Title: 

Adaptive Data-Driven Strategies for Rapid Forecasting and Assessment in Electricity Modeling and Structural Health Monitoring

Abstract:

Due to the increasing efficiency and availability of information technologies for collecting massive amounts of data (e.g., smart meters and sensors) in recent years, a variety of advanced technologies and decision-making strategies in the civil engineering sector have shifted in leaps and bounds to a data-driven manner. While there is still no consensus in industry and academia on the latest advances, challenges, and trends in some innovative and complex data-driven methods related to, it is undeniable that these techniques have been proven to be considerably effective in helping academics and engineers solve many real-life tasks linked to the smart city framework. In the two areas of Residential Electricity Modeling (REM) and Structural Health Monitoring (SHM), highly evolving in the smart city era, data-driven strategies should be adaptively developed to address different specific problems. Effective model selection algorithms and novel cepstrum-based feature extraction methods can be incorporated to accelerate the model training process and to improve decision performance, with achieving the ideal characterization of necessary physical information embedded in the collected raw data that is most relevant to the objectives, especially for the case of modeling deep neural networks.

Speaker Bio:

Lechen Li is a Ph.D. candidate in the Department of Civil Engineering and Engineering Mechanics within the group of Prof. Raimondo Betti. His research interests lie in data-driven SHM and smart electricity network development. Before joining the group of Prof. Betti, he worked on urban energy modeling in the group of Prof. Patricia Culligan.