Using Convolutional Neural Network to Recognize Learning Images for Early Warning of At-Risk Students

Project Code :TCMAPY225

Objective

The objective is to propose two innovative approaches called “one-channel learning image recognition” (1-CLIR) and “three-channel learning image recognition” (3-CLIR) to take advantage of the advanced CNN framework to improve the predictive model’s performance.

Abstract

Instructional design is crucial in online courses and scholars have found its connections with student’s learning performance. Due to the lack of face-to-face interactions and observations in online learning, the considerations involved in the design of an effective online course can be significantly different than those in a face-to-face course, which is also why many higher education institutions provide instructional designers to support faculty members. In fact, institutions invest substantial resources aimed at supporting learners in overcoming learning obstacles associated with the characteristics of online learning environments.

The results indicate both methods can significantly capture more at-risk students (the highest average recall rate is equal to 77.26%) than the following machine learning algorithms—Support Vector Machine (SVM), Random Forest (RF), and Deep Neural Network (DNN) in the middle of the semester.

Keywords: Convolution Neural Networks, Machine Learning, Distance Learning, Image Recognition, At-Risk, Early Warning, Prediction.

NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.