EECS500 Seminar

Lei Li
Fast Algorithms for Mining Co-evolving Time Series
Carnegie Mellon University
Glennan 313
12:30-1:30 pm

Time series data arise in numerous applications, such as motion capture, computer network monitoring, data center monitoring, environmental monitoring and many more. Finding patterns and learning features in such collections of sequences are crucial for leveraging them to solve real-world, domain specific problems, for example, to build humanoid robots, to detect pollution in drinking water, and to identify intrusion in computer networks.

In this talk, we focus on fast algorithms on  mining co-evolving time series, with or without missing values. I will present a series of our effort in analyzing those data: time series mining and summarization with missing values, and learning features from multiple sequences.  Algorithms proposed in these works allow us to obtain meaningful patterns effectively and efficiently. Thus they enable vital mining tasks including forecasting, compression, and segmentation for co-evolving time series, even with missing values. I also propose "
PLiF'', a novel algorithm to extract features from multiple sequences, which will serve as a corner stone of many applications for time series such clustering and similarity search. Our algorithms scale linearly with respect to the length of sequences, and outperform the competitors often by large factors. In addition, I will briefly mention several other pieces of my work, including natural motion stitching, bone constrained occlusion filling and a parallelization of our algorithms for multi-core systems.


Lei Li is a Ph.D. candidate of Computer Science Department at Carnegie Mellon University. His research interests include machine learning and data mining, particularly for time series, with applications in motion capture, environmental monitoring, data center monitoring, computer network security, and bio-image databases. Lei received a bachelor's degree in Computer Science (ACM class) from Shanghai Jiao Tong University in 2006. website: http://www.cs.cmu.edu/~leili