Dissertation Talk: Statistical Learning Towards Gamification in Human-Centric Cyber-Physical Systems
Seminar: Dissertation Talk: EE | November 9 | 11 a.m.-12 p.m. | Cory Hall, 400 Hughes
In this talk, we explore Human-Centric Cyber-Physical Systems by simultaneously considering users behavior/preference and their interaction as strategic agents. Peoples interaction in a cyber-physical system is a core mechanism of the implementation of smart building technology. However, human preference in regard to living conditions is usually unknown and heterogeneous in its manifestation as control inputs to a building. We focus on the development of a generalized gamification abstraction towards enabling strategic interactions among non-cooperative agents in Human-Centric Cyber-Physical Systems. The proposed framework enables a humans-in-the-loop strategy using an interface to allow building managers to interact with occupants.
In our first approach, we propose the design and implementation of a large-scale network gamification application with the goal of improving the energy efficiency of a building through the utilization of cutting-edge Internet of Things (IoT) sensors and cyber-physical systems sensing/actuation platforms. Then, by observing human decision-makers and their decision strategies in their operation of building systems, we can apply inverse learning techniques in order to estimate their utility functions. To improve forecasting performance, we extend the benchmark utility learning scheme by leveraging Deep Learning end-to-end training with Deep bi-directional Recurrent Neural Networks. In the second part of the talk, we model user interaction as a continuous Nash game between non-cooperative players. We propose a parametric utility learning framework leveraging inverse optimization techniques and explore vulnerability from adversarial attacks in utility learning and present potential security risks.
A series of experimental trials was conducted to generate real-world data, which was then used as the main source of data for our approaches. We apply the proposed methods to data from social game experiments designed to encourage energy efficient behavior among smart building occupants in the Nanyang Technological University (NTU) residential housing and the Center for Research in Energy Systems Transformation (CREST) on the UC Berkeley campus.