesis suggests that head posture undergoes significant changes when learners interact with a mobile phone, contrasting with the typical behavior seen when learners face a computer during e-learning sessions. We propose an approach designed to detect deviations in head posture from the average observed during a learner's session, operating as a semi-supervised method. This system flags events indicating alterations in head posture for subsequent human review and selection of mobile phone usage occurrences with a sensitivity over 90%.

Biometrics and Behavior Analysis for Detecting Distractions in e-Learning

TL;DR

The hypothesis suggests that head posture undergoes significant changes when learners interact with a mobile phone, contrasting with the typical behavior seen when learners face a computer during e-Iearning sessions.

Abstract

In this article, we explore computer vision approaches to detect abnormal head pose during e-learning sessions and we introduce a study on the effects of mobile phone usage during these sessions. We utilize behavioral data collected from 120 learners monitored while participating in a MOOC learning sessions. Our study focuses on the influence of phone-usage events on behavior and physiological responses, specifically attention, heart rate, and meditation, before, during, and after phone usage. Additionally, we propose an approach for estimating head pose events using images taken by the webcam during the MOOC learning sessions to detect phone-usage events. Our hypothesis suggests that head posture undergoes significant changes when learners interact with a mobile phone, contrasting with the typical behavior seen when learners face a computer during e-learning sessions. We propose an approach designed to detect deviations in head posture from the average observed during a learner's session, operating as a semi-supervised method. This system flags events indicating alterations in head posture for subsequent human review and selection of mobile phone usage occurrences with a sensitivity over 90%.
Paper Structure (10 sections, 2 equations, 2 figures, 1 table)

This paper contains 10 sections, 2 equations, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Works
  3. MultiModal Data Description
  4. Methods
  5. Statistical Analysis
  6. Head Pose Study
  7. Results
  8. Statistical Analysis
  9. Head Pose Based Event Detection Approach for Phone Usage
  10. Conclusion and Future Work

Figures (2)

  • Figure 1: The head pose of a learner is captured at the instance of a phone event (left). The graph illustrates the yaw angle over time, captured during a LS (right). The solid blue line represents the raw data, the blue dashed line represents the global average and the orange dashed line indicates the local average, calculated using a sliding window of size $w$. The dotted blue lines represent thresholds, adjustable via the parameter $n$. When the local average crosses a threshold an event is predicted. Predicted events are denoted by a red shaded area, while actual events are denoted by a green shaded area.
  • Figure 2: Average sensitivity obtained by the head pose based approach to detect phone usage across all users (left). Average number of events obtained by the head pose based the approach across all users (right). Axes $x$ and $y$ represent parameters $w$ and $n$, respectively.