System of Systems Signature Area Seminar - Wed., Jan. 22
|Event Date:||January 22, 2014|
|Hosted By:||College of Engineering
|Location:||RHPH 164, WL campus
The engineering of interconnected systems must take uncertainty into account to ensure optimal performance, because design and control are constrained by disturbances and limited knowledge. This talk introduces a data-driven framework to accelerate system engineering by establishing a feedback loop between modeling and experimentation. The approach consists of design, modeling and optimization. Firstly, I present an experimental design method for efficient modeling and prototyping. I prove formal guarantees of near-optimality and efficient computation for maximizing the mutual information between data and models. Secondly, I introduce an approximate Bayesian inference method to select multiscale models of interaction networks from heterogeneous data. Finally, I indicate how to select the best tradeoff between the task-specific informativeness of an empirical solution and its stability with respect to noise and missing data.
The application of this framework to computer-based tutoring systems enabled the individualized treatment of learning disabilities; moreover, it proved instrumental in modeling metabolic signaling systems, proving for the first time the nuclear phosphorylation of Msn2, a process involved in cancer and obesity. Future research will look at the human body as part of an interconnected system to better design personalized diagnostics and therapeutics. I claim that numerous other engineering applications can benefit from the development of similar data-driven approaches.
Dr.Sc. Busetto is a researcher at the Automatic Control Laboratory and at the Competence Center for Systems Physiology and Metabolic Diseases, ETH Zurich, where he is establishing an initiative to engineer systems for personalized biomedicine and individualized teaching. His research focuses on data-driven modeling of systems characterized by interactions with hard-to-predict human and faulty components.
Dr.Sc. Busetto received the ETH Medal for Outstanding Doctoral Thesis for predictive modeling of complex dynamical systems. He has been awarded the Best Student Paper at the IC in AI in Education for modeling human engagement with intelligent tutoring, and the Best Paper at the IEEE IC in Computational Science and Engineering for systems biology. He received the Best Master Thesis Award at the University of Padua, Italy, for computational system nanotech. He is a researcher at SystemsX.ch, the Swiss Initiative in Systems Biology and one of the largest ever partnerships in biomedicine, and initiated collaborations in regenerative medicine, wind energy, and intelligent tutoring. His research appears in top-tier journals (such as Nature Methods, Science Signaling, PLoS Comp.Bio.) and his collaboration projects received significant media coverage on television, radio, general and specialized press (SF1, ORF, APA, der Standard).