An ADMM-based Optimal Transmission Frequency Management System for IoT Edge Intelligence

Wu, Hongde; O’Connor, Noel E.; Bruton, Jennifer; Liu, Mingming

doi:10.1109/wf-iot51360.2021.9595357

Cited by 2 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We first review the optimal transmission frequency management system in our previous work [10] followed by a review of related works in relation to anomaly detection for IoT.…”

Section: Related Workmentioning

confidence: 99%

“…Our objective in this work is to further explore the benefits of edge AI. Specifically, we wish to investigate how edge AI can be leveraged to carry out real-time anomaly detection in the IoT system proposed in our previous work [10], where a group of IoT devices work collaboratively to seek for an optimal resource allocation scheme of their transmission frequencies using the alternating direction method of multipliers (ADMM)based optimisation method. We note that each IoT edge device in the proposed system [10] has the potential to adjust its allocated data transmission frequency through a user-defined utility function, which is only accessible to each local device, and some model parameters.…”

Section: Introductionmentioning

confidence: 99%

“…Specifically, we wish to investigate how edge AI can be leveraged to carry out real-time anomaly detection in the IoT system proposed in our previous work [10], where a group of IoT devices work collaboratively to seek for an optimal resource allocation scheme of their transmission frequencies using the alternating direction method of multipliers (ADMM)based optimisation method. We note that each IoT edge device in the proposed system [10] has the potential to adjust its allocated data transmission frequency through a user-defined utility function, which is only accessible to each local device, and some model parameters. In a real-world setup, this implies that a cyberattacker may wish to manipulate the functions in order to implicitly increase or decrease the transmission frequency of any IoT devices for his own benefits in attacking the network.…”

Section: Introductionmentioning

confidence: 99%

“…The key focus of our previous work [10] was to propose an optimisation framework for an IoT network so that the transmission frequency of the connected IoT devices can be dynamically adjusted to their optimal values through an ADMM-based iterative optimisation method. In this work, we focus on the design of an anomaly detector on top of the system we proposed in [10], which is able to infer anomalies that may occur in the underlying IoT transmission management system in real time. Thus, the scope of work is significantly extended in comparison to [10].…”

Section: Introductionmentioning

confidence: 99%

“…In this work, we focus on the design of an anomaly detector on top of the system we proposed in [10], which is able to infer anomalies that may occur in the underlying IoT transmission management system in real time. Thus, the scope of work is significantly extended in comparison to [10]. 2.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Real-Time Anomaly Detection for an ADMM-Based Optimal Transmission Frequency Management System for IoT Devices

O’Connor

Bruton

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

In this paper, we investigate different scenarios of anomaly detection on decentralised Internet of Things (IoT) applications. Specifically, an anomaly detector is devised to detect different types of anomalies for an IoT data management system, based on the decentralised alternating direction method of multipliers (ADMM), which was proposed in our previous work. The anomaly detector only requires limited information from the IoT system, and can be operated using both a mathematical-rule-based approach and the deep learning approach proposed in the paper. Our experimental results show that detection based on mathematical approach is simple to implement, but it also comes with lower detection accuracy (78.88%). In contrast, the deep-learning-enabled approach can easily achieve a higher detection accuracy (96.28%) in the real world working environment.

show abstract

“…We first review the optimal transmission frequency management system in our previous work [10] followed by a review of related works in relation to anomaly detection for IoT.…”

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%