Towards Building a Distributed Virtual Flow Meter via Compressed Continual Learning. Arief, H. A., Thomas, P. J., Constable, K., & Katsaggelos, A. K. Sensors, 22(24):9878, MDPI, dec, 2022. ![Towards Building a Distributed Virtual Flow Meter via Compressed Continual Learning [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex A robust–accurate estimation of fluid flow is the main building block of a distributed virtual flow meter. Unfortunately, a big leap in algorithm development would be required for this objective to come to fruition, mainly due to the inability of current machine learning algorithms to make predictions outside the training data distribution. To improve predictions outside the training distribution, we explore the continual learning (CL) paradigm for accurately estimating the characteristics of fluid flow in pipelines. A significant challenge facing CL is the concept of catastrophic forgetting. In this paper, we provide a novel approach for how to address the forgetting problem via compressing the distributed sensor data to increase the capacity of the CL memory bank using a compressive learning algorithm. Through extensive experiments, we show that our approach provides around 8% accuracy improvement compared to other CL algorithms when applied to a real-world distributed sensor dataset collected from an oilfield. Noticeable accuracy improvement is also achieved when using our proposed approach with the CL benchmark datasets, achieving state-of-the-art accuracies for the CIFAR-10 dataset on blurry10 and blurry30 settings of 80.83% and 88.91%, respectively.
@article{arief2022towards,
abstract = {A robust–accurate estimation of fluid flow is the main building block of a distributed virtual flow meter. Unfortunately, a big leap in algorithm development would be required for this objective to come to fruition, mainly due to the inability of current machine learning algorithms to make predictions outside the training data distribution. To improve predictions outside the training distribution, we explore the continual learning (CL) paradigm for accurately estimating the characteristics of fluid flow in pipelines. A significant challenge facing CL is the concept of catastrophic forgetting. In this paper, we provide a novel approach for how to address the forgetting problem via compressing the distributed sensor data to increase the capacity of the CL memory bank using a compressive learning algorithm. Through extensive experiments, we show that our approach provides around 8% accuracy improvement compared to other CL algorithms when applied to a real-world distributed sensor dataset collected from an oilfield. Noticeable accuracy improvement is also achieved when using our proposed approach with the CL benchmark datasets, achieving state-of-the-art accuracies for the CIFAR-10 dataset on blurry10 and blurry30 settings of 80.83% and 88.91%, respectively.},
author = {Arief, Hasan Asy'ari and Thomas, Peter James and Constable, Kevin and Katsaggelos, Aggelos K.},
doi = {10.3390/s22249878},
issn = {1424-8220},
journal = {Sensors},
keywords = {continual learning,distributed acoustic sensing,virtual flow meter},
month = {dec},
number = {24},
pages = {9878},
pmid = {36560248},
publisher = {MDPI},
title = {{Towards Building a Distributed Virtual Flow Meter via Compressed Continual Learning}},
url = {https://www.mdpi.com/1424-8220/22/24/9878},
volume = {22},
year = {2022}
}
Downloads: 0
{"_id":"qqPeeGoJfrXtEwjEd","bibbaseid":"arief-thomas-constable-katsaggelos-towardsbuildingadistributedvirtualflowmeterviacompressedcontinuallearning-2022","author_short":["Arief, H. A.","Thomas, P. J.","Constable, K.","Katsaggelos, A. K."],"bibdata":{"bibtype":"article","type":"article","abstract":"A robust–accurate estimation of fluid flow is the main building block of a distributed virtual flow meter. Unfortunately, a big leap in algorithm development would be required for this objective to come to fruition, mainly due to the inability of current machine learning algorithms to make predictions outside the training data distribution. To improve predictions outside the training distribution, we explore the continual learning (CL) paradigm for accurately estimating the characteristics of fluid flow in pipelines. A significant challenge facing CL is the concept of catastrophic forgetting. In this paper, we provide a novel approach for how to address the forgetting problem via compressing the distributed sensor data to increase the capacity of the CL memory bank