You are here: Home NEWS & EVENTS Events Calendar
Events Calendar
  • [June 19, 2017]

    Adaptive sampling strategy for online monitoring of big data streams

  • Speaker:
    Kaibo Liu
    Monday, June 19, 2017
    Room 512, Founder Building
    Xi Zhang
  • Abstract
  • Matthias Ihme is an Associate Professor in the Department of Mechanical Engineering at Stanford University. He holds a BSc. degree in Mechanical Engineering and a MSc. degree in Computational Engineering. In 2008, he received his Ph.D. in Mechanical Engineering from Stanford. After being on the faculty of the Aerospace Engineering Department at the University of Michigan for five years, he returned to Stanford in 2013. He is a recipient of the NSF CAREER Award (2009), the ONR Young Investigator Award (2010), the AFOSR Young Investigator Award (2010), the NASA Early Career Faculty Award (2015), and the Hiroshi Tsuji Early Career Research Award (2017). His research interests are broadly on the computational modeling of reacting flows, the development of numerical methods, and the investigation of advanced combustion concepts.With the rapid advancement of sensor technology, a huge amount of data is generated in various applications, which poses new and unique challenges for Statistical Process Control (SPC). In the first part of this talk, we will introduce a Nonparametric Adaptive Sampling (NAS) strategy to online monitor non-normal big data streams in the context of limited resources, where only a subset of observations are available at each acquisition time. In particular, this proposed method integrates a rank-based CUSUM scheme and an innovative idea that corrects the anti-rank statistics with partial observations, which can effectively detect a wide range of possible mean shifts when data streams are exchangeable and follow arbitrary distributions. Two theoretical properties on the sampling layout of the proposed NAS algorithm are investigated when the process is in control and out of control. Then, in the second part of this talk, we further consider a scenario that the out-of-control variables are clustered in a small and unknown region and further propose a novel Spatial Adaptive Sampling and Monitoring (SASAM) procedure that aims to leverage the “spatial covariate” information embedded in the data streams for quick change detection. Specifically, the proposed sampling strategy adaptively and intelligently integrates two seemingly contradictory ideas: (1) space filling sampling that quickly searches for possible out-of-control variables; and (2) directional sampling that focuses on highly suspicious out-of-control variables that may cluster in a small region. Both simulations and case studies are conducted under different scenarios to illustrate the superior performance of the proposed methods.
  • Biography
  • Dr. Kaibo Liu is an assistant professor at the department of Industrial and Systems Engineering, University of Wisconsin-Madison. He received the B.S. degree in industrial engineering and engineering management from the Hong Kong University of Science and Technology, Hong Kong, China, the M.S. degree in statistics and the Ph.D. degree in industrial engineering from the Georgia Institute of Technology, Atlanta, respectively. Dr. Kaibo Liu’s research is in the area of system informatics and data analytics, with an emphasis on the data fusion approach for system modeling, monitoring, diagnosis, prognostics and maintenance. The significance of his research has been evidenced by the wide recognition in a broad of research communities in Quality, Statistics, Reliability and Data Mining, including several best paper awards from INFORMS and ISERC and several featured articles from IIE and INFORMS magazines. In addition, his research results and papers have led to successful funding supports by NSF, DoD, and Industry. He was also the winner of the Gilbreth Memorial Fellowship from Institute of Industrial Engineers (IIE) in 2012, the winner of the Richard A. Freund International Scholarship from American Society for Quality (ASQ) in 2013, and the winner (2nd place) of the Pritsker Doctoral Dissertation Award from IIE in 2014.