2018 IEEE International Conference on Edge Computing (EDGE) 2018
DOI: 10.1109/edge.2018.00020
|View full text |Cite
|
Sign up to set email alerts
|

Edge-Centric Efficient Regression Analytics

Abstract: We introduce an edge-centric parametric predictive analytics methodology, which contributes to real-time regression model caching and selective forwarding in the network edge where communication overhead is significantly reduced as only model's parameters and sufficient statistics are disseminated instead of raw data obtaining high analytics quality. Moreover, sophisticated model selection algorithms are introduced to combine diverse local models for predictive modeling without transferring and processing data… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
35
0

Year Published

2019
2019
2022
2022

Publication Types

Select...
3
3

Relationship

3
3

Authors

Journals

citations
Cited by 30 publications
(35 citation statements)
references
References 19 publications
0
35
0
Order By: Relevance
“…The authors in [20,21] proposed a privacy scheme called BalancePIC which aims at preserving a balance between privacy, data integrity and computational cost in edge-assisted IoT devices. In addition to this, researchers in [2] introduced a methodology for parametric regression analysis at the network edge where they defined algorithms for building regression models at the edge and selectively forwarding the parameters and other statistics to the gateway and/or cloud to support decision making during query evaluation. Such methods provide solutions to the problems associated with the traditional IoT architectures that directly forwards the contextual data to the cloud.…”
Section: Related Workmentioning
confidence: 99%
See 4 more Smart Citations
“…The authors in [20,21] proposed a privacy scheme called BalancePIC which aims at preserving a balance between privacy, data integrity and computational cost in edge-assisted IoT devices. In addition to this, researchers in [2] introduced a methodology for parametric regression analysis at the network edge where they defined algorithms for building regression models at the edge and selectively forwarding the parameters and other statistics to the gateway and/or cloud to support decision making during query evaluation. Such methods provide solutions to the problems associated with the traditional IoT architectures that directly forwards the contextual data to the cloud.…”
Section: Related Workmentioning
confidence: 99%
“…It detailed all the components involved and their functions in the system emphasizing the need for edge analysis in the mix. However, model evaluation and updating schemes were not included in the proposed system as suggested in [2]. This is a very important aspect of an IoT system as multidimensional conceptual data suffers from data bursty and statistical transiency.…”
Section: Related Workmentioning
confidence: 99%
See 3 more Smart Citations