Distributed Artificial Intelligence Enabled by oneM2M and Fog Networking

Kun Luncai; Fuchun Josephlin

doi:10.1109/CSCN.2018.8581775

Distributed Artificial Intelligence Enabled by oneM2M and Fog Networking

Kun Luncai, Fuchun Josephlin

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

Abstract

Deep learning enabled by neural networks has been proven to be an effective Artificial Intelligence (AI) algorithm in sophisticated applications. The algorithm is normally divided into two phases: learning phase and inference phase. In this research, we assume the learning phase is already accomplished offline and focus on expediting the inference phase by replacing the centralized processing of Cloud with the distributed processing of Fog. In our approach, inference algorithms in AI are distributed to multiple layers of Fog networking, constructed from oneM2M Middle Nodes. We verify the performance improvement of our proposed distributed AI/Fog system by comparing it against a Cloud-centric system based on a use case of smart shopping mall.

Original language	English
Title of host publication	2018 IEEE Conference on Standards for Communications and Networking, CSCN 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781538681466
DOIs	https://doi.org/10.1109/CSCN.2018.8581775
State	Published - 19 Dec 2018
Event	2018 IEEE Conference on Standards for Communications and Networking, CSCN 2018 - Paris, France Duration: 29 Oct 2018 → 1 Nov 2018

Publication series

Name	2018 IEEE Conference on Standards for Communications and Networking, CSCN 2018

Conference

Conference	2018 IEEE Conference on Standards for Communications and Networking, CSCN 2018
Country	France
City	Paris
Period	29/10/18 → 1/11/18

Keywords

Artificial Intelligence
Fog computing
IoT platform
OneM2M

Access to Document

10.1109/CSCN.2018.8581775

Fingerprint Dive into the research topics of 'Distributed Artificial Intelligence Enabled by oneM2M and Fog Networking'. Together they form a unique fingerprint.

Cite this

Luncai, K., & Josephlin, F. (2018). Distributed Artificial Intelligence Enabled by oneM2M and Fog Networking. In 2018 IEEE Conference on Standards for Communications and Networking, CSCN 2018 [8581775] (2018 IEEE Conference on Standards for Communications and Networking, CSCN 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CSCN.2018.8581775

@inproceedings{eedbe49e17914d8993ad4e7b875c1109,

title = "Distributed Artificial Intelligence Enabled by oneM2M and Fog Networking",

abstract = "Deep learning enabled by neural networks has been proven to be an effective Artificial Intelligence (AI) algorithm in sophisticated applications. The algorithm is normally divided into two phases: learning phase and inference phase. In this research, we assume the learning phase is already accomplished offline and focus on expediting the inference phase by replacing the centralized processing of Cloud with the distributed processing of Fog. In our approach, inference algorithms in AI are distributed to multiple layers of Fog networking, constructed from oneM2M Middle Nodes. We verify the performance improvement of our proposed distributed AI/Fog system by comparing it against a Cloud-centric system based on a use case of smart shopping mall.",

keywords = "Artificial Intelligence, Fog computing, IoT platform, OneM2M",

author = "Kun Luncai and Fuchun Josephlin",

year = "2018",

month = dec,

day = "19",

doi = "10.1109/CSCN.2018.8581775",

language = "English",

series = "2018 IEEE Conference on Standards for Communications and Networking, CSCN 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2018 IEEE Conference on Standards for Communications and Networking, CSCN 2018",

address = "United States",

note = "null ; Conference date: 29-10-2018 Through 01-11-2018",

}

Luncai, K & Josephlin, F 2018, Distributed Artificial Intelligence Enabled by oneM2M and Fog Networking. in 2018 IEEE Conference on Standards for Communications and Networking, CSCN 2018., 8581775, 2018 IEEE Conference on Standards for Communications and Networking, CSCN 2018, Institute of Electrical and Electronics Engineers Inc., 2018 IEEE Conference on Standards for Communications and Networking, CSCN 2018, Paris, France, 29/10/18. https://doi.org/10.1109/CSCN.2018.8581775

Distributed Artificial Intelligence Enabled by oneM2M and Fog Networking. / Luncai, Kun; Josephlin, Fuchun.

2018 IEEE Conference on Standards for Communications and Networking, CSCN 2018. Institute of Electrical and Electronics Engineers Inc., 2018. 8581775 (2018 IEEE Conference on Standards for Communications and Networking, CSCN 2018).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Distributed Artificial Intelligence Enabled by oneM2M and Fog Networking

AU - Luncai, Kun

AU - Josephlin, Fuchun

PY - 2018/12/19

Y1 - 2018/12/19

N2 - Deep learning enabled by neural networks has been proven to be an effective Artificial Intelligence (AI) algorithm in sophisticated applications. The algorithm is normally divided into two phases: learning phase and inference phase. In this research, we assume the learning phase is already accomplished offline and focus on expediting the inference phase by replacing the centralized processing of Cloud with the distributed processing of Fog. In our approach, inference algorithms in AI are distributed to multiple layers of Fog networking, constructed from oneM2M Middle Nodes. We verify the performance improvement of our proposed distributed AI/Fog system by comparing it against a Cloud-centric system based on a use case of smart shopping mall.

AB - Deep learning enabled by neural networks has been proven to be an effective Artificial Intelligence (AI) algorithm in sophisticated applications. The algorithm is normally divided into two phases: learning phase and inference phase. In this research, we assume the learning phase is already accomplished offline and focus on expediting the inference phase by replacing the centralized processing of Cloud with the distributed processing of Fog. In our approach, inference algorithms in AI are distributed to multiple layers of Fog networking, constructed from oneM2M Middle Nodes. We verify the performance improvement of our proposed distributed AI/Fog system by comparing it against a Cloud-centric system based on a use case of smart shopping mall.

KW - Artificial Intelligence

KW - Fog computing

KW - IoT platform

KW - OneM2M

UR - http://www.scopus.com/inward/record.url?scp=85060692761&partnerID=8YFLogxK

U2 - 10.1109/CSCN.2018.8581775

DO - 10.1109/CSCN.2018.8581775

M3 - Conference contribution

AN - SCOPUS:85060692761

T3 - 2018 IEEE Conference on Standards for Communications and Networking, CSCN 2018

BT - 2018 IEEE Conference on Standards for Communications and Networking, CSCN 2018

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 29 October 2018 through 1 November 2018

ER -

Luncai K, Josephlin F. Distributed Artificial Intelligence Enabled by oneM2M and Fog Networking. In 2018 IEEE Conference on Standards for Communications and Networking, CSCN 2018. Institute of Electrical and Electronics Engineers Inc. 2018. 8581775. (2018 IEEE Conference on Standards for Communications and Networking, CSCN 2018). https://doi.org/10.1109/CSCN.2018.8581775