Online learning has been widely applied due to developments in information technology. However, there has no evaluation and application for primary school students. All innovation efforts in learning are directed at improving the quality of education by creating an active learning atmosphere for students. Students’ participation in the teaching-learning process can be improved by selecting appropriate learning materials suitable to the student’s learning style. The research aims to develop and measure the impact of an Artificial-Intelligence (AI)-based learning style prediction model in an online learning portal for primary school students. The subjects were recruited from Indonesian primary school students in grades 4 to 6. To fulfill the principle of personalized learning, the AI model in the online learning portal was designed to recommend learning materials that suit students’ learning styles. We formulated a new AI approach that enables collaborative filtering-based AI models to be driven by learning style prediction.With this AI algorithm, the online learning portal can provide material recommendations tailored specifically to the learning style of each student. The AI model performance test achieved satisfactory results, with an average RMSE (Root Mean Squared Error) of 0.9035 from a rating scale of 1 to 5. Moreover, students’ learning performance was improved based on the results of t-test analysis on 269 subjects between the pre-test and post-test scores.

In building management, energy optimization is one of the main concern that needs to be automated. For automation, an intelligent system needs to be developed. However, an intelligent system needs to be trained in a large dataset before it can be used reliably. In this paper, we present a transfer learning scheme to develop an intelligent system for smart building management system. Specifically, the intelligent system is able to count human inside a room, which can be utilized to adaptively adjust energy usage in a room. The transfer learning scheme employs a deep learning model that is pretrained on ImageNet dataset. To enable the human counting capability, the model is trained on a dataset specifically collected for human counting case.

Current approaches of university students’ Grade Point Average (GPA) prediction rely on the use of tabular data as input. Intuitively, adding historical GPA data can help to improve the performance of a GPA prediction model. In this study, we present a dual-input deep learning model that is able to simultaneously process time-series and tabular data for predicting student GPA. Our proposed model achieved the best performance among all tested models with 0.4142 MSE (Mean Squared Error) and 0.418 MAE (Mean Absolute Error) for GPA with a 4.0 scale. It also has the best $R^{2}$ -score of 0.4879, which means it explains the true distribution of students’ GPA better than other models.