@comment{{This file has been generated by bib2bib 1.96}}
@comment{{Command line: /usr/bin/bib2bib -c 'category : "stream mining"' -ob stream.bib hahsler.bib}}
@inproceedings{hahsler:Jovanovic2011,
author = {Vladimir Jovanovic and Margaret H. Dunham and Michael Hahsler and Yu Su},
title = {Evaluating Hurricane Intensity Prediction Techniques in Real Time},
booktitle = {Third IEEE ICDM Workshop on Knowledge Discovery from Climate Data, Proceedings of the of the 2011 IEEE International Conference on Data Mining Workshops (ICDMW 2011)},
year = {2011},
pages = {},
location = {Vancouver, Canada},
date = {December 10, 2011},
publisher = {IEEE},
editor = {},
abstract = {
While the accuracy of hurricane track prediction
has been improving, predicting intensity, the maximum sustained wind
speed, is still a very difficult challenge. This is problematic because
the destructive power of a hurricane is directly related to its
intensity. In this paper, we present Prediction Intensity Interval
model for Hurricanes (PIIH) which combines sophisticated data mining
techniques to create an online real time model for accurate intensity
predictions and we present a web-based framework to dynamically compare
PIIH to operational models used by the National Hurricane Center (NHC).
The created dynamic website tracks, compares, and provides
visualization to facilitate immediate comparisons of prediction
techniques. This paper is a work in progress paper reporting on both,
new features of the PIIH model and online visualization of the accuracy of
that model as compared to other techniques.
},
pdf = {http://michael.hahsler.net/research/Hurricane/ICDMW_11/PIIH_Evaluation.pdf},
category = {stream mining, climate}
}
@inproceedings{hahsler:Hahsler2011,
author = {Michael Hahsler and Margaret H. Dunham},
title = {Temporal Structure Learning for Clustering Massive Data Streams
in Real-Time},
booktitle = {{SIAM} Conference on Data Mining ({SDM11})},
year = {2011},
pages = {664--675},
location = {Mesa, Arizona},
date = {April 28--30, 2011},
publisher = {SIAM},
editor = {},
abstract = {
This paper describes one of the first attempts to model the temporal
structure of massive data streams in real-time using data stream
clustering. Recently, many data stream clustering algorithms have
been developed which efficiently find a partition of the data
points in a data stream. However, these algorithms disregard the
information represented by the temporal order of the data points in
the stream which for many applications is an important part of the
data stream. In this paper we propose a new framework called
Temporal Relationships Among Clusters for Data Streams (TRACDS)
which allows to learn the temporal structure while clustering a
data stream. We identify, organize and describe the clustering
operations which are used by state-of-the-art data stream
clustering algorithms. Then we show that by defining a set of new
operations to transform Markov Chains with states representing
clusters dynamically, we can efficiently capture temporal ordering
information. This framework allows us to preserve temporal
relationships among clusters for any state-of-the-art data stream
clustering algorithm with only minimal overhead.
To investigate the usefulness of TRACDS, we evaluate the improvement of
TRACDS over pure data stream clustering for anomaly detection using
several synthetic and real-world data sets. The experiments show that
TRACDS is able to considerably improve the results even if we introduce
a high rate of incorrect time stamps which is typical for real-world
data streams.
},
pdf = {http://michael.hahsler.net/research/TRACDS_SDM11/TRACDS_SDM11.pdf},
category = {stream mining}
}
@article{hahsler:Dunham2010b,
author = {Margaret H. Dunham and Michael Hahsler and Myra Spiliopoulou},
title = {Novel Data Stream Pattern Mining, {Report on the StreamKDD'10 Workshop}},
journal = {SIGKDD Explorations},
year = {2010},
volume = {12},
number = {2},
pages = {54--55},
url = {http://www.sigkdd.org/explorations/issue.php?volume=12&issue=2&year=2010&month=12},
abstract = {
This report summarizes the First International Workshop on
Novel Data Stream Pattern Mining held at the 16th ACM SIGKDD
International Conference on Knowledge Discovery and Data
Mining, on July 25 2010 in Washington, DC.
