Clark School Home UMD
ECE

Events Calendar

Event Information

MS Thesis Defense: Yitian Wang
Tuesday, November 14, 2017
1:00 p.m.
AVW2168
For More Information:
Maria Hoo
301 405 3681
mch@umd.edu

ANNOUNCEMENT: MS Thesis Defense

Name: Yitian Wang

Committee Members:
Professor Joseph Jaja, Chair/Advisor
Professor Gang Qu
Professor Tudor Dumitras

Date/Time: Tuesday, November 14, 2017, at 1pm

Place: AVW 2168

Title:Analysis and Forecasting for Traffic Flow Data

Abstract:
 
In this thesisa number of techniques related to Principal Component Analysis (PCA) are used to derive core traffic patterns from streams of traffic data on a large number of road segments. Using a few number of khidden variables, we show that the traffic information on the road segments can be captured by k traffic patterns. The dimensionality of the correlated road segments is successfully reduced from n to a much smaller number kby applying techniques related to Principal Component Analysis (PCA), where n is the number of road segments while k is the number of hidden variables. We use the knearest neighbor(KNN) method to predict the values of the hidden variables over small time windows. As a result, we are able to forecast the speeds for n road segments very quickly. Our results are aimed at network-level and real-time prediction. In general, the computation of PCA is computationally demanding when n is large. A more efficient online version of PCA, called PASTd algorithm isused to reduce data dimension. As a result, our forecasting method is efficient, flexible, and robust.

 

This Event is For: Faculty

Browse Events By Calendar

Calendar Home

« Previous Month    Next Month »

November 2017
SU M TU W TH F SA
1 2 3 4 w
5 6 7 8 9 10 11 w
12 13 14 15 16 17 18 w
19 20 21 22 23 24 25 w
26 27 28 29 30 w
Search Events

Events

Events Calendar
Submit Event

News

Newsroom
News Search
News Archives