Metabolic engineering of the cyanobacterium Synechocystis sp. PCC 6803 for the production of astaxanthin
2020 Spring. Includes bibliographical references. Distributed Stream Processing Engines (DSPEs) have seen significant deployment growth along with an increase in streaming data sources such as sensor networks. These DSPEs enable processing large amounts of streaming data in a cluster of commodity ma...
Main Author: | |
---|---|
Other Authors: | , , |
Format: | Text |
Language: | English |
Published: |
Colorado State University. Libraries
2020
|
Subjects: | |
Online Access: | https://hdl.handle.net/10217/208427 |
id |
ftcolostateunidc:oai:mountainscholar.org:10217/208427 |
---|---|
record_format |
openpolar |
spelling |
ftcolostateunidc:oai:mountainscholar.org:10217/208427 2023-06-11T04:15:46+02:00 Metabolic engineering of the cyanobacterium Synechocystis sp. PCC 6803 for the production of astaxanthin Pereira, Aaron Pallickara, Sangmi Pallickara, Shrideep Zahran, Sammy 2020-06-22T11:52:34Z born digital masters theses application/pdf https://hdl.handle.net/10217/208427 English eng eng Colorado State University. Libraries 2020- CSU Theses and Dissertations Pereira_colostate_0053N_15904.pdf https://hdl.handle.net/10217/208427 Copyright and other restrictions may apply. User is responsible for compliance with all applicable laws. For information about copyright law, please see https://libguides.colostate.edu/copyright. Text 2020 ftcolostateunidc 2023-05-04T17:36:44Z 2020 Spring. Includes bibliographical references. Distributed Stream Processing Engines (DSPEs) have seen significant deployment growth along with an increase in streaming data sources such as sensor networks. These DSPEs enable processing large amounts of streaming data in a cluster of commodity machines to extract knowledge and insights in real-time. Due to fluctuating data arrival rates in real-world applications, modern DSPEs often provide auto-scaling. However, the existing designs of advanced analytical frameworks are not effectively aligned with scalable streaming computing environments. We have designed and developed ORCA, a federated learning architecture that supports the training of traditional Artificial Neural Networks as well as Convolutional Neural Networks and Long Short-term Memory Network based models while ensuring resiliency during scaling. ORCA also introduces dynamic adjustment of the 'elasticity' hyper-parameter for rescaled computing environments. We estimate this elasticity hyper-parameter using reinforcement learning. Our empirical benchmarks show that ORCA is capable of achieving an MSE of 0.038 over real-world streaming datasets. Text Orca Digital Collections of Colorado (Colorado State University) |
institution |
Open Polar |
collection |
Digital Collections of Colorado (Colorado State University) |
op_collection_id |
ftcolostateunidc |
language |
English |
description |
2020 Spring. Includes bibliographical references. Distributed Stream Processing Engines (DSPEs) have seen significant deployment growth along with an increase in streaming data sources such as sensor networks. These DSPEs enable processing large amounts of streaming data in a cluster of commodity machines to extract knowledge and insights in real-time. Due to fluctuating data arrival rates in real-world applications, modern DSPEs often provide auto-scaling. However, the existing designs of advanced analytical frameworks are not effectively aligned with scalable streaming computing environments. We have designed and developed ORCA, a federated learning architecture that supports the training of traditional Artificial Neural Networks as well as Convolutional Neural Networks and Long Short-term Memory Network based models while ensuring resiliency during scaling. ORCA also introduces dynamic adjustment of the 'elasticity' hyper-parameter for rescaled computing environments. We estimate this elasticity hyper-parameter using reinforcement learning. Our empirical benchmarks show that ORCA is capable of achieving an MSE of 0.038 over real-world streaming datasets. |
author2 |
Pallickara, Sangmi Pallickara, Shrideep Zahran, Sammy |
format |
Text |
author |
Pereira, Aaron |
spellingShingle |
Pereira, Aaron Metabolic engineering of the cyanobacterium Synechocystis sp. PCC 6803 for the production of astaxanthin |
author_facet |
Pereira, Aaron |
author_sort |
Pereira, Aaron |
title |
Metabolic engineering of the cyanobacterium Synechocystis sp. PCC 6803 for the production of astaxanthin |
title_short |
Metabolic engineering of the cyanobacterium Synechocystis sp. PCC 6803 for the production of astaxanthin |
title_full |
Metabolic engineering of the cyanobacterium Synechocystis sp. PCC 6803 for the production of astaxanthin |
title_fullStr |
Metabolic engineering of the cyanobacterium Synechocystis sp. PCC 6803 for the production of astaxanthin |
title_full_unstemmed |
Metabolic engineering of the cyanobacterium Synechocystis sp. PCC 6803 for the production of astaxanthin |
title_sort |
metabolic engineering of the cyanobacterium synechocystis sp. pcc 6803 for the production of astaxanthin |
publisher |
Colorado State University. Libraries |
publishDate |
2020 |
url |
https://hdl.handle.net/10217/208427 |
genre |
Orca |
genre_facet |
Orca |
op_relation |
2020- CSU Theses and Dissertations Pereira_colostate_0053N_15904.pdf https://hdl.handle.net/10217/208427 |
op_rights |
Copyright and other restrictions may apply. User is responsible for compliance with all applicable laws. For information about copyright law, please see https://libguides.colostate.edu/copyright. |
_version_ |
1768372855558373376 |