Predictive Model of Undergraduate Student Grading Using Machine Learning for Learning Analytics

Predicting the academic achievement has become very important for university students as well as lecturers, especially during the difficult times of pandemic Covid-19, online distance learning (ODL) with some students need to do part-time job due to financial problems. Furthermore, we are surrounded by a plethora of digital entertainment, such as social media platforms and mobile games, which may also serve as a distraction and undermine students' commitment to their studies. Therefore, this paper develops a model to predict student academic performance using Machine Learning approaches. The model is developed by training the dataset acquired that consists of demographic information, study preparation, academic performance and motivation from the students in a public higher institution in Malaysia. The model is also tested on the public dataset related to student academic performance. The findings showed that JRip classifier have obtained the best accuracy of 92% for the newly collected data and 100% accuracy by using Random Forest classifier on the public dataset. The developed model and data visualization are useful for the development of learning analytics system which students and lecturers can make an early intervention and determining whether students need to take necessary actions to improve their academic results in real-time, as well as gaining a better understanding of the factors that may affect their academic performance. © 2022 IEEE.

Performance Evaluation of Masked Face Recognition using Deep Learning for Covid-19 Standard of Procedure (SOP) Compliance Monitoring

Wearing a face mask can reduce the risk of Covid-19 transmission. As a reason, creating an effective masked face recognition model is critical for the development of an autonomous face mask wearing monitoring system. Manual way of face mask wearing monitoring is a tedious task especially in the crowd and large public areas. Furthermore, masked face recognition is complex due to variety of face mask wearing image appearances such as occlusions, calibrations, scene complexity and the types of face mask used. This paper provides the performance evaluation of the Deep Convolutional Neural Network (CNN) model and machine learning classifiers for masked face recognition. Specifically, DENSENET201, NASNETLARGE, INCEPTIONRESNETV2 and EFFICIENTNET (EFFNET) as a feature extractor. Then, the extracted features are classified by using Support Vector Machine (SVM), Linear Support Vector Machine (LSVM), Decision Tree (DT), K-nearest neighbour (KNN) and Convolutional Neural Network (CNN). The recognition model is evaluated on the face mask detection dataset. The experiment results have shown that DENSENET201-SVM and EFFNET-LSVM obtained the best classification accuracy of 0.9972. However, EFFNET-LSVM has the advantage of better computational time of feature extraction, classification as well as the size of features.