Colloquium: Andy Liu
Friday, March 29
1 p.m.
Avery 19
There will be no reception for this colloquium.
“Learning Data Science with Robotics: A Multidisciplinary Approach
for Data Analytics”
Abstract: Over the past few years, rapid technological advances in data science have been reshaping our world and enabling the emergence of new innovations. With the abundance of data available at our fingertips today, having the analytics skills required to work with data isn’t just valuable but a necessity. However, in order to deliver a successful analytics project, students not only need to learn the required knowledge and skills in data science, but also need to gain problem solving skills.
At the same time the data analytics revolution is evolving rapidly, advances in robotics, AI, and machine learning are heralding a new era of innovation. To improve the learning experience and study outcomes, a multidisciplinary approach with robotics can be used for learning data science. The students with different backgrounds form groups to work on the multimodal human-robot interaction data, including robot data, network data, social behavioral data, demographic data, task performance data, etc. They are able to use the skills they learned in Data Science Class and their experiences in different disciplines to gain actionable insights from their data. Students are also able to learn how to design and develop creative and innovative analytics solutions to solve real-world problems. These skills will be added on as students move toward completion of their degrees.
Bio: Xiaoming Liu is a Visiting Assistant Professor of Computer Science at Louisiana State University in Shreveport. Dr. Liu received his Ph.D. in Computer Science from the University of the Western Cape in South Africa in 2015 and M.S. in Business Analytics from the University of Texas at Dallas in 2017. His research focuses on building adaptive computational models of complex human-robot social networks, especially the assessment of log-term child-robot relationships for children with special needs. Using multimodal interaction data and mobile sensing data, his research evaluates models of how disabled children behavior with their robot companions and other children in cooperative and non-cooperative environments. His other interests include social robots, human-robot interaction, artificial intelligence, machine learning, and social networks.