DMCA
Enhanced Anytime Algorithm for Induction of Oblivious Decision Trees
BibTeX
@MISC{Last_enhancedanytime,
author = {Mark Last and Albina Saveliev},
title = {Enhanced Anytime Algorithm for Induction of Oblivious Decision Trees},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract. Real-time data mining of high-speed and non-stationary data streams has a large potential in such fields as efficient operation of machinery and vehicles, wireless sensor networks, urban traffic control, stock data analysis etc.. These domains are characterized by a great volume of noisy, uncertain data, and restricted amount of resources (mainly computational time). Anytime algorithms offer a tradeoff between solution quality and computation time, which has proved useful in applying artificial intelligence techniques to timecritical problems. In this paper we are presenting a new, enhanced version of an anytime algorithm for constructing a classification model called Information Network (IN). The algorithm improvement is aimed at reducing its computational cost while preserving the same level of model quality. The quality of the induced model is evaluated by its classification accuracy using the standard 10-fold cross validation. The improvement in the algorithm anytime performance is demonstrated on several benchmark data streams.
Keyphrases
oblivious decision tree enhanced anytime algorithm anytime algorithm algorithm anytime performance artificial intelligence technique computational time large potential several benchmark data stream urban traffic control timecritical problem model quality efficient operation solution quality induced model classification model enhanced version stock data analysis etc real-time data mining computational cost computation time non-stationary data stream wireless sensor network classification accuracy uncertain data standard 10-fold cross validation great volume algorithm improvement information network
