Show simple item record

dc.contributor.authorAli, Muhammad
dc.contributor.authorAnjum, Ashiq
dc.contributor.authorYaseen, M. Usman
dc.contributor.authorZamani, A. Reza
dc.contributor.authorBalouek-Thomert, Daniel
dc.contributor.authorRana, Omer
dc.contributor.authorParashar, Manish
dc.date.accessioned2018-05-22T13:16:01Z
dc.date.available2018-05-22T13:16:01Z
dc.date.issued2018-05-14
dc.identifier.citationAli, M. et al (2018) 'Edge enhanced deep learning system for large-scale video stream analytics.', Proceedings of the 2nd International Conference on Fog and Edge Computing (ICFEC), Washington DC, 1-3 May.en
dc.identifier.isbn9781538664889
dc.identifier.doi10.1109/CFEC.2018.8358733
dc.identifier.urihttp://hdl.handle.net/10545/622729
dc.description.abstractApplying deep learning models to large-scale IoT data is a compute-intensive task and needs significant computational resources. Existing approaches transfer this big data from IoT devices to a central cloud where inference is performed using a machine learning model. However, the network connecting the data capture source and the cloud platform can become a bottleneck. We address this problem by distributing the deep learning pipeline across edge and cloudlet/fog resources. The basic processing stages and trained models are distributed towards the edge of the network and on in-transit and cloud resources. The proposed approach performs initial processing of the data close to the data source at edge and fog nodes, resulting in significant reduction in the data that is transferred and stored in the cloud. Results on an object recognition scenario show 71\% efficiency gain in the throughput of the system by employing a combination of edge, in-transit and cloud resources when compared to a cloud-only approach.
dc.description.sponsorshipN/Aen
dc.language.isoenen
dc.publisherIEEEen
dc.relation.urlhttps://ieeexplore.ieee.org/document/8358733/en
dc.subjectEdge computingen
dc.subjectDeep learningen
dc.subjectMachine learningen
dc.subjectCloud computingen
dc.subjectStream analyticsen
dc.titleEdge enhanced deep learning system for large-scale video stream analytics.en
dc.typeMeetings and Proceedingsen
dc.contributor.departmentUniversity of Derbyen
dc.contributor.departmentRutgers Universityen
dc.contributor.departmentUniversity of Cardiffen
dc.identifier.journalProceedings of the 2nd International Conference on Fog and Edge Computing (ICFEC)en
html.description.abstractApplying deep learning models to large-scale IoT data is a compute-intensive task and needs significant computational resources. Existing approaches transfer this big data from IoT devices to a central cloud where inference is performed using a machine learning model. However, the network connecting the data capture source and the cloud platform can become a bottleneck. We address this problem by distributing the deep learning pipeline across edge and cloudlet/fog resources. The basic processing stages and trained models are distributed towards the edge of the network and on in-transit and cloud resources. The proposed approach performs initial processing of the data close to the data source at edge and fog nodes, resulting in significant reduction in the data that is transferred and stored in the cloud. Results on an object recognition scenario show 71\% efficiency gain in the throughput of the system by employing a combination of edge, in-transit and cloud resources when compared to a cloud-only approach.


Files in this item

Thumbnail
Name:
Edge-Enhanced-Deep-Learning-IC ...
Size:
1.216Mb
Format:
PDF
Description:
Author Accepted Manuscript

This item appears in the following Collection(s)

Show simple item record