Two ISIS professors have received National Science Foundation awards in the area of intelligent learning environments and distributed real-time embedded systems.
These awards are the result of stimulus funds from the American Recovery and Reinvestment Act of 2009.
The two awards are:
Formal Analysis of Choice-Adaptive Intelligent Learning Environments (FACILE) that support Future Learning
Principle Investigator: Professor Gautam Biswas
Educators often make use of computer technology to enhance the educational experience. For example, students can complete quests in game environments, engage in inquiry, interact with virtual agents, run science simulations, take quizzes, access the Web, and more generally make choices about different learning activities. The environment can then adapt intelligently by encouraging (alternative) choices.
This project continues this endeavor to expand the technological-educational impact by developing computer environments that permit student choice when learning, and design feedback that provides metacognitive support to the student for making better choices. In this way, students learn in the computer environment and transfer this learning toward making choices in real learning situations.
Studies will be run in a number of middle school science classrooms in Metro Nashville to demonstrate the effectiveness of the system.
Automating the Deployment of Distributed Real-time and Embedded System Software using Hybrid Heuristics-based Search Techniques
Principle Investigator: Professor Aniruddha Gokhale
Modern automobiles and flight avionics systems form complex distributed real-time and embedded (DRE) systems. For example, a high-end luxury car can have over 80 electronic control units (ECUs), which are small embedded processors, and multiple networks linking the processors. Furthermore, several hundred software components can be distributed across these multiple networked ECUs.
Optimizing the deployment of these software components by packing the software more tightly onto the processors can reduce the size of the required underlying infrastructure and have numerous positive side-effects, such as weight and power consumption savings.
Determining how to deploy software to hardware in DRE systems is a challenging problem due to the large number of complex constraints that must be dealt with, such as real-time scheduling constraints, component placement restrictions, and fault-tolerance guarantees. This research effort focuses on developing new hybrid heuristic and meta-heuristic techniques for determining how to deploy software to computational nodes. The algorithms and tools will be made available in open source through the Generic Eclipse Modeling System, which is distributed by 45 world-wide mirrors, and the ESCHER tool repository.
Opportunities for outreach will be sought at Vanderbilt through the NSF Science and Technology Center (called TRUST) and at the Vanderbilt Center for Science Outreach.