Yundong Cai

Agents as intelligent user interfaces for the net generation

Riding on the back of the rapid expansion of the Internet, online virtual worlds which combine the prowess of interactive digital media and social networks have attained a high level of acceptance among the Net Generation users. This development prompted researchers to look into the potential of embedding learning contents into virtual worlds to create virtual learning environments (VLEs) that suit the need of the Net Generation learners. However, the special characteristics of virtual worlds that make them popular also pose great challenges to educators who wish to leverage their power. These challenges call for more sophisticated human computer interaction (HCI) mechanisms to assist learners to navigate the intriguing landscape of VLEs. In this paper, we demonstrate a teachable remembrance agent which acts as an intelligent user interface to provide innovative ways for students to interact with VLEs.

Creating an Immersive Game World with Evolutionary Fuzzy Cognitive Maps

The Evolutionary Fuzzy Cognitive Map improves on serious games by modeling both fuzzy and probabilistic causal relationships among the games variables. It permits asynchronous updates of the variables so that they can evolve dynamically and stochastically. These improvements give players a more engaging, immersive experience.

Context modeling with Evolutionary Fuzzy Cognitive Map in interactive storytelling

To generate a believable and dynamic virtual world is a great challenge in interactive storytelling. In this paper, we propose a model, namely evolutionary fuzzy cognitive map (E-FCM), to model the dynamic causal relationships among different context variables. As an extension to conventional FCM, E-FCM models not only the fuzzy causal relationships among the variables, but also the probabilistic property of causal relationships, and asynchronous activity update of the concepts. With this model, the context variables evolve in a dynamic and uncertain manner with the according evolving time. As a result, the virtual world is presented more realistically and dynamically.

Socializing Pedagogical Agents for Personalization in Virtual Learning Environments

Personalization in virtual learning environments is the system ability to provide individualization and a set of personalized services such as personalized content management, learner model, or adaptive instant interaction. The intelligent agent technology has potential regarding the creation of such personalized, adaptive and interactive e-learning applications. However, most of the available solutions have so far focused on porting existing courses with traditional teaching methods onto the virtual environments, making them available in an attractive animated interface without any fine-tuning and adaptation to the learner needs. This paper proposes a novel market-inspired collaboration model where the agents are self-interested autonomic elements collaborate to achieve a comprehensive learner model. Mentor agent makes decisions on top of a Dempster-Shafer belief accumulation to help student whenever she believes student has lost the clues and needs help. Proposed architecture is validated by applying on a sample agent augmented virtual environment designed to engage and motivate students at the lower secondary level in Singapore. Extensive experiments illustrate the effectiveness of the proposed interaction model where students have found the mentor agent as believable as a virtual teacher.

Internet of Things Based Data Driven Storytelling for Supporting Social Connections

The empty nest syndrome has become a significant modern social problem. Recent research has enhanced physical health monitoring for the elderly in smart home environment. However, the social needs of the empty nesters have been less supported in smart home designs. A compelling story about the elderly can make the adult children emotionally attached to their elderly parents and establish a healthy social connection between them. In this work, we propose a data-driven story generation system based on the Internet of Things (IoT). IoT based techniques enable the real time collection of the elderlys environment data through various sensors located in the home. The story generation system can weave the information mined from the sensor data into a story with high persuasive and emotion arousing power. Our system automatically collects raw sensor data on the cloud server and maps them to values of semantically meaningful context variables through activity functions. A director agent organizes the story plot with a Goal Net based approach and dynamically generates storylines based on a set of scene selection rules. The proposed system is carefully studied with a simulated smart home environment.

Towards an Integrated Design of Digital Library and Virtual Museum in the Heritage Preservation of the Chinese “Qipao”

As treasure houses of human history and knowledge with rich repositories on cultural heritage, museums and libraries have advantages of presence experience and powerful searching abilities respectively. We propose in this paper an integrated design of virtual museum and digital library in the preservation of cultural heritage of the Chinese “qipao”, as an example of preservation of cultural heritage resources in digital space.

Agent-Oriented methodology for interactive storytelling (AOMIS)

Interactive virtual storytelling attracts a lot of research interests to create engaging, interactive and dynamic storytelling. However, it is still a great challenge to create an interactive storytelling system from text-based stories for novice. In this paper, we propose an easy-to-use Agent-Oriented Methodology for Interactive Storytelling (AOMIS) to guide novice to generate interactive storytelling system. In this methodology, interactive storytelling system is constructed as a multi-agent system of director agent and character agents. The interactive storytelling is simulated as the goal pursuing of the agents with respect to user interactions and context changes. By viewing the interactive storytelling in the perspective of goal-oriented agents, our methodology is a hybrid of plot-oriented interactive storytelling and character-based interactive storytelling.