Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence

Deng, Shuiguang; Zhao, Hailiang; Fang, Weijia; Yin, Jianwei; Dustdar, Schahram; Zomaya, Albert Y.

doi:10.1109/jiot.2020.2984887

Cited by 714 publications

(281 citation statements)

References 53 publications

Supporting

Mentioning

280

Contrasting

Unclassified

Order By: Relevance

“…In recent years, we are experiencing a great surge of Edge Intelligence (see in [4]- [6]). Numerous attempts have been made to combine AI techniques and edge, tapping the profound potential of the ubiquitous deployed edge devices.…”

Section: Related Workmentioning

confidence: 99%

“…Formally, we let c t,n [1/µ t,n , s t,n , M/B t,n ] denote the contextual feature vectors that are collected by the scheduler before the scheduling phase. More explicitly, µ t,n is the ratio of available computation capacity of client n over round t. We can simply comprehend µ t,n as the available CPU ratio of the client 4 . A binary indicator s t,n indicates if client n has participated in training in the last round.…”

Section: Applicationmentioning

confidence: 99%

See 1 more Smart Citation

An Efficiency-Boosting Client Selection Scheme for Federated Learning With Fairness Guarantee

Huang

Lin

et al. 2021

IEEE Trans. Parallel Distrib. Syst.

150

View full text Add to dashboard Cite

The issue of potential privacy leakage during centralized AI's model training has drawn intensive concern from the public. A Parallel and Distributed Computing (or PDC) scheme, termed Federated Learning (FL), has emerged as a new paradigm to cope with the privacy issue by allowing clients to perform model training locally, without the necessity to upload their personal sensitive data. In FL, the number of clients could be sufficiently large, but the bandwidth available for model distribution and re-upload is quite limited, making it sensible to only involve part of the volunteers to participate in the training process. The client selection policy is critical to an FL process in terms of training efficiency, the final model's quality as well as fairness. In this paper, we will model the fairness guaranteed client selection as a Lyapunov optimization problem and then a C 2 MAB-based method is proposed for estimation of the model exchange time between each client and the server, based on which we design a fairness guaranteed algorithm termed RBCS-F for problem-solving. The regret of RBCS-F is strictly bounded by a finite constant, justifying its theoretical feasibility. Barring the theoretical results, more empirical data can be derived from our real training experiments on public datasets.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Applicationmentioning

confidence: 99%

An Efficiency-Boosting Client Selection Scheme for Federated Learning With Fairness Guarantee

Huang

Lin

et al. 2021

IEEE Trans. Parallel Distrib. Syst.

150

View full text Add to dashboard Cite

show abstract

“…Edge AI is in its early stages, attracting many companies and researchers to its study and application development. Considering the restrictions on energy consumption, processing power and memory size existing in Device Edge, development efforts have focused on framework design, model adaptation and processor acceleration [5].…”

Section: B Edge Aimentioning

confidence: 99%

Towards to an Embedded Edge AI Implementation for Longitudinal Rip Detection in Conveyor Belt

Klippel¹,

Oliveira²,

Maslov³

et al. 2020

Anais Estendidos Do X Simpósio Brasileiro De Engenharia De Sistemas Computacionais (SBESC Estendido 2020)

View full text Add to dashboard Cite

The use of deep learning on edge AI to detect failures in conveyor belts solves a complex problem of iron ore beneficiation plants. Losses in the order of thousands of dollars are caused by failures in these assets. The existing fault detection systems currently do not have the necessary efficiency and complete loss of belts is common. Correct fault detection is necessary to reduce financial losses and unnecessary risk exposure by maintenance personnel. This problem is addressed by the present work with the training of a deep learning model for detecting images of failures of the conveyor belt. The resulting model is converted and executed in an edge device located near the conveyor belt to stop it in case a failure is detected. The results obtained in the development and tests carried out to date show the feasibility of using Edge AI to solve complex problems in a mining environment such as detecting longitudinal rips and stimulate the continuity of the work considering new scenarios and operational conditions in the search for a robust and replicable solution.

show abstract

“…The Cloud layer takes care of: (i) collecting and managing raw IoT service usage data, (ii) training an activity model, and (iii) managing Edge nodes. We assume that each smart home comes with an Edge server to allow low levels of latency for decision making [12]. The trained activity model is deployed on the Edge to recognize activities and predict next action within an activity.…”

Section: Activity Learning Frameworkmentioning

confidence: 99%

Enabling Edge Intelligence for Activity Recognition in Smart Homes

Zhang

et al. 2018

2018 IEEE 15th International Conference on Mobile Ad Hoc and Sensor Systems (MASS)

View full text Add to dashboard Cite

We propose a novel activity learning framework based on Edge Cloud architecture for the purpose of recognizing and predicting human activities. Although activity recognition has been vastly studied by many researchers, the temporal features that constitute an activity, which can provide useful insights for activity models, have not been exploited to their full potentials by mining algorithms. In this paper, we utilize temporal features for activity recognition and prediction in a single smart home setting. We discover activity patterns and temporal relations such as the order of activities from real data to develop a prompting system. Analysis of real data collected from smart homes was used to validate the proposed method.

show abstract

Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence

Cited by 714 publications

References 53 publications

An Efficiency-Boosting Client Selection Scheme for Federated Learning With Fairness Guarantee

An Efficiency-Boosting Client Selection Scheme for Federated Learning With Fairness Guarantee

Towards to an Embedded Edge AI Implementation for Longitudinal Rip Detection in Conveyor Belt

Enabling Edge Intelligence for Activity Recognition in Smart Homes

Contact Info

Product

Resources

About