Prof. Clay Scott, assistant professor in the division of Electrical and Computer Engineering, was recently awarded an NSF CAREER grant for his research project, “Guided Sensing,” which offers a unique approach to the problem of mining the vast stores of information available for any given problem. Scott’s specific interest is to develop and apply new theory for biomedical applications.
To describe the project in general terms, in many complex problems related to discovery, detection, and diagnosis, researchers and practitioners alike are continually faced with the question “What data should I gather next?” When the possibilities for data collection are overwhelming, and experiments or measurements are costly or time-consuming, this question becomes all the more critical.
This research investigates guided sensing algorithms, which make recommendations about the next measurements to gather, with the understanding that a domain expert makes the final decision. This work develops new methods for guided sensing that account for temporal and task-based constraints, missing data, and environmental noise as well as human error.
More specifically, the proposed work is strongly connected to two motivating applications: (1) Rapid identification of toxic chemicals in emergency response situations; and (2) Design of flow cytometry experiments for analyzing cell-based diseases. Through collaborations with experts in each field, the methods developed will be disseminated to actual users and implemented in real systems.
The proposed work has the potential to impact potentially thousands or even millions of citizens who are victims of toxic chemical accidents or bioterrorism, or who suffer from hematological disorders such as lymphoma and leukemia. Furthermore, the proposed work will apply more broadly to other problems where rapid identification or sensor scheduling are critical, such as machine fault monitoring and remote sensing.
The educational component of this CAREER award is aimed at improving the motivation of college students taking their first course in Probability, a theoretical course that is required for electrical engineers. Prof. Scott teaches this course, and intends to peak students’ interest by relating the material to real-world problems through the introduction of three specific examples that will illustrate the theory being taught. Probability is often a student’s first exposure to the kind of abstract, mathematical thinking that characterizes advanced study in Signal Processing, Communication, and Control.
Clay Scott’s research interests include machine learning, pattern recognition, data mining, statistical learning theory, and statistical signal processing. He is particularly interested in the application of his research to real-world problems, especially in the biomedical field.
The CAREER grant is one of NSF’s most prestigious awards, conferred for “the early career-development activities of those teacher-scholars who most effectively integrate research and education within the context of the mission of their organization.”