Improving Performance and Accuracy of Local PCA

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F11%3A10099306" target="_blank" >RIV/00216208:11320/11:10099306 - isvavai.cz</a>
Alternative codes found
RIV/68407700:21230/11:00183691
Result on the web
<a href="http://dx.doi.org/10.1111/j.1467-8659.2011.02047.x" target="_blank" >http://dx.doi.org/10.1111/j.1467-8659.2011.02047.x</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1111/j.1467-8659.2011.02047.x" target="_blank" >10.1111/j.1467-8659.2011.02047.x</a>

Result language
angličtina
Original language name
Improving Performance and Accuracy of Local PCA
Original language description
Local Principal Component Analysis (LPCA) is one of the popular techniques for dimensionality reduction and data compression of large data sets encountered in computer graphics. The LPCA algorithm is a variant of k-means clustering where the repetitive classification of high dimensional data points to their nearest cluster leads to long execution times. The focus of this paper is on improving the efficiency and accuracy of LPCA. We propose a novel SortCluster LPCA algorithm that significantly reduces the cost of the point-cluster classification stage, achieving a speed-up of up to 20. To improve the approximation accuracy, we adopt the k-means++ algorithm [AV07]. We show that similar ideas that lead to the efficiency of our SortCluster LPCA algorithm can be used to accelerate k-means++. The resulting initialization algorithm is faster than purely random seeding while producing substantially more accurate data approximation.
Czech name
—
Czech description
—

Type
J<sub>x</sub> - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)
CEP classification
JC - Computer hardware and software
OECD FORD branch
—

Publication year
2011
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)