Ali, Muhammad, Anjum, Ashiq, Yaseen, M. Usman, Zamani, A. Reza, Balouek-Thomert, Daniel, Rana, Omer F. ORCID: https://orcid.org/0000-0003-3597-2646 and Parashar, Manish 2018. Edge enhanced deep learning system for large-scale video stream analytics. Presented at: 2018 IEEE 2nd International Conference on Fog and Edge Computing (ICFEC), Washington DC, USA, 1-3 May 2018. 2018 IEEE 2nd International Conference on Fog and Edge Computing (ICFEC). IEEE, 10.1109/CFEC.2018.8358733 |
Preview |
PDF
- Accepted Post-Print Version
Download (1MB) | Preview |
Abstract
Applying 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.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Date Type: | Published Online |
Status: | Published |
Schools: | Computer Science & Informatics |
Publisher: | IEEE |
ISBN: | 9781538664896 |
Date of First Compliant Deposit: | 15 May 2018 |
Date of Acceptance: | 15 February 2018 |
Last Modified: | 23 Oct 2022 13:42 |
URI: | https://orca.cardiff.ac.uk/id/eprint/111447 |
Citation Data
Cited 54 times in Scopus. View in Scopus. Powered By ScopusĀ® Data
Actions (repository staff only)
Edit Item |