ABSTRACT:

In recent years, personal location data is continuously captured by mobile devices, GPS chips and other sensors. Such data provides a unique learning opportunity on individuals’ mobility behavior that may be used for various applications in transportation, marketing, homeland security and smart cities. Nonetheless, modeling such data poses new challenges related to data volume, diversity, inhomogeneity and the required granularity level. In this talk, we will address a real ‘smart city’ use-case and cover some of its associated opportunities and challenges. We will present a new set of mobility-behavior models that generalizes Markov Chains and Variable-Order Bayesian Networks. We will discuss how they can be used in different smart city applications such as pattern recognition, anomaly detection, clustering and classification.

Bio:
Irad Ben-Gal is a visiting professor at MS&E Stanford University and a full professor in the Department of Industrial Engineering at Tel Aviv University, heading the AI & Business Analytics lab.  His research focuses on applied probability, machine learning and information theory applications to industrial and service systems. He wrote 3 books, published more than 80 scientific papers and patents and received several best papers awards. He is a Department Editor in IIE Transactions and serves on the Editorial Boards of several data science journals. Irad led various R&D projects and worked with companies such as Siemens, Intel, Applied Materials, GM, Nokia, AT&T, Oracle and SAP.  Irad is the co-founder and active chairman of CB4 (“See Before”), a startup backed by Sequoia Capital that provides granular predictive analytics solutions to retail organizations.