Complex Decision Systems Laboratory
The Complex Decision Systems Laboratory is focused on applying the physics of complex systems and the mathematics of information theory to the development of robust decision systems. Improving the quality of machine decisions depends on accurately managing uncertainty. Through a generalization of Shannon’s Information Theory we have developed a Risk Profile metric to analyze the accuracy, decisiveness and robustness of probabilistic forecasts. The metric also underlies an innovative approach to information fusion, which we are applying to novel machine learning methods. The goal of the laboratory is to develop tools for artificial intelligence which will incorporate the complexity of heavy-tail distributions and long-range correlations found in natural systems.
The methods have been applied to radar tracking and discrimination, blind demodulation of signals, detection of cyber-security anomalies and multi-sensor fusion. We are exploring applications in modeling of financial and biological systems.
Principal Investigator
Dr. Kenric Nelson is a Research Professor with Boston University Electrical & Computer Engineering and a Senior Principal Engineer with Raytheon Integrated Defense Systems. At Boston University he is developing a novel approach to information theory for complex systems. At Raytheon he leads projects on sensor management, tracking, discrimination, and debris mitigation. He has multiple inventions applying non-additive information theory to improve the robustness of radar processing and enable efficient probabilistic computation. His education in electrical engineering includes a B.S. degree Summa Cum Laude from Tulane University, a M.S. degree from Rensselaer Polytechnic Institute, and a Ph.D. degree from Boston University. His education in Program Management includes an Executive Certificate from MIT Sloan and certification with the Program Management Institute. His research interests include machine learning, complex adaptive signals and systems, and sensor systems.
Collaborators
Sabir Umarov, University of New Haven Mathematics
Mark Kon, Boston University Mathematics
Eugene Stanley, Warren Distinguished Professor, Boston University
Constantino Tsallis, Brazilian Physics Research Center
Greg McDaniel, Mechanical Engineering, Boston University
Wenchao Li, Electrical and Computer Engineering, Boston University
Avi Pfeffer, Chief Scientist, Charles River Analytics
Paul Work, Principal Engineering Fellow, Raytheon