Record link: 
http://hdl.handle.net/20.500.12708/192177
-
Title: 
Data-centric Edge-AI: A Symbolic Representation Use Case
en
Citation: 
Ilager, S. S., De Maio, V., Lujic, I., & Brandic, I. (2023). Data-centric Edge-AI: A Symbolic Representation Use Case. In 2023 IEEE International Conference on Edge Computing and Communications (EDGE) (pp. 301–308). IEEE. https://doi.org/10.1109/EDGE60047.2023.00052
-
Publisher DOI: 
10.1109/EDGE60047.2023.00052
-
Publication Type: 
Inproceedings - Full-Paper Contribution
en
Language: 
English
-
Authors: 
Ilager, Shashikant Shankar 
De Maio, Vincenzo 
Lujic, Ivan 
Brandic, Ivona 
-
Organisational Unit: 
E194-04 - Forschungsbereich Data Science 
-
Published in: 
2023 IEEE International Conference on Edge Computing and Communications (EDGE) 
-
ISBN: 
979-8-3503-0483-1
-
Date (published): 
1-Sep-2023
-
Event name: 
2023 IEEE International Conference on Edge Computing and Communications (EDGE) 
en
Event date: 
2-Jul-2023 - 8-Jul-2023
-
Event place: 
Chicago, United States of America (the)
-
Number of Pages: 
8
-
Publisher: 
IEEE, Piscataway
-
Peer reviewed: 
Yes
-
Keywords: 
Computing; Edge Computing; Edge AI
en
Abstract: 
Today’s machine learning pipelines are primarily executed in the cloud, from data storage to data processing, model training, and deployment. However, machine learning is moving to edge devices, creating the demand for AI applications at the edge, known as Edge-AI. Traditional data management practices applied in the cloud are proving to be inefficient for Edge-AI, due to resource and energy constraints of edge devices and real-time requirements of applications. This paper identifies the challenges associated with data processing for Edge-AI. We then discuss methods for efficient data processing at the edge, leading to data-centric Edge-AI. As a use case scenario, we discuss the symbolic representation of time series data and explain how it could help save the cost of data storage and processing in developing Edge-AI applications.
de
Research Areas: 
Logic and Computation: 50%
Mathematical and Algorithmic Foundations: 20%
Computer Science Foundations: 30%
-
Science Branch: 
1020 - Informatik: 90%
5020 - Wirtschaftswissenschaften: 10%
-
Appears in Collections:
Conference Paper

Show full item record

Page view(s)

175
checked on Jan 18, 2024

Google ScholarTM

Check