Gauging attention of students in an e-learning environment

Revadekar, Abhishek; Oak, Shreya; Gadekar, Aumkar; Bide, Pramod

doi:10.1109/cict51604.2020.9312048

Cited by 27 publications

(13 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Emotion and engagement detection treat both desirable and undesirable states. Webcam images and mouse gestures are utilized to detect desirable emotion or high engagement level in a binary scale [18,19,20,21,22,23,24,25]. The information extracted by webcam images is facial expression, upper-body posture, heart rate, and so on.…”

Section: Related Workmentioning

confidence: 99%

Predicting Online Student Effort with Accelerometer, Heart Rate Sensors, and Camera Using Random Forest Regression Model

Harada¹

2022

IJMECS

View full text Add to dashboard Cite

In online education through web conference tools, teachers cannot grasp students' states by watching their behaviors like in an offline classroom. Each student also cannot be affected by others' good behavior. This paper proposes a prediction method of the student effort through acceleration sensors and a heart rate sensor worn on a student's body, and a local camera. The effort is expressed by the levels of concentration, excitation, and bodily action. A Random Forest regression model is used to predict each level from the sensor and camera data. Exhibiting the prediction result brings visibility of student states like offline. We verified the effectiveness of the prediction model through an experiment. We built the Random Forest regression prediction models from the sensors, camera, and student effort data obtained by actual lectures. In the case of building one prediction model for one lecture/one subject, the average R 2 values were 0.953, 0.925, and 0.930 in the concentration, excitation, and bodily action, respectively. The R 2 was -0.835 when one prediction model trained by one lecture's data is applied for another lecture's prediction. That was 0.285 when one model by 4 subjects' data is applied for prediction for the rest 1 subject. It means that the prediction model has high accuracy but is dependent on individual persons and lectures, which forces a burden to individual student to collect initial training data for individual lecture to build a prediction model. We also found that the acceleration data are the most important features. It implies the effectiveness of using acceleration sensors to predict student effort.

show abstract

Section: Related Workmentioning

confidence: 99%

Predicting Online Student Effort with Accelerometer, Heart Rate Sensors, and Camera Using Random Forest Regression Model

Harada¹

2022

IJMECS

View full text Add to dashboard Cite

show abstract

“…There are applications developed for parents and teachers to assign, monitor and analyze the efficiency while performing assignments with the use of smartphones and eye tracking solutions [9]. There are other computer vision based posture tracking for checking student attentiveness [10]. The need for proper lighting and various other factors such as user intervention at regular intervals are really important for these systems to function as desired.…”

Section: Related Workmentioning

confidence: 99%

Real Time Vigilance Detection using Frontal EEG

Ganesh¹,

Gurumoorthy²

2021

IJCSIT

View full text Add to dashboard Cite

Vigilance of an operator is compromised in performing many monotonous activities like workshop and manufacturing floor tasks, driving, night shift workers, flying, and in general any activity which requires keen attention of an individual over prolonged periods of time. Driver or operator fatigue in these situations leads to drowsiness and lowered vigilance which is one of the largest contributors to injuries and fatalities amongst road accidents or workshop floor accidents. Having a vigilance monitoring system to detect drop in vigilance in these situations becomes very important. This paper presents a system which uses non-invasively recorded Frontal EEG from an easy-to-use commercially available Brain Computer Interface wearable device to determine the vigilance state of an individual. The change in the power spectrum in the Frontal Theta Band (4-8Hz) of an individual’s brain wave predicts the changes in the attention level of an individual - providing an early detection and warning system. This method provides an accurate, yet cheap and practical system for vigilance monitoring across different environments.

show abstract

“…While e-learning users are closer to our proposed demographic, the similarities in methodology and findings suggests that studies performed on driver inattentiveness is highly applicable to stationary environments. In regards to monitoring emotional distraction, Revadekar et al [10] performed a relevant study on gauging student attention in e-learning environments by measuring facial expression in addition to posture, lean, and head movement.…”

Section: Mapping Facial and Physical Motionmentioning

confidence: 99%

“…PERCLOS refers to the proportion/ percentage of the time in a minute that a subject's eye is more than eighty percent closed. Facial expressions can also be used to determine fatigue and distraction, as previous research has indicated that non neutral facial expressions suggest that when a subject is dwelling on an emotion for longer than a given threshold [10], they may become inattentive to an assigned task.…”

Section: Introductionmentioning

confidence: 99%

How Facial Features Convey Attention in Stationary Environments

Domantay¹

2021

Preprint

View full text Add to dashboard Cite

Awareness detection technologies have been gaining traction in a variety of enterprises; most often used for driver fatigue detection, recent research has shifted towards using computer vision technologies to analyze user attention in environments such as online classrooms. This paper aims to extend previous research on distraction detection by analyzing which visual features contribute most to predicting awareness and fatigue. We utilized the open source facial analysis toolkit OpenFace in order to analyze visual data of subjects at varying levels of attentiveness. Then, using a Support-Vector Machine (SVM)we created several prediction models for user attention and identified Histogram of Oriented Gradients (HOG) and Action Units to be the greatest predictors of the features we tested. We also compared the performance of this SVM to deep learning approaches that utilize Convolutional and/or Recurrent neural networks (CNN's and CRNN's).Interestingly, CRNN's did not appear to perform significantly better than their CNN counterparts. While deep learning methods achieved greater prediction accuracy, SVMs utilized less resources and, using certain parameters, were able to approach the performance of deep learning methods.

show abstract

Gauging attention of students in an e-learning environment

Cited by 27 publications

References 18 publications

Predicting Online Student Effort with Accelerometer, Heart Rate Sensors, and Camera Using Random Forest Regression Model

Predicting Online Student Effort with Accelerometer, Heart Rate Sensors, and Camera Using Random Forest Regression Model

Real Time Vigilance Detection using Frontal EEG

How Facial Features Convey Attention in Stationary Environments

Contact Info

Product

Resources

About