Zobrazeno 1 - 10
of 34
pro vyhledávání: '"Ke-Thia Yao"'
Publikováno v:
Entropy, Vol 22, Iss 11, p 1202 (2020)
Boltzmann machines have useful roles in deep learning applications, such as generative data modeling, initializing weights for other types of networks, or extracting efficient representations from high-dimensional data. Most Boltzmann machines use re
Externí odkaz:
https://doaj.org/article/28182cba64964ed8a2592cc52702a947
Autor:
Ke-Thia Yao, Cauligi S. Raghavenda, Cyrus Ashayeri, Dhruvil Trivedi, Tirth Patel, Manish Lal, Richard Row, Attila Aksehirli, Iraj Ershaghi
Publikováno v:
Day 3 Wed, October 05, 2022.
This paper presents a physics based and data driven machine learning approach for chemical treatment candidate well selection in fields producing heavy oil. In heavy oil fields, cyclic steam is often used to not only to stimulate the formation around
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ac36701d3af6fc40a5e6c580c3de821d
https://doi.org/10.2118/209999-ms
https://doi.org/10.2118/209999-ms
Publikováno v:
Entropy, Vol 22, Iss 1202, p 1202 (2020)
Entropy
Volume 22
Issue 11
Entropy
Volume 22
Issue 11
Boltzmann machines have useful roles in deep learning applications, such as generative data modeling, initializing weights for other types of networks, or extracting efficient representations from high-dimensional data. Most Boltzmann machines use re
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ec6f0c8be474eb62d365cdd23d44a4e3
https://www.mdpi.com/1099-4300/22/11/1202
https://www.mdpi.com/1099-4300/22/11/1202
Autor:
Thomas E. Potok, Robert M. Patton, Federico M. Spedalieri, Garrett S. Rose, Ke-Thia Yao, Catherine D. Schuman, Jeremy Liu, Steven R. Young, Gangotree Chakma
Publikováno v:
ACM Journal on Emerging Technologies in Computing Systems. 14:1-21
Current deep learning approaches have been very successful using convolutional neural networks trained on large graphical-processing-unit-based computers. Three limitations of this approach are that (1) they are based on a simple layered network topo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ca4a6bff557c5544299f73d270b4f146
https://doi.org/10.1145/3178454
https://doi.org/10.1145/3178454
Autor:
Robert M. Patton, Steven R. Young, Jeremy Liu, Federico M. Spedalieri, Thomas E. Potok, Catherine D. Schuman, Garrett S. Rose, Ke-Thia Yao, Gangotree Chamka
Publikováno v:
Entropy; Volume 20; Issue 5; Pages: 380
Entropy
Entropy
Training deep learning networks is a difficult task due to computational complexity, and this is traditionally handled by simplifying network topology to enable parallel computation on graphical processing units (GPUs). However, the emergence of quan
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3de32407cfd056748e1dd911754e20d3
Autor:
U. Neumann, Ke-Thia Yao, Charalampos Chelmis, S. You, Viktor K. Prasanna, N. Killen, R. House, Iraj Ershaghi, R. Raghavendra, B. Thigpen, V. Sankur
Publikováno v:
All Days.
We present an integrated system that automatically collects historical and current data from heterogeneous sources, performs analytics to identify telltale signatures of Loss of Containment (LOC) events, and makes asset behavior predictions as an ass
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0beb8c92b60ad8f433642ccb66c3e381
https://doi.org/10.2118/181048-ms
https://doi.org/10.2118/181048-ms
Publikováno v:
All Days.
This paper presents a data driven approach for failure prediction for Electrical Submersible Pumps (ESP). ESP system is well known as an effective artificial lift method which has been applied to about 20 percent of almost one million wells worldwide
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cd197455a46950d94f0a98f904e09650
https://doi.org/10.2118/174062-ms
https://doi.org/10.2118/174062-ms
Publikováno v:
All Days.
Offshore oil and gas platforms facilities include extensive piping components, pressure vessels, and other equipment. These are monitored regularly to minimize non-conformances for safety and integrity of platforms. This paper focuses on using field
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8ef491b564bd845ef23248b06164d0af
https://doi.org/10.2118/173995-ms
https://doi.org/10.2118/173995-ms
Publikováno v:
All Days.
This paper presents the results of using autoencoder-derived features, rather than hand-crafted features, for predicting rod pump well failures using Support Vector Machines (SVMs). Features derived from dynamometer card shapes are used as inputs to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1257f4c8caf9f24f0586272205f19bd2
https://doi.org/10.2118/174015-ms
https://doi.org/10.2118/174015-ms
Autor:
Stephen P. Crago, Ke-Thia Yao, Mikyung Kang, Andrew J. Younge, Dong In Kang, John Paul Walters, Geoffrey C. Fox
Publikováno v:
IEEE CLOUD
As more scientific workloads are moved into the cloud, the need for high performance accelerators increases. Accelerators such as GPUs offer improvements in both performance and power efficiency over traditional multi-core processors, however, their
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e8a5cd34c4446320095d6d4778a4fff8
https://doi.org/10.1109/cloud.2014.90
https://doi.org/10.1109/cloud.2014.90