This project, purchasing networking equipment, a database server, file servers, and digital video editing, supports the following research projects: Intelligent desktop interfaces, Large-scale pedestrian evacuation simulation, and Insect recognition and population counting for environmental monitoring. In order to provide computer users with a more timely and useful application context, the 1st project, Task Tracer, develops machine learning algorithms for understanding task context and a new paradigm for desktop interface design. The 2nd project produces large volumes of motion data of people with varying abilities (able-bodied, wheel chair mobile, etc.) for distribution to the pedestrian simulation community via the web. New and accurate models for 2- and 3-dimensional representations of human motion for heterogeneous crowds are expected from this work. Image processing and computer vision techniques for segmenting and identifying various insects are employed in the last project; whereas machine learning techniques are utilized for processing this data to classify the insect into the proper genus species. This project should result in new devices for imaging insect specimens.
Broader Impact: This research should improve the effectiveness of computers for: Understanding and streamlining human productivity with computer systems, Helping emergency personnel to better understand and respond to emergency egress situations, and Automating the recognition and counting of insect populations for important environmental monitoring activities.
