Compared Insights on Machine-Learning Anomaly Detection for Process Control Feature

Wan, Ming; Li, Quanliang; Yao, Jiangyuan; Song, Yan; Liu, Yang; Wan, Yuxin

doi:10.32604/cmc.2022.030895

Cited by 5 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Process control research has been increasing its value and quantity due to its importance in the application in different sectors, increasing economy, productivity, and improving quality, among other aspects. There are various applications of Industry 4.0 and other technologies in process control and machine learning, which can find anomalies and then aim to stop and provide real-time solutions, offering a breakthrough in designing and implementing anomaly detection [1]. This detection is a challenging task, which must consider the restrictive characteristics of the transmission data [2].…”

Section: Introductionmentioning

confidence: 99%

Bibliometric study with statistical patterns of industry 4.0 applied to process control

Cruzado-Yesquén,

Torres-Salazar,

Alvarez-Vasquez

et al. 2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Industries are interested in offering their products or services to the consumer using high standards in process control. Industry 4.0 has emerged as a series of technological tools that can be incorporated into various processes. This research aims to perform a bibliometric analysis of the application of Industry 4.0 in process control in different sectors from 2013 to 2022 through the Scopus and Web of Science databases. The data studied were extracted from the bibliographic information of citations, abstracts, and keywords published by the articles collected. These data were processed in RStudio. As a result, it was found that the most cited articles are deep and automatic learning. Both technologies aim to reduce anomalies, increasing product efficiency, reliability, and quality. The contribution of physics in this work is shown in data mining tools, such as Bibliometrix, whose foundation is given by mathematical and statistical models, to extract data useful for future scientific studies.

show abstract

Section: Introductionmentioning

confidence: 99%

Bibliometric study with statistical patterns of industry 4.0 applied to process control

Cruzado-Yesquén,

Torres-Salazar,

Alvarez-Vasquez

et al. 2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…Under the explosive growth of data, the efficiency of representation learning with manual statistics or shallow networks has drastically decreased. In recent years, representational learning based on deep learning has made remarkable achievements in anomaly detection [16,17], and image processing [18,19]. Deploying deep learning technology in representation learning provides a new perspective on solving the issues caused by data explosion.…”

Section: Introductionmentioning

confidence: 99%

An effective attention and residual network for malware detection

Gu,

Xing,

Hou

2024

IET Communications

View full text Add to dashboard Cite

Due to its open source and large user base, Android has emerged as the most popular operating system. Android's popularity and openness have made it a prime target for malicious attackers. Permissions have received great attention from researchers because of their effectiveness in restricting applications’ access to sensitive resources. However, existing malware detection methods based on permissions are easily bypassed by inter‐application resource access. To address these issues, we combine inter‐application resource access‐related intent features with permission features. Besides, we designed a customized convolutional neural network using two squeeze‐and‐excitation blocks to learn the inherent relationships between multi‐type features. The two basic SE blocks perform squeezing operations based on average pooling and max pooling, respectively, to compute channel‐wise attention from multiple perspectives. We designed a series of experiments based on real‐world samples to evaluate the efficacy of the proposed framework. Empirical results demonstrate that our framework outperforms state‐of‐the‐art methods, achieving an accuracy of 96.29%, precision of 97.52%, recall of 94.63%, F1‐score of 96.06% and MCC of 92.60%. These promising experimental results consistently demonstrate that AMERDroid is an effective approach for Android malware detection.

show abstract

“…In other words, industrial automation control can realize automatic control, supervision, and optimization of the industrial production process, and improve production efficiency and quality by reducing staffing requirements. However, with the rapid development and deep integration of IT (Information Technology) and OT (Operational Technology), interconnection and intercommunication have been gradually infiltrating into the traditional manufacturing industry, and industrial automation control is also facing huge challenges from information security [4]. Moreover, various networks connecting application services with industrial devices have been considered another important piece of control systems, and break down the physical barrier due to the interconnection and intercommunication of networking technologies.…”

Section: Introductionmentioning

confidence: 99%

Functional Pattern-Related Anomaly Detection Approach Collaborating Binary Segmentation with Finite State Machine

Wan,

Hao,

et al. 2023

CMC

View full text Add to dashboard Cite

The process control-oriented threat, which can exploit OT (Operational Technology) vulnerabilities to forcibly insert abnormal control commands or status information, has become one of the most devastating cyber attacks in industrial automation control. To effectively detect this threat, this paper proposes one functional patternrelated anomaly detection approach, which skillfully collaborates the BinSeg (Binary Segmentation) algorithm with FSM (Finite State Machine) to identify anomalies between measuring data and control data. By detecting the change points of measuring data, the BinSeg algorithm is introduced to generate some initial sequence segments, which can be further classified and merged into different functional patterns due to their backward difference means and lengths. After analyzing the pattern association according to the Bayesian network, one functional state transition model based on FSM, which accurately describes the whole control and monitoring process, is constructed as one feasible detection engine. Finally, we use the typical SWaT (Secure Water Treatment) dataset to evaluate the proposed approach, and the experimental results show that: for one thing, compared with other changepoint detection approaches, the BinSeg algorithm can be more suitable for the optimal sequence segmentation of measuring data due to its highest detection accuracy and least consuming time; for another, the proposed approach exhibits relatively excellent detection ability, because the average detection precision, recall rate and F1-score to identify 10 different attacks can reach 0.872, 0.982 and 0.896, respectively.

show abstract

Compared Insights on Machine-Learning Anomaly Detection for Process Control Feature

Cited by 5 publications

References 29 publications

Bibliometric study with statistical patterns of industry 4.0 applied to process control

Bibliometric study with statistical patterns of industry 4.0 applied to process control

An effective attention and residual network for malware detection

Functional Pattern-Related Anomaly Detection Approach Collaborating Binary Segmentation with Finite State Machine

Contact Info

Product

Resources

About