Overview: Multimodal data are prevalent in industrial monitoring, finance and healthcare. In particular, time series are often tagged with text comments from experts that provide layman users with the domain knowledge to understand the charts. Texts give the patterns qualitative meaning, while time series makes the words quantitative. Analyzing the relationship between different data types is the key to unraveling the hidden structure of such data.
Overview: This project aims to learn skills by mimicking experts’ behaviors in given tasks. The proposed SAiL engine is trained to perform action prediction tasks from demonstrations by learning a mapping function between observed states and actions. The main challenges in real applications, medical and health care, for example, are that the collection of such experts’ demonstrations is very expensive and It takes a large amount of time and money for expert training.
Overview: With ubiquitous sensing and networking capability, traditional complex physical systems have been undergoing revolutionary changes in their ICT capabilities. They are now equipped with a large number of sensors distributed across different parts of the system, which collect a tremendous amount of data from system operation.