using a compressive learning algorithm. Through extensive experiments, we show that our approach provides around 8% accuracy improvement compared to other CL algorithms when applied to a real-world distributed sensor dataset collected from an oilfield. Noticeable accuracy improvement is also achieved when using our proposed approach with the CL benchmark datasets, achieving state-of-the-art accuracies for the CIFAR-10 dataset on blurry10 and blurry30 settings of 80.83% and 88.91%, respectively.","author":[{"propositions":[],"lastnames":["Arief"],"firstnames":["Hasan","Asy'ari"],"suffixes":[]},{"propositions":[],"lastnames":["Thomas"],"firstnames":["Peter","James"],"suffixes":[]},{"propositions":[],"lastnames":["Constable"],"firstnames":["Kevin"],"suffixes":[]},{"propositions":[],"lastnames":["Katsaggelos"],"firstnames":["Aggelos","K."],"suffixes":[]}],"doi":"10.3390/s22249878","issn":"1424-8220","journal":"Sensors","keywords":"continual learning,distributed acoustic sensing,virtual flow meter","month":"dec","number":"24","pages":"9878","pmid":"36560248","publisher":"MDPI","title":"Towards Building a Distributed Virtual Flow Meter via Compressed Continual Learning","url":"https://www.mdpi.com/1424-8220/22/24/9878","volume":"22","year":"2022","bibtex":"@article{arief2022towards,\nabstract = {A robust–accurate estimation of fluid flow is the main building block of a distributed virtual flow meter. Unfortunately, a big leap in algorithm development would be required for this objective to come to fruition, mainly due to the inability of current machine learning algorithms to make predictions outside the training data distribution. To improve predictions outside the training distribution, we explore the continual learning (CL) paradigm for accurately estimating the characteristics of fluid flow in pipelines. A significant challenge facing CL is the concept of catastrophic forgetting. In this paper, we provide a novel approach for how to address the forgetting problem via compressing the distributed sensor data to increase the capacity of the CL memory bank using a compressive learning algorithm. Through extensive experiments, we show that our approach provides around 8% accuracy improvement compared to other CL algorithms when applied to a real-world distributed sensor dataset collected from an oilfield. Noticeable accuracy improvement is also achieved when using our proposed approach with the CL benchmark datasets, achieving state-of-the-art accuracies for the CIFAR-10 dataset on blurry10 and blurry30 settings of 80.83% and 88.91%, respectively.},\nauthor = {Arief, Hasan Asy'ari and Thomas, Peter James and Constable, Kevin and Katsaggelos, Aggelos K.},\ndoi = {10.3390/s22249878},\nissn = {1424-8220},\njournal = {Sensors},\nkeywords = {continual learning,distributed acoustic sensing,virtual flow meter},\nmonth = {dec},\nnumber = {24},\npages = {9878},\npmid = {36560248},\npublisher = {MDPI},\ntitle = {{Towards Building a Distributed Virtual Flow Meter via Compressed Continual Learning}},\nurl = {https://www.mdpi.com/1424-8220/22/24/9878},\nvolume = {22},\nyear = {2022}\n}\n","author_short":["Arief, H. A.","Thomas, P. J.","Constable, K.","Katsaggelos, A. K."],"key":"arief2022towards","id":"arief2022towards","bibbaseid":"arief-thomas-constable-katsaggelos-towardsbuildingadistributedvirtualflowmeterviacompressedcontinuallearning-2022","role":"author","urls":{"Paper":"https://www.mdpi.com/1424-8220/22/24/9878"},"keyword":["continual learning","distributed acoustic sensing","virtual flow meter"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://sites.northwestern.edu/ivpl/files/2023/06/IVPL_Updated_publications-1.bib","dataSources":["KTWAakbPXLGfYseXn","ePKPjG8C6yvpk4mEK","37Qfzv6wRptYkoSCL","zFPgsTDAW8aDnb5iN","E6Bth2QB5BYjBMZE7","nbnEjsN7MJhurAK9x","PNQZj6FjzoxxJk4Yi","7FpDWDGJ4KgpDiGfB","bod9ms4MQJHuJgPpp","QR9t5P2cLdJuzhfzK","D8k2SxfC5dKNRFgro","7Dwzbxq93HWrJEhT6","qhF8zxmGcJfvtdeAg","fvDEHD49E2ZRwE3fb","H7crv8NWhZup4d4by","DHqokWsryttGh7pJE","vRJd4wNg9HpoZSMHD","sYxQ6pxFgA59JRhxi","w2WahSbYrbcCKBDsC","XasdXLL99y5rygCmq","3gkSihZQRfAD2KBo3","t5XMbyZbtPBo4wBGS","bEpHM2CtrwW2qE8FP","teJzFLHexaz5AQW5z"],"keywords":["continual learning","distributed acoustic sensing","virtual flow meter"],"search_terms":["towards","building","distributed","virtual","flow","meter","via","compressed","continual","learning","arief","thomas","constable","katsaggelos"],"title":"Towards Building a Distributed Virtual Flow Meter via Compressed Continual Learning","year":2022}