Juhi Ranjan, PhD Dissertation Defense


Date: Friday, October 21st, 2016 at 8:30 am in Rice 204
Advisor: Kamin Whitehouse
Committee: Jack Stankovic (Committee Chair),  Gabe Robins, Laura Barnes and James Scott (Microsoft Research, UK)

It Takes Two: Exploring Interactions between Smart Objects and Wearables to Implicitly Identify and Authenticate Object Users

In today’s context, the term `Smart Objects’ are used to refer to objects that incorporate computing and communication in some capacity, in order to enhance the functionality and/or interaction experience for the end user. User identity is a very important context for objects that are typically shared between different people. This is because people have different personalities and preferences, and therefore have different requirements from the same objects. Therefore, when they interact with objects, they often need to re-configure them to suit their ow needs. For example, while showering, people prefer different water temperatures, and therefore need to set the hot and cold water mixer to their preferred configuration every time they take a shower.

In the current state of the art, Smart Objects don’t really adapt themselves to the person using them without explicitly engaging them in an identification process. In order for objects to perform personalized functions, they must solve what we refer as the Implicit User Identification and Authentication (IUIA) problem: understanding who is actually using a given object, and being able to validate their identity, without expecting the user to explicitly participate in an identification process.

In this dissertation, we explore the use of Wearables in performing IUIA. There are two main reasons why we believe that wearable devices are an attractive technological solution that can assist Smart Objects in solving this problem: a. wearables adoption is growing at a rapid pace, and b. they are embedded with sensors that can monitor location context and hand motion of their wearer. However, while sensors in Wearables are great for making approximate measures of a person’s activities, the imprecision of their sensing systems makes them challenging for use in applications such as IUIA, which require high precision and accuracy.

In this work, we explore the following hypothesis – Despite the coarse granularity of its location sensing, and imprecision in sensing hand’s motion trajectory, data from sensors in wearable devices, when augmented with data from Smart Objects, can be used to identify and authenticate users interacting with Smart Objects. We explore different levels of information shared by the Wearable device with a Smart Object, and explore how each level of data abstraction affects the user identification accuracy

PhD Defense Student Defenses