Data science and statistical/machine learning techniques can be leveraged to tackle various predictive and decision control problems in a wide range of application domains.

This talk will focus on two domains: (1) large-scale networked systems such as IP backbone or wireless cellular networks, and (2) smart health applications.

The first part of the talk will discuss lessons learned and opportunities in Internet measurement area. We will demonstrate how flexibility of software-defined networking (SDN) can be leveraged to adapt measurement rules based on optimal online strategies to augment traditional network inference techniques to obtain better estimates of network characteristics, such as traffic matrix or per-hop delay/loss rates. We will discuss the importance of data pre-processing, featurization, and choice of models by case studies from our prior work on detecting malicious activities in wireless networks and modeling user activity graphs on massive online social platforms.

The second part of the talk focuses on opportunities and challenges that arise in applying IoTs, big data, AI, and machine learning (ML) techniques to smart health domain such as AI-assisted critical patient care or medical imaging. Specifically, we will draw examples from our on-going collaborative projects with UC Davis Medical Center, the Alzheimer Disease Center, and the MIND Institute in Sacramento