Events Calendar

Dian Gong (USC), Student Seminar Series

Speaker: Dian Gong, USC Electrical Engineering Ph.D. Student

Talk Title: Machine Learning to Structured Time Series Analysis

Series: Student Seminar Series

Abstract: Time series and sequential data have been investigated for several decades in statistics, signal processing and econometrics. The success of machine learning techniques brings opportunities to efficiently analyze more complex, high dimensional and large-scale time series data. In this talk, we present a non-parametric learning framework to multivariate time series data. The raw time series is first temporally decomposed into different units with certain semantic meanings by our newly proposed Kernelized Temporal Cut (KTC). KTC is an online non-parametric change-point detection method that can detect regime changes for complex sequential data. Given two time series units, the similarity (distance) can be calculated by using spaito-temporal alignment methods such as DTW. To handle the nonlinearity of multivariate time series data in many applications, we propose Dynamic Manifold Warping (DMW). DMW is a combination of DTW and manifold learning by exploring the intrinsic manifold structure of time series data. After temporal segmentation and the design of distance metric, we can treat each time series unit as one data instance, and many tasks can be performed, such as clustering, classification and retrieval. We apply this framework to human action analysis and achieve promising results.

Biography: Dian Gong is a PhD Candidate major in Electrical Engineering and minor in Computer Science at USC. His advisor is Prof. Gerard Medioni, and his research areas are machine learning to structured time series, manifold learning and probabilistic Tensor Voting. He also uses cutting-edge machine learning techniques to computer vision applications such as human activity recognition. His works are published at conferences such as AISTATS 2010, ICCV 2011, ICML 2012 and ECCV 2012. He worked as a summer quantitative trading associate at Barclays Capital New York office. He also worked as research intern at Sony US Research, San Jose, CA on distance metric learning, and Microsoft Research Asia, on probabilistic graphical model. In the past, he won several mathematics contest awards such as the Gold medal of China Mathematics Olympiad, and selected as national team candidate for International Mathematics Olympiad. He got his BS in Electronic Engineering from Tsinghua University.

Advisor: Gerard Medioni
Refreshments will be provided

Host:

More Info: https://mhi.usc.edu/events/event-details/?event_id=901927

Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248

Audiences: Everyone Is Invited

Contact: Assistant to CS chair

Event Link: https://mhi.usc.edu/events/event-details/?event_id=901927