Oral Presentation Time: 1400-1500

Venue: Fanling Room, Lower Level I

Presenter(s)

– Dr Richard Wing Cheung LUI, Senior Lecturer, Department of Computing, The Hong Kong Polytechnic University

Abstract

This presentation introduces the design and implementation of GPTutor, a Generative AI (GenAI) powered Intelligent Tutoring System (ITS) developed at the Hong Kong Polytechnic University (PolyU). GPTutor aims to enhance student learning experiences through personalised tutoring and interactive exploration. It helps students gain a deeper understanding of the course materials provided by their instructors. During the first phase of our implementation, we developed features for instructors to upload and manage their course content and to create learning scenarios based on the learning content. The system includes a conversational interface for students to ask questions and explore course content to deepen their understanding. As the answers are generated based on the instructor-uploaded content, GPTutor provides more factual responses, reduces hallucinations, and aligns better with the instructors’ intended learning outcomes (ILO). We will also share findings from our pilot study, which involved approximately 200 undergraduate and postgraduate students at PolyU. Finally, we will discuss our future plans for further development and enhancement of the platform.

Theme: 1. Showcase Project Achievements

Sub-theme: Innovative Technology-in-Education

Poster Presentation Time: 1225-1400; 1500-1600

Venue: I1, Tai Po-Shek-O Room, Lower Level I

Presenter(s)

– Dr Selena YAN, Senior E-learning Assistant, Li Ka Shing Faculty of Medicine, The University of Hong Kong

– Ms Leah LI, Senior E-learning Assistant, School of Clinical Medicine, The University of Hong Kong

Abstract

Generative Artificial Intelligence (GenAI) is a transformative technology that fosters creativity, problem-solving, and critical thinking skills in various industries, including healthcare and medical education. At HKU Medicine, we appreciate the importance of advancing GenAI literacy and propose to develop and deliver a new online course that covers the latest advances, pitfalls, ethical and professional aspects of GenAI. We aim to advance AI and digital competency for all students, professoriates and clinicians at HKU Medicine and the Hong Kong medical community. To evaluate the effectiveness of this online GenAI literacy course, an assessment study will be conducted. We will use a mixed methods approach to collect both quantitative and qualitative data through pre- and post- surveys, individual interviews and practical exercises. The survey will be adapted from the “Scale for the Assessment of Non-Experts’ AI Literacy” (SNAIL), while the interviews will provide additional context and insights into participants’ experiences and challenges with GenAI. Practical exercises will provide objective data for evaluation. Target participants will be recruited through convenience sampling, and data analysis will include both statistical and thematic analyses. The study has already obtained ethical approval. Results from this study will be used to identify improvement needs for the online course and inform the integration of GenAI in medical and health sciences education and clinical practices. Overall, the project will contribute to the advancement of GenAI literacy in medical education and healthcare professions, supporting the ethical and effective application of GenAI technology in these fields.

Theme: 1: Showcase Project Achievements

Sub-theme: 1.2  Fund for Innovative Technology-in-Education (FITE)

Poster Presentation Time: 1225-1400; 1500-1600

Venue: I4, Tai Po-Shek-O Room, Lower Level I

Presenter(s)

– Dr Yanjie SONG, Associate Professor, Department of Mathematics and Information Technology, The Education University of Hong Kong

– Mr Kaiyi WU, Department of Mathematics and Information Technology, The Education University of Hong Kong

Abstract

Integrating artificial intelligence (AI) into educational settings is crucial for developing innovative teaching methods that enhance student learning. This study investigates the development and application of Learningverse, a 2D/3D metaverse platform that integrates digital humans with advanced Large Language Model Operations (LLMOps) to create AI teaching agents. Leveraging the capabilities of Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG), we designed intelligent digital human teachers. These LLMOps system-constructed multi-agents, including Communication Encoder, Body Movement Coding Encoder, Eye Gaze Coding Encoder, and Expression Coding Encoder, provide personalized and strategic scaffolding to students, offering real-time feedback and support to improve their learning outcomes. Additionally, the platform utilizes GPT-SoVITS trained TTS to clone real teachers’ voices, enhancing the realism of digital human teachers. The platform can customize digital teachers and build scenarios based on different subject courses, adapting them to various thematic curricula. A pilot study evaluated the effectiveness of these digital teachers in enhancing student engagement and performance in Learningverse. Preliminary findings reveal a significant improvement in students’ interactions, motivation, and overall learning achievements. This research highlights the potential of LLMOps-integrated digital human teachers in transforming teaching practices and enriching educational experiences in the metaverse.

