Knocking BIG DATA Down to Size

This Fall, the ISE Department welcomed its newest faculty member, Xiaolei Fang, to Daniels Hall. Fang is the first of three new faculty members who will strengthen and grow the Department’s data analytics research area. Sara Shashaani (Michigan) and Hong Wan (Purdue) will be joining ISE in the spring of 2019.

ISE: What made you decide to join the ISE faculty at NC State?
FANG: There are two main reasons. The first one is that ISE cares about the success of their new faculty members. One of the statements that impressed me the most during my campus visit was that ISE will do everything it could to help a new faculty member succeed. I feel that the faculty members here are extremely nice and supportive. ISE also has a wide range of research areas, which provide many potential collaboration opportunities. The second reason is that both my wife and I like Raleigh, which is a very good place to live.

ISE: When did you become interested in data analytics and what was its appeal?
FANG: I become interested in data analytics when I was a graduate student in China. At that time, I participated in five real-world projects in the steel manufacturing industry. My work was to build remote-condition monitoring systems for steel-making machines. Such systems involve collecting data using sensors, analyzing data, and making decisions with the purpose of detecting faults/anomalies, diagnosing the root cause of a fault, and predicting future performance. At that time, I noticed that the most challenging thing was how to analyze sensor data. Since my undergraduate background is in Mechanical Engineering, I did not have enough knowledge in statistics and optimization to address these challenges. Therefore, I decided to join Georgia Tech to obtain a master’s degree in Statistics and a Ph.D. degree in Industrial Engineering.

ISE: Tell us about your current research.
FANG: Currently, my research focuses on addressing the analytical, computational, and scalability challenges associated with High-dimensional and Big Data analytics. First, real-world datasets almost always have complex structures and poor data quality, which require the development of new data science and machine learning algorithms. Second, sensor data in real-world applications usually come at a very high speed. In order to do real-time analysis and decision-making, the data analytics methodologies are required to be computationally efficient. Third, the data volume is huge, which requires data science algorithms to support Big Data analysis such as distributed computing.

ISE: What is the ultimate goal of your research?
FANG: The ultimate goal is to improve the performance of complex engineering systems. For example, effectively assess and interpret system condition, early detect system anomalies, quickly diagnose fault root causes, accurately predict future health condition, intelligently make decisions (such as schedules for maintenance, inventory, and logistics), and optimally control systems for operations.

ISE: What research plans do you have in the ISE Department?
FANG: I plan to collaborate with other faculty members within the ISE department first. ISE has a wide range of research areas, many of which have all kinds of data with which my expertise in data science can help. In addition, I will collaborate with colleagues in the Department of Statistics and Computer Science.

To learn more about Fang and his research go to: