Modern sensing technology allows us enhanced monitoring of dynamic activities in business, traffic, and home, just to name a few. The increasing amount of sensor measurements, however, brings us the challenge for efficient data analysis. This is especially true when sensing targets can interoperate—in such cases we need learning models that can capture the relations of sensors, possibly without collecting or exchanging all data. Generative graphical models namely the Markov random fields (MRF) fit this purpose, which can represent complex spatial and temporal relations among sensors, producing interpretable answers in terms of probability. The only drawback will be the cost for inference, storing and optimizing a very large number of parameters—not uncommon when we apply them for real-world applications.
Description
Spatio-temporal random fields: compressible representation and distributed estimation - Springer
%0 Journal Article
%1 piatkowski2013spatiotemporal
%A Piatkowski, Nico
%A Lee, Sangkyun
%A Morik, Katharina
%D 2013
%I Springer US
%J Machine Learning
%K compression fields markov random spatial temporal to:becker
%N 1
%P 115-139
%R 10.1007/s10994-013-5399-7
%T Spatio-temporal random fields: compressible representation and distributed estimation
%U http://dx.doi.org/10.1007/s10994-013-5399-7
%V 93
%X Modern sensing technology allows us enhanced monitoring of dynamic activities in business, traffic, and home, just to name a few. The increasing amount of sensor measurements, however, brings us the challenge for efficient data analysis. This is especially true when sensing targets can interoperate—in such cases we need learning models that can capture the relations of sensors, possibly without collecting or exchanging all data. Generative graphical models namely the Markov random fields (MRF) fit this purpose, which can represent complex spatial and temporal relations among sensors, producing interpretable answers in terms of probability. The only drawback will be the cost for inference, storing and optimizing a very large number of parameters—not uncommon when we apply them for real-world applications.
@article{piatkowski2013spatiotemporal,
abstract = {Modern sensing technology allows us enhanced monitoring of dynamic activities in business, traffic, and home, just to name a few. The increasing amount of sensor measurements, however, brings us the challenge for efficient data analysis. This is especially true when sensing targets can interoperate—in such cases we need learning models that can capture the relations of sensors, possibly without collecting or exchanging all data. Generative graphical models namely the Markov random fields (MRF) fit this purpose, which can represent complex spatial and temporal relations among sensors, producing interpretable answers in terms of probability. The only drawback will be the cost for inference, storing and optimizing a very large number of parameters—not uncommon when we apply them for real-world applications.},
added-at = {2013-10-08T13:59:11.000+0200},
author = {Piatkowski, Nico and Lee, Sangkyun and Morik, Katharina},
biburl = {https://www.bibsonomy.org/bibtex/2eed8d4fcd9cfc30c01c1bf72e8e9cdbb/thoni},
description = {Spatio-temporal random fields: compressible representation and distributed estimation - Springer},
doi = {10.1007/s10994-013-5399-7},
interhash = {314e29a1c444118b8a4e8d2ba7ab6336},
intrahash = {eed8d4fcd9cfc30c01c1bf72e8e9cdbb},
issn = {0885-6125},
journal = {Machine Learning},
keywords = {compression fields markov random spatial temporal to:becker},
language = {English},
number = 1,
pages = {115-139},
publisher = {Springer US},
timestamp = {2016-09-06T08:23:07.000+0200},
title = {Spatio-temporal random fields: compressible representation and distributed estimation},
url = {http://dx.doi.org/10.1007/s10994-013-5399-7},
volume = 93,
year = 2013
}