04/09/2021
By Karen Volis

The Kennedy College of Sciences, Department of Computer Science, invites you to attend a doctoral dissertation defense by Yang Gao on "Analyzing the Usage of Intelligent Personal Assistants in Daily Life.”

Ph.D. Candidate: Yang Gao
Defense Date: Wednesday, April 21, 2021
Time: 9:30 to 11:30 a.m. EST
Location: This will be a virtual defense via Zoom. Those interested in attending should contact Yang_Gao@student.uml.edu at least 24 hours prior to the defense to request access to the Zoom link.

Committee Chair (Advisor): Tingjian Ge, Professor, Computer Science Department, University of Massachusetts Lowell
Committee Members:

  • Cindy Chen, Associate Professor, Computer Science Department , University of Massachusetts Lowell
  • Guanling Chen (external member), Chief Technology Officer, For U Trucking

Abstract:
Intelligent personal assistants (IPAs) have developed rapidly in the recent five years. With the development of the artificial intelligence (AI) industry, IPAs are gradually becoming familiar to the public as a relatively mature field of AI systems. More and more IPAs have been embedded in the systems of a variety of mobile devices (e.g., smartphones and tablets), wearable devices (e.g., smartwatches and headsets), and smart home devices (e.g., smart speakers and smart TVs). An IPA usually consists of two components: a chatbot and an AI backend. As a human-computer interaction interface of the IPA, the chatbot evolved from text interaction to voice interaction or multimodal interaction, and from command responses to natural conversations. The AI backend enriched the application scenarios of the IPA, which cover but are not limited to automation devices and media playback control, information query, schedule management, personal recommendation, and personal health management.

As an automated assistant, many existing IPA embedded devices (or systems) are already providing excellent service to handle concierge-type tasks following user commands. However, there are still many challenges for IPAs to become smart partners which automatically perform management or data-handling tasks based on real-time data and online information without user initiation.

In this dissertation work, I will conduct two case studies. One is analyzing the usage of a well-known IPA embedded device (Amazon Echo) and its impact on daily life through NLP techniques. Secondly, I will devise a deep-learning-based automated diet monitoring approach for IPA with off-the-shelf Bluetooth headsets. Our study provides insights into the pervasive nature of IPAs in people’s life and the solid AI techniques behind them in order to make the best use of IPAs.

All interested students and faculty members are invited to attend the defense via remote access.