Theme: 1. Showcase Project Achievements

Sub-theme: 1.2  Fund for Innovative Technology-in-Education (FITE)

Oral Presentation Time: 1400-1500
Poster Presentation Time: 1225-1400; 1500-1600

Oral Presentation Venue: Fanling Room, Lower Level I
Poster Presentation Venue: I2, Tai Po-Shek-O Room, Lower Level I

Presenter(s)

– Dr Ting Leung Albert LEE, Lecturer, Department of Electrical and Electronic Engineering, The University of Hong Kong

– Dr Victor LEE, Lecturer, Department of Electrical and Electronic Engineering, The University of Hong Kong

– Dr Zhengyuan WEI, Research Associate, Department of Electrical and Electronic Engineering, The University of Hong Kong

– Mr Alex KIANG, The University of Hong Kong

Abstract

Retrieval-augmented generation (RAG) has been demonstrated to be highly effective in generative AI applications, resulting in substantial improvement in accuracy and reliability of large language model responses. The success of this approach is accomplished through seamless integration of AI capabilities and practical knowledge base, which fosters an interactive learning mechanism conducive to automatic question-answering augmented with references and refined prompts, leading to a more vibrant and connected learning environment. Communication portals enable effective inquiry and prompt responses while the course-specific chatbot helps reduce teachers’ workload and streamline classroom management. In this project, the RAG approach is applied to a discipline-core course named Integrated Design Project (IDP) in the second semester 2023-24. This project-based course consists of 78 EEE undergraduate students with diverse programming experience. The IDP-specific AI chatbot is developed using the Coze platform with a Discord server. To name a few, the main contents of practical knowledge base include the procedures for setting up a Raspberry Pi webcam, the installation process of Jetson Inference library on Jetson Nano, how to use YOLO model for object detection, how to install Jetson inference library on Jetson Nano, etc. The anonymous feedback survey conducted at the end of the course shows high utilization and satisfaction of the chatbot, confirming the effectiveness of this approach in facilitating students’ learning.

Theme: 1. Showcase Project Achievements

Sub-theme: Innovative Technology-in-Education

Poster Presentation Time: 1225-1400; 1500-1600

Venue: I3, Tai Po-Shek-O Room, Lower Level I

Presenter(s)

– Ms Winnie WONG, Educational Development Manager, Centre for Learning, Teaching and Technology, The Education University of Hong Kong

– Mr Vincent CHAN, Educational Development Assistant, Centre for Learning, Teaching and Technology, The Education University of Hong Kong

Abstract

Background and Objectives: This project aims to leverage the immersive capabilities of the metaverse to enhance data security and privacy awareness among students and staff at the Education University of Hong Kong. Develop a series of interactive and engaging educational materials to enhance the understanding of data security principles and data privacy policies. Design and implement a dynamic and user-friendly online platform (Metaverse Space) to host the educational materials, facilitating easy access and learning for target audiences. Methods and Findings: Within this metaverse-based platform, users are presented with practical scenarios that simulate real-world situations involving security-critical concepts. The educational virtual environment is strategically gamified to motivate users through rewarding challenges and progressive levels, bridging the gap between theory and practice. The dynamic simulation exercises allow participants to directly experience the impact of security failures and rehearse protective actions in a risk-free, controlled setting, nurturing applied skills alongside conceptual understanding. The survey results, based on responses from (n=20), indicate that the gamified metaverse prototype is both engaging and effective in teaching data security and privacy concepts. The interactive scenarios and simulations were particularly praised for their usefulness in understanding real-world data security issues. The navigation of the metaverse environment was generally considered easy. Overall, the positive responses suggest that the gamified metaverse is a valuable tool for learning data security, demonstrating its effectiveness in an educational context. Discussion and Perspectives: Leveraging Metaverses data security learning platform offers an innovative and immersive approach to addressing the limitations of traditional training methods, empowering users with comprehensive knowledge and applied skills to mitigate evolving cyber threats.

Theme: 1. Showcase Project Achievements

Sub-theme: 1.2  Fund for Innovative Technology-in-Education (FITE)

Poster Presentation Time: 1225-1400; 1500-1600

Venue: K1, Tai Po-Shek-O Room, Lower Level 1

Presenter(s)

– Dr Laura ZHOU, Education Development Officer, Education Development Centre, The Hong Kong Polytechnic University

– Mr Leo WONG, Project Associate, Education Development Centre, The Hong Kong Polytechnic University

Abstract

The flipped learning and teaching approach redefines the traditional classroom dynamic by swapping the order of direct instruction and homework activities. In a flipped classroom, students engage with instructional materials (such as videos, readings, or podcasts) outside of class, freeing up valuable in-class time for active learning, collaborative activities, and deeper understanding. In our quest to promote effective flipped learning and teaching practices, we conducted comprehensive interviews with experienced teaching staff at PolyU, who have successfully integrated this methodology into their course. Their valuable insights were collected and compiled into case studies, which were then disseminated to all teaching staff members through e-newsletters and experience sharing workshops. These teaching cases serve as compelling examples, showcasing the versatility and impact of flipped learning and teaching. They underscore the significance of adapting pedagogical methods to enhance student learning experiences. By shifting the locus of content consumption outside the classroom, educators empower students to actively engage with the material during face-to-face sessions, fostering a deeper understanding and more meaningful interactions.

Theme: 1: Showcase Project Achievements

Sub-theme: 1.2  Fund for Innovative Technology-in-Education (FITE)