DocumentCode :
841283
Title :
High-Dimensionality Data Reduction with Java
Author :
Villalon, E.
Author_Institution :
Inst. for Quantitative Social Sci., Harvard Univ., Cambridge, MA
Volume :
10
Issue :
5
fYear :
2008
Firstpage :
64
Lastpage :
69
Abstract :
The author used the Java multimedia framework along with statistical software from the Colt project to preprocess and compare videos downloaded from Internet sites. Preprocessing the videos decreases each one´s dimensionality and size, making it easier to analyze, interpret, and convey useful information about the data´s most relevant attributes. In this article, the author shows that preprocessing raw data to decrease its dimensionality and size is essential for interpreting data and conveying useful information about its attributes. Graphically visualizing data sets with histograms or other graphs can help researchers detect structural features and properties for classifying similar data sets or making inferences about different data sets.
Keywords :
Java; data compression; data reduction; data visualisation; feature extraction; image classification; image colour analysis; mathematics computing; multimedia computing; statistical analysis; video coding; Colt project; Internet site; Java multimedia framework; data set graphical visualization; high-dimensionality data reduction; image colour analysis; similar data set classification; statistical software; structural feature detection; video compression; Data mining; Frequency; Histograms; Image analysis; Image color analysis; Information analysis; Java; Performance analysis; Spatial databases; Videos; Java; and computation on matrices.; statistical methods; video analysis;
fLanguage :
English
Journal_Title :
Computing in Science & Engineering
Publisher :
ieee
ISSN :
1521-9615
Type :
jour
DOI :
10.1109/MCSE.2008.134
Filename :
4604507
Link To Document :
بازگشت