2015
Geilke, Michael; Karwath, Andreas; Kramer, Stefan
Modeling recurrent distributions in streams using possible worlds Conference
2015 IEEE International Conference on Data Science and Advanced Analytics, DSAA 2015, IEEE, 2015, ISBN: 978-1-4673-8272-4.
Abstract | Links | BibTeX | Tags: density estimation, machine learning, possible worlds, stream mining
@conference{geilke2015,
title = {Modeling recurrent distributions in streams using possible worlds},
author = {Michael Geilke and Andreas Karwath and Stefan Kramer},
url = {http://dx.doi.org/10.1109/DSAA.2015.7344814},
doi = {10.1109/DSAA.2015.7344814},
isbn = {978-1-4673-8272-4},
year = {2015},
date = {2015-10-19},
booktitle = {2015 IEEE International Conference on Data Science and Advanced Analytics, DSAA 2015},
pages = {1-9},
publisher = {IEEE},
crossref = {DBLP:conf/dsaa/2015},
abstract = {Discovering changes in the data distribution of streams and discovering recurrent data distributions are challenging problems in data mining and machine learning. Both have received a lot of attention in the context of classification. With the ever increasing growth of data, however, there is a high demand of compact and universal representations of data streams that enable the user to analyze current as well as historic data without having access to the raw data. To make a first step towards this direction, we propose a condensed representation that captures the various - possibly recurrent - data distributions of the stream by extending the notion of possible worlds. The representation enables queries concerning the whole stream and can, hence, serve as a tool for supporting decision-making processes or serve as a basis for implementing data mining and machine learning algorithms on top of it. We evaluate this condensed representation on synthetic and real-world data.
},
keywords = {density estimation, machine learning, possible worlds, stream mining},
pubstate = {published},
tppubtype = {conference}
}
Discovering changes in the data distribution of streams and discovering recurrent data distributions are challenging problems in data mining and machine learning. Both have received a lot of attention in the context of classification. With the ever increasing growth of data, however, there is a high demand of compact and universal representations of data streams that enable the user to analyze current as well as historic data without having access to the raw data. To make a first step towards this direction, we propose a condensed representation that captures the various - possibly recurrent - data distributions of the stream by extending the notion of possible worlds. The representation enables queries concerning the whole stream and can, hence, serve as a tool for supporting decision-making processes or serve as a basis for implementing data mining and machine learning algorithms on top of it. We evaluate this condensed representation on synthetic and real-world data.