We propose the extension for Artificial Intelligence (AI)-supported learning recommendations within higher education, focusing on enhancing the widely-used Moodle Learning Management System (LMS) and extending it to the Learning eXperience Platform (LXP). The proposed LXP is an enhancement of Moodle, with an emphasis on learning support and learner motivation, incorporating various recommendation types such as content-based, collaborative, and session-based recommendations to provide the next learning resources given by lecturers and retrieved from the content curation of Open Educational Resources (OER) for the learners. In addition, we integrated a chatbot using Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) with AI-based recommendations to provide an effective learning experience.

The application of Generative Artificial Intelligence (AI) in early-stage design processes has emerged as a promising method for generating innovative solution concepts. However, AI-driven concepts may introduce secondary problems when implemented practically. This study proposes a systematic framework integrating Generative AI (GPT-4o), patent analysis using Retrieval-Augmented Generation (RAG), and Failure Mode and Effects Analysis (FMEA) to predict, evaluate, and mitigate potential risks. Applied to a case study on nickel recovery through froth flotation, the framework significantly enhanced the feasibility, usefulness, and sustainability of solution concepts. The research highlights the scientific contribution and practical benefits of combining Generative AI with structured risk-analysis methods for sustainable innovation.

Traffic congestions are common in every large cities. This paper presents Electronic Road Pricing system design prototype based on embedded system Raspberry Pi with RFID and image processing capability based on OpenALPR. The system works in a way that vehicle passing under the gantry will be recorded by photographing the image of license plate and reading the RFID tag. The image and tag will be serialized to XML and transmitted to server through a socket. The output is transaction record and license plate reading from OpenALPR. Early test showed that RFID is able to work optimal at range between 0–360 cm and is able to work at vehicles moving at 10, 20, and 40 Km/h except OpenALPR which failed two out of three tests because of minimum data training. After trained with 1000 Indonesian license plates, the OpenALPR is able to recognize nine out of ten that given randomly.