},
category = {stream mining}
}
@inproceedings{hahsler:Yu2010,
author = {Yu Su and Sudheer Chelluboina and Michael Hahsler and Margaret H. Dunham},
title = {A New Data Mining Model for Hurricane Intensity Prediction},
booktitle = {Second IEEE ICDM Workshop on Knowledge Discovery from Climate Data: Prediction, Extremes and Impacts, Proceedings of the of the 2010 IEEE International Conference on Data Mining Workshops (ICDMW 2010)},
year = {2010},
pages = {98--105},
location = {Sydney, Australia},
date = {December 14, 2010},
publisher = {IEEE},
editor = {},
url = {http://www.computer.org/portal/web/csdl/doi/10.1109/ICDMW.2010.158},
abstract = {
This paper proposes a new hurricane intensity prediction model, WFL-EMM,
which is based on the data mining techniques of feature weight learning
(WFL) and Extensible Markov Model (EMM). The data features used are
those employed by one of the most popular intensity prediction models,
SHIPS. In our algorithm, the weights of the features are learned by a
genetic algorithm (GA) using historical hurricane data. As the GA's
fitness function we use the error of the intensity prediction by an EMM
learned using given feature weights. For fitness calculation we use a
technique similar to $k$-fold cross validation on the training data.
The best weights obtained by the genetic algorithm are used to build an
EMM with all training data. This EMM is then applied to predict the
hurricane intensities and compute prediction errors for the test data.
Using historical data for the named Atlantic tropical cyclones from
1982 to 2003, experiments demonstrate that WFL-EMM provides
significantly more accurate intensity predictions than SHIPS within 72
hours. Since we report here first results, we indicate how to improve
WFL-EMM in the future.
},
pdf = {http://michael.hahsler.net/research/Hurricane/ICDMW_10/05693288.pdf},
category = {stream mining, climate}
}
@book{hahsler:Dunham2010,
editor = {Margaret H. Dunham and Michael Hahsler and Myra Spiliopoulou},
title = {Proceedings of the First International Workshop on Novel Data Stream Pattern Mining Techniques (StreamKDD'10)},
publisher = {ACM Press},
year = 2010,
issn = {978-1-4503-0226-5},
location = {Washington, D.C.},
publisher = {ACM},
address = {New York, NY, USA},
url = {http://portal.acm.org/citation.cfm?id=1833280},
abstract = {Data stream mining gained in importance over the last years
because it is indispensable for many real applications such as
prediction and evolution of weather phenomena; security and anomaly
detection in networks; evaluating satellite data; and mining health
monitoring streams. Stream mining algorithms must take account of
the unique properties of stream data: infinite data, temporal
ordering, concept drifts and shifts, demand for scalability etc.
This workshop brings together scholars working in different areas of
learning on streams, including sensor data and other forms of accumulating
data. Most of the papers in the next pages are on unsupervised learning
with clustering methods. Issues addressed include the detection of outliers
and anomalies, evolutionary clustering and incremental clustering, learning
in subspaces of the complete feature space and learning with exploitation
of context, deriving models from text streams and visualizing them. },
category = {stream mining}
}
@article{hahsler:Hahsler2010,
author = {Michael Hahsler and Margaret H. Dunham},
title = {\pkg{rEMM}: Extensible {M}arkov Model for Data Stream
Clustering in \proglang{R}},
journal = {Journal of Statistical Software},
year = {2010},
volume = {35},
number = {5},
pages = {1--31},
url = {http://www.jstatsoft.org/v35/i05/},
abstract = {
Clustering streams
of continuously arriving data has become an important application of
data mining in recent years and efficient algorithms have been proposed
by several researchers. However, clustering alone neglects the fact
that data in a data stream is not only characterized by the proximity
of data points which is used by clustering, but also by a temporal
component. The Extensible Markov Model (EMM) adds the temporal
component to data stream clustering by superimposing a dynamically
adapting Markov Chain. In this paper we introduce the implementation of
the R extension package rEMM which implements EMM and we discuss some
examples and applications.
},
category = {stream mining}
}
This file was generated by bibtex2html 1.96.