1. PERCEPOLIS: Pervasive Cyberinfrastructure for Personalized Learning and Instructional Support INTRODUCTION The overarching objective of the PERCEPOLIS project is to develop educational cyberinfrastructure that facilitates resource sharing, collaboration, and personalized learning in higher education. We leverage advances in agent-based software engineering, databases, global information sharing processes, and pervasive computing to create this cyberinfrastructure. PERCEPOLIS promotes and enables three key changes to currently dominant pedagogy: Modular course development and offering Blended learning Networked curricula The modular approach increases the resolution of the curriculum and allows for finer-grained personalization of learning processes and associated data collection. Each course is decomposed of into several topics, some of which are mandatory, per course/curriculum objectives. Additional, elective topics that can be provided to reinforce prerequisites, or present more advanced topics. Associated with each topic are teaching (intended for instructors) and learning (intended for students) artifacts. Examples include lectures’ slides, assignments, and experiential artifacts such as individual and group projects. In blended learning, online, computer-mediated instruction supplements traditional classrooms. This allows class time to be used for active learning, interactive problem-solving, and reflective instructional tasks, rather than traditional lectures. In a networked curriculum the components form a cohesive and strongly interconnected whole, where learning in one area reinforces and supports learning in other areas. Student: Amir Bahmani, PhD student, Department of Computer Science Faculty Advisors: Dr. Sahra Sedigh, Department of Electrical and Computer Engineering and Dr. Ali Hurson, Department of Computer Science PROPOSED APPROACH One goal of PERCEPOLIS is to facilitate selection of a personalized trajectory (topics and artifacts) for each student, based on his or her background, interests, and needs. The following information is utilized in personalization: A detailed profile of each student. Detailed information about each course topic and artifact. Course objectives and curricular requirements. PERCEPOLIS serves as middleware that links the databases containing this information. From the computing point of view: Each artifact is tagged with metadata. The Summary Schemas Model (SSM) is utilized to create a curricular taxonomy, that represents the relationships among various topics in the curriculum. SSM has been developed to support automatic identification of semantically similar/ dissimilar data that have different/same names and representations. Agent-based software uses SSM to identify appropriate topics/artifacts for each student. CONCLUSIONS PERCEPOLIS supports a shift from teaching technical skills to fostering the professional expertise required for a student to succeed as a practicing engineer. The development of PERCEPOLIS will yield advances in pervasive computing, multi-agent systems, and distributed databases. MAIN RESEARCH TASKS This doctoral research started in Sept. 2010 and is in the exploratory phase. Near-term research tasks include the following: Literature review (FS 2010 - SP 2011) Prototyping (SP 2011) Developing the multi-agent system with IBM Aglets framework Refining the Summary Schemas Model Designing a distributed database of learning artifacts for select CS/CpE courses (CpE 111, CpE 213, CS 301) These tasks will enable refinement of the research focus. ACKNOWLEDGEMENTS This research was supported in part by the Missouri S&T Intelligent Systems Center. RELATED WORK Research on training and learning in virtual environments, e.g., Medulla [FKP09], MASCARET [BQD04], and HERA [ALB08]. Research on multi-agent architectures with focus on distance education systems and intelligent tutoring systems, e.g., [DLF03] and [WBP01]. Frameworks focused on knowledge creation and course management processes, e.g., [VSM07] and [PIR05]. Research on pervasive computing, mobile agent technology, and distributed, heterogeneous multi-database systems. REFERENCES [FKP09] M. R. FOX, H. KELLY, S. PATIL: “Medulla: A cyberinfrastructure-enabled framework for research, teaching, and learning with virtual worlds”, In Online Worlds: Convergence of the Real and the Virtual, Springer-Verlag, pp. 87–100, 2009. [DLF03] F.A. Dorça, C.R. Lopes, and M.A. Fernandes: “A Multiagent Architecture for Distance Education Systems”, Proceedings of the 3rd IEEE International Conference on Advanced Learning Technologies (ICALT 2003), pp. 368-369, 2003. [PIR05] S. Piramuthu: “Knowledge-based web-enabled agents and intelligent tutoring systems”, IEEE Trans. Educ., vol. 48, no. 4, pp. 750–756, Nov. 2005. [BQD04] C. Buche, R. Querrec, P. De Loor, and P. Chevaillier. MASCARET: “ A Pedagogical Multi-agent System for Virtual Environment for Training”, International Journal of Distance Education Technologies (JDET), pp.41-61, November 2004. [ALB08] K. Amokrane, D. Lourdeaux, and J. Burkhardt, “Hera: Learner tracking in a virtual environment”, IJVR : International Journal of Virtual Reality, vol. 7, no. 3, pp. 23–30, September 2008. [WBP01] C. Webber, L. Bergia, S. Pesty, and N. Balacheff, “The Baghera project: a multi-agent architecture for human learning”. In J.I. Vassileva, ed., Workshop on Multi-Agent Architectures for Distributed Learning Environments, pp. 12–17, San Antonio, USA, 2001. [VSM07] Y. Vovides, S. Sanchez-Alonso, V. Mitropoulou, and G. Nickmans, “The use of e-learning course management system to support learning strategies and to improve self-regulated learning”, in Educational Research Review, Vol 2, Issue 1, pp. 64-74, 2007. Partial Taxonomy of CS /CpE Curricula Sample environment for a course on design and analysis of algorithms Overview of proposed cyberinfrastructure