Predictive Analytics for Smart and Connected Systems

The Internet of things (IoT) enabled systems have become increasingly available in practice. Examples include GM's OnStar® tele-service system, the InSite® telemonitoring system from GE, smart home appliances and various personalized remote patient monitoring systems. The unprecedented data availability in such connected systems provides significant opportunities for smart data analytics but, at the same time, it reveals critical challenges. First, the high dimensional stream data with heterogeneity, diverse data types and complex spatiotemporal structure often hinders establishing a unified analytics framework. Second, individual-level data has become available in large scale and consequently, there is a pressing need for individualized modeling and prediction. In this talk we try to address some of these challenges, through data analytics methodologies specifically tailored for IoT enabled smart and connected systems.

Specifically, we establish a non-parametric modeling framework based on transfer/multitask learning that can predict the evolution of condition/system monitoring signals through borrowing strength from historical and in-service data. This framework leverages on multivariate gaussian processes and functional graphical models to establish a unified data analytics framework that can incorporate functional heterogeneity and diverse data types both quantitative and qualitative. Further, a generic distributed estimation scheme for functional data that scales efficiently to high dimensions and minimizes the negative transfer of knowledge between uncorrelated functional outputs is proposed. Consistency in estimation and variable selection (oracle property) are then established. The methodologies are validated using numerical studies and a case study with real world data in the application to cloud-based vehicle health monitoring service systems.

Raed Al Kontar is an Assistant Professor in the Department of Industrial & Operations Engineering at the University of Michigan and an affiliate with both the Michigan Institutes for Data science (MIDAS) and Computational Discovery and Engineering (MICDE). His research broadly focuses on developing data analytics and decision-making methodologies specifically tailored for Internet of Things (IoT) enabled smart and connected products/systems.

Raed received his Ph.D. in Industrial and Systems Engineering and M.S in Statistics from the University of Wisconsin Madison in 2018. He also received his B.S in Civil and Environmental Engineering with a minor in Mathematics from the American University of Beirut (AUB) in 2014. Some of his awards include: Best Paper Award Finalist from Quality, Statistics, and Reliability (QSR) Section of INFORMS 2018, Best Student Paper Award Winner from QSR Section of INFORMS 2017; E. Wayne Kay Graduate Scholarship from the Society of Manufacturing Engineers (SME), Gilbreth Memorial Fellowship from Institute of Industrial and Systems Engineers (IISE); Most innovative paper approach from UW Madison; Early Excellence in teaching award from UW Madison; Valedictorian and student speaker in the graduation commencement ceremony at AUB.