I am an associate professor of computer science and a director of the Innovative Educational Compting Laboratory at North Carolina State University. I am also an affiliate of the Center for Educational Informatics.

My primary research focus is on the technology innovation and integration to advance the sciences of learning.

I am interested in the innovation and application of Artificial Intelligence technologies for students to learn, teachers to teach, and researchers to understand how people learn (and, more importantly, fail to learn!). I am therefore an engineer of transformative technologies and a practitioner to improve education.

I am also interested in studying the transformative theory of learning and teaching that brings us with the significant knowledge on how people learn and how people should be taught. I am therefore a learning scientist working on the empirical data collected from field studies conducted with the learning technologies that I invent.

One of the most challenging issues for online-courseware engineering is to maintain the quality of individual instructional elements contained in the courseware. To address this challenge, an evidence-based learning-engineering method for validating instructional elements on online courseware is proposed. Individual students’ learning trajectories on particular online courseware and their final learning outcomes are consolidated into a state transition graph. The state transition graph is then associated with pre-defined rewards on which the value iteration technique is applied to compute the converse policy, which by definition reflects worst actions (i.e., contents) taken to yield the least successful learning. We hypothesize that when the consolidated graph contains learning performance data collected from a large body of students, the converse policy accurately reflects ineffective instructional elements.