My research concentrates on big data analytics to develop systematic data-driven analytics methodologies for process modeling, quality control, and performance improvement in computationally aware systems. By incorporating engineering domain knowledge with advanced techniques in statistics and machine learning, the  methodologies facilitate (i) the identification of appropriate and robust models that describe the system structures and dynamics, (ii) the effective surveillance of system status, (iii) the more accurate forecasting of future trends and dynamics, and (iv) the informative decisions that improve the system productivity and performance. The generic research leads to immediate applications in manufacturing, healthcare, traffic, climate, energy and service systems, etc.

I am a co-founder of the Data Informatics of Systems Improvement and DEsign (DISIDE) laboratory.

1. Big Data Streams Monitoring and Sampling

The objective of this line of research is to create a new paradigm of dynamic data-driven modeling, sampling and monitoring schemes for Big Data which involve large-volume and high-dimensional data streams in real time.

2. Engineering knowledge-enhanced Complex process modeling and diagnosis

The objective of this line of research is for leveraging and incorporating domain knowledge to facilitate process modeling and diagnosis, and quantifying key performance indicators for complex systems.

3. System informatics and spatiotemporal real-time prediction

The objective of this line of research is to establish network modeling and spatiotemporal prediction by incorporating domain knowledge.