ASTREAM: Data-Stream-Driven Scalable Anomaly Detection With Accuracy Guarantee in IIoT Environment

Yang, Yongrong; Yang, Xuan; Heidari, Mohsen; Khan, Mohammad Ayoub; Srivastava, Gautam; Khosravi, Mohammad R.; Qi, Lianyong

doi:10.1109/tnse.2022.3157730

Cited by 60 publications

(33 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, they showed that the false alarms can be reduced up to 75% compared to the conventional deep learning approaches. Considering data streams in industrial IoT environments, Yang et al [17] proposed a tree structure-based anomaly detection system, where the authors incorporates the window sliding, detection strategy changing, and model updating mechanisms into the locality-sensitive hashing-based iForest model [18] [19] to handle the infiniteness of data streams in real-time scenario. Similarly, Qi et al [20] proposed an intrusion detection system for multiaspect data streams by combining locality-sensitive hashing, isolation forest, and principal component analysis techniques.…”

Section: Related Workmentioning

confidence: 99%

An Enhanced AI-Based Network Intrusion Detection System Using Generative Adversarial Networks

Park

Lee

Kim

et al. 2023

IEEE Internet Things J.

View full text Add to dashboard Cite

As communication technology advances, various and heterogeneous data are communicated in distributed environments through network systems. Meanwhile, along with the development of communication technology, the attack surface has expanded, and concerns regarding network security have increased. Accordingly, to deal with potential threats, research on Network Intrusion Detection Systems (NIDS) has been actively conducted. Among the various NIDS technologies, recently interest is focused on artificial intelligence(AI)-based anomaly detection systems, and various models have been proposed to improve the performance of NIDS. However, there still exists the problem of data imbalance, in which AI models cannot sufficiently learn malicious behavior and thus fail to detect network threats accurately. In this study, we propose a novel AI-based network intrusion detection system that can efficiently resolve the data imbalance problem and improve the performance of the previous systems. To address the aforementioned problem, we leveraged a state-of-the-art generative model that could generate plausible synthetic data for minor attack traffic. In particular, we focused on the reconstruction error and Wasserstein distancebased generative adversarial networks, and autoencoder-driven deep learning models. To demonstrate the effectiveness of our system, we performed comprehensive evaluations over various datasets and demonstrated that the proposed systems significantly outperformed the previous AI-based NIDS.

show abstract

Section: Related Workmentioning

confidence: 99%

An Enhanced AI-Based Network Intrusion Detection System Using Generative Adversarial Networks

Park

Lee

Kim

et al. 2023

IEEE Internet Things J.

View full text Add to dashboard Cite

show abstract

“…The approach combines sliding window, model update, and change detection strategies with LSHiForest to achieve accurate and efficient anomaly detection with better scalability. The approach is evaluated on the KDDCUP99 dataset, and the results show that it outperforms baselines in terms of accuracy and efficiency [7]. A third paper introduces the concept of advanced machine-metameric dimension (AmD) to analyze the efficacy, efficiency, and effectiveness of updated Heterogeneous Industrial Internet of Things (HetIoT) machines.…”

Section: Literature Surveymentioning

confidence: 99%

“…Since it is required to control the position of the valve, the calculation algorithm programming form upgraded from Equations ( 5) and (7) to P n at nth sampling instant as…”

Section: Process Modelmentioning

confidence: 99%

IIoT‐Based Intelligent Process Control for Crude Oil Separation: Investigating the Impact of Model‐Based Control and Genetic Algorithms

et al. 2023

View full text Add to dashboard Cite

Integrating the Internet of Things (IIoT) with intelligent process control can improve the performance and efficiency of various industrial processes. However, there is a need for continued research on integrating IIoT-based control with advanced techniques such as model-based control and genetic algorithms to fully realize these benefits. This study investigates the impact of such integration on the performance of crude oil separation processes. To this end, we implemented IIoT-based intelligent process control with model-based control and genetic algorithms using specific IIoT devices and platforms, such as SCADAPACK 535E and FactoryTalk. The results of our implementation show that this technique can significantly improve the quality of crude oil separation, with an increase from 95% to 99% over two months of production. Overall, our findings suggest that integrating IIoT-based intelligent process control with advanced techniques such as model-based control and genetic algorithms can significantly improve the performance of crude oil separation processes and may have similar benefits in other industrial processes. Further research is needed to fully understand these techniques’ potential in different contexts and identify best practices for their implementation.

show abstract

“…U LTRA-RELIABLE and low-latency communications are one of the key services which is present in the current fifth-generation (5G) as well as the futuristic sixthgeneration (6G) networks [1]- [4].…”

Section: Introductionmentioning

confidence: 99%

Intercell Interference Coordination for UAV Enabled URLLC With Perfect/Imperfect CSI Using Cognitive Radio

Ranjha

Javed

Srivastava

et al. 2023

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

Ultra-reliable and low latency communications (URLLC) will be the backbone of the upcoming sixth-generation (6G) systems and will facilitate mission-critical scenarios. A design accounting for stringent reliability and latency requirements for URLLC systems poses a challenge for both industry and academia. Recently, unmanned aerial vehicles (UAV) have emerged as a potential candidate to support communications in futuristic wireless systems due to providing favourable channel gains thanks to Lineof-Sight (LoS) communications. However, usage of UAV in cellular infrastructure increases interference in aerial and terrestrial user equipment (UE) limiting the performance gain of UAV-assisted cellular systems. To resolve these issues, we propose low-complexity algorithms for intercell interference coordination (ICIC) using cognitive radio when single and multi-UAVs are deployed in a cellular environment to facilitate URLLC services. Moreover, we model BS-to-UAV (B2U) interference in downlink communication, whereas in the uplink we model UAV-to-BS (U2B), UAV-to-UAV (U2U), and UE-to-UAV (UE2U) interference under perfect/imperfect channel state information (CSI). Results demonstrate that the proposed perfect ICIC accounts for fairness among UAVs especially in downlink communications compared to conventional ICIC algorithms. Furthermore, in general, the proposed UAV-sensing assisted ICIC and perfect ICIC algorithms yield better performance than conventional ICIC for both uplink and downlink for the single and multi-UAV framework.INDEX TERMS URLLC, multi-UAV, cognitive radio, intercell interference coordination (ICIC).

show abstract

ASTREAM: Data-Stream-Driven Scalable Anomaly Detection With Accuracy Guarantee in IIoT Environment

Cited by 60 publications

References 39 publications

An Enhanced AI-Based Network Intrusion Detection System Using Generative Adversarial Networks

An Enhanced AI-Based Network Intrusion Detection System Using Generative Adversarial Networks

IIoT‐Based Intelligent Process Control for Crude Oil Separation: Investigating the Impact of Model‐Based Control and Genetic Algorithms

Intercell Interference Coordination for UAV Enabled URLLC With Perfect/Imperfect CSI Using Cognitive Radio

Contact Info

Product

Resources

About