nan Ailiya

The Design of Persuasive Teachable Agent

Teachable agents are pedagogical agents based on the concept of learning-by-teaching. Persuasion theory enhances the capabilities of teachable agents by influencing positive attitude change in learners. This paper proposes Persuasive Teachable Agent (PTA) that enables the selection of persuasive strategies based on persuasion theory to improve learning attitudes. In a preliminary study involving PTA, learners were observed to display increased interest in engaging in learning activities with the teachable agent.

Authoring Educational Games through Affective Teachable Agent

To take the advantage of computer-aided learning, more and more educational researchers realize the importance of encouraging teenagers to learn in their virtual life. To make the design and development of virtual games continuous and smooth, teachers should be involved in the learning content design iteratively. To this end this paper proposes an authoring tool which extends the teachable agent in Virtual Singapora project with authoring capabilities. In this way, not only educators can directly bring their ideas into the game design, but also the game developers can effectively implement the design to realize game scenarios. A preliminary study illustrates the effectiveness of this approach.

Persuasive Teachable Agent with Goal Net

A persuasive teachable agent (PTA) is a pedagogical agent which uses persuasion to encourage positive learning attitudes and behaviors in student tutors. This paper presents a life-like animated autonomous PTA in the 3D Virtual Learning Environments (VLE) which makes use of the Goal Net agent model and persuasion theory. The PTA aims to autonomously exert social influence on the student tutors, encouraging them to teach the PTA. A case study is also presented to illustrate our approach.

Persuasive Teachable Agent User Modeling

Teachable agents help students learn more effectively through the benefits of learning-by-teaching. Our field study has shown that learners do not benefit fully from learning with teachable agents due to a lack focus in engaging in learning tasks. We propose the persuasive teachable agent user model as a means to understand individual user learning needs through persuasion theory in order to address these issues, with a small group study displaying encouraging results in improving learning interest among learners.

Intrinsically motivated agent for service management in smart homes

We discuss the challenges of designing an adaptive service management for smart homes. Agents with intrinsic motivation are proposed to deal with environment uncertainty, incomplete information, and diversity of requirements. The proposed agent-mediate service is realized by a goal oriented approach, which can help service customers to make fast and intelligent decisions so as to achieve the user requirements on transparency, reliability, and interoperability. An experimental study shows the effectiveness of the proposed service management.

ELM-Based Agents for Grid Resource Selection

Resource selection in Grid involves great dynamics and uncertainties inherited from tasks and resources. The optimal selection of a resource against a task requires fast and intelligent services. Intelligent agent with fast learning capability is promising to resource selection problem in Grid. This paper proposes an Extreme Learning Machine (ELM)-based agent, in which an ELM connectionist module is embedded in an extended Belief-Desire-Intention (BDI) architecture. ELM empowers the agent with fast training and learning speed in the Grid environment. To improve generalization performance a cooperative learning among a group of ELM-based agents is proposed, for which the group decision is summarized upon individual decisions. The experiment results show that ELM-based agents are able to provide intelligent resource selection services, and the proposed cooperative learning outperforms the individual one.