The unexpected closure of educational institutions as a result of the emergence of COVID-19 prompted the authorities to suggest adopting alternatives to traditional learning methods. E-learning is an innovative approach for delivering electronically mediated, well-designed, learner-centred interactive learning environments by utilizing internet and digital technologies with respect to instructional design principles. This paper presents the implementation and prototyping of an innovative web-based e-learning platform for chemistry course known as Al-Chemy. Al-Chemy was developed for foundation students at Tahmidi Centre, Universiti Sains Islam Malaysia. The rapid application development (RAD) methods have been used in developing Al-Chemy through website wix.com. Al-Chemy was structured with interactive notes, animation, virtual experiment, quizzes, and games. The combination of these activities helps students in learning basic and advanced concepts of chemistry.

Efficient management of household trash is essential to maintaining a sustainable society and a good environment. Low community engagement in environmental cleanup has led to dozens of unused refuse management apps. Today’s refuse management system lacks a secure identification protocol for identifying users, especially those who have signed up for the app. Predicting and understanding human household behavior is needed, and it remains a complex challenge. Therefore, this study aims to predict human household behavior in the refuse management system using artificial neural networks (ANN). The work involved in developing the prediction model included data collection, data pre-processing, neural network model development, and performance validation. There are 505 participants, urban residents in Kuala Lumpur obtained for this study. ANN with one hidden layer is developed in MATLAB. The results show that the accuracy of the developed model is 83%. It indicates that ANN performed well in predicting household behavior in the refuse management system.