entropy-logo

Journal Browser

Journal Browser

Information Theory for Anomaly Detection in Complex Systems

A special issue of Entropy (ISSN 1099-4300). This special issue belongs to the section "Multidisciplinary Applications".

Deadline for manuscript submissions: closed (20 July 2022) | Viewed by 8081

Special Issue Editor

Department of Information and Communication Technology, University of Agder, 4630 Kristiansand, Norway
Interests: machine learning; deep learning; anomaly detection; trustworthy AI; explainable AI; AI verification and verifiability; AI morality

Special Issue Information

Dear Colleagues,

In the future, humans and technology-enabled systems will interact in smart spaces which are increasingly open, connected, and intelligent. People, processes, services, and things will come together in systems such as smart homes, buildings, industrial plants, and cities. Data from very large, ubiquitous, complex systems consisting of many interacting components (e.g., power generation, transportation and communication systems, manufacturing businesses, cities, and economies) will routinely be collected through IoT sensors, video surveillance, social network streams, transactions, economic activities, etc. Modelling complex systems for monitoring, forecasting, and decision-making is challenging due to their dynamic nature and complex patterns in the data that evolve over time. 

The interconnectedness of complex systems renders them more vulnerable to malfunction and intrusions, which may be reflected in the collected time series in (perhaps) very subtle changes (i.e., outliers can only be understood in the context of the temporal changes in the data streams). It is an inherently very difficult problem, as some anomalies may never have been seen before, making examples unavailable. Besides the detection and classification of anomalies, inference about the root causes of detected anomalies in general real-world setting is not yet well understood. 

In many applications, the valuable information associated with rare events is found in a very small subset of the overall collected data: rare events dominate the importance of the total information of the collected big data. Unlike machine learning modelling which aims at characterizing big data in terms of statistics to understand its general structure, the fundamental question from the perspective of information theory is the effective measurement of the information with importance for the low-probability events. Thus, information-theoretic measures can be used to create novel anomaly detection models. 

We welcome the submission of original research and survey articles on anomaly detection in multivariate time series using information-theoretic methods including but not limited to

  • Entropy-based anomaly detection;
  • Anomaly detection in time series of graphs;
  • Graph signal entropy;
  • Cross-entropy anomaly detection;
  • Hybrid approaches (information theory/statistical learning/machine learning) to anomaly detection;

with applications such as

  • System health monitoring;
  • Network security;
  • Social media;
  • Health informatics;
  • Fraud detection;
  • Video surveillance.

Prof. Dr. Christian Omlin
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Entropy is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Published Papers (3 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

28 pages, 5916 KiB  
Article
A Bearing Fault Diagnosis Method Based on PAVME and MEDE
by Xiaoan Yan, Yadong Xu, Daoming She and Wan Zhang
Entropy 2021, 23(11), 1402; https://0-doi-org.brum.beds.ac.uk/10.3390/e23111402 - 25 Oct 2021
Cited by 16 | Viewed by 1853
Abstract
When rolling bearings have a local fault, the real bearing vibration signal related to the local fault is characterized by the properties of nonlinear and nonstationary. To extract the useful fault features from the collected nonlinear and nonstationary bearing vibration signals and improve [...] Read more.
When rolling bearings have a local fault, the real bearing vibration signal related to the local fault is characterized by the properties of nonlinear and nonstationary. To extract the useful fault features from the collected nonlinear and nonstationary bearing vibration signals and improve diagnostic accuracy, this paper proposes a new bearing fault diagnosis method based on parameter adaptive variational mode extraction (PAVME) and multiscale envelope dispersion entropy (MEDE). Firstly, a new method hailed as parameter adaptive variational mode extraction (PAVME) is presented to process the collected original bearing vibration signal and obtain the frequency components related to bearing faults, where its two important parameters (i.e., the penalty factor and mode center-frequency) are automatically determined by whale optimization algorithm. Subsequently, based on the processed bearing vibration signal, an effective complexity evaluation approach named multiscale envelope dispersion entropy (MEDE) is calculated for conducting bearing fault feature extraction. Finally, the extracted fault features are fed into the k-nearest neighbor (KNN) to automatically identify different health conditions of rolling bearing. Case studies and contrastive analysis are performed to validate the effectiveness and superiority of the proposed method. Experimental results show that the proposed method can not only effectively extract bearing fault features, but also obtain a high identification accuracy for bearing fault patterns under single or variable speed. Full article
(This article belongs to the Special Issue Information Theory for Anomaly Detection in Complex Systems)
Show Figures

Figure 1

14 pages, 1523 KiB  
Article
Research on the Fastest Detection Method for Weak Trends under Noise Interference
by Guang Li, Jing Liang and Caitong Yue
Entropy 2021, 23(8), 1093; https://0-doi-org.brum.beds.ac.uk/10.3390/e23081093 - 22 Aug 2021
Cited by 1 | Viewed by 1894
Abstract
Trend anomaly detection is the practice of comparing and analyzing current and historical data trends to detect real-time abnormalities in online industrial data-streams. It has the advantages of tracking a concept drift automatically and predicting trend changes in the shortest time, making it [...] Read more.
Trend anomaly detection is the practice of comparing and analyzing current and historical data trends to detect real-time abnormalities in online industrial data-streams. It has the advantages of tracking a concept drift automatically and predicting trend changes in the shortest time, making it important both for algorithmic research and industry. However, industrial data streams contain considerable noise that interferes with detecting weak anomalies. In this paper, the fastest detection algorithm “sliding nesting” is adopted. It is based on calculating the data weight in each window by applying variable weights, while maintaining the method of trend-effective integration accumulation. The new algorithm changes the traditional calculation method of the trend anomaly detection score, which calculates the score in a short window. This algorithm, SNWFD–DS, can detect weak trend abnormalities in the presence of noise interference. Compared with other methods, it has significant advantages. An on-site oil drilling data test shows that this method can significantly reduce delays compared with other methods and can improve the detection accuracy of weak trend anomalies under noise interference. Full article
(This article belongs to the Special Issue Information Theory for Anomaly Detection in Complex Systems)
Show Figures

Figure 1

24 pages, 7257 KiB  
Article
A Framework for Detecting System Performance Anomalies Using Tracing Data Analysis
by Iman Kohyarnejadfard, Daniel Aloise, Michel R. Dagenais and Mahsa Shakeri
Entropy 2021, 23(8), 1011; https://0-doi-org.brum.beds.ac.uk/10.3390/e23081011 - 03 Aug 2021
Cited by 8 | Viewed by 2693
Abstract
Advances in technology and computing power have led to the emergence of complex and large-scale software architectures in recent years. However, they are prone to performance anomalies due to various reasons, including software bugs, hardware failures, and resource contentions. Performance metrics represent the [...] Read more.
Advances in technology and computing power have led to the emergence of complex and large-scale software architectures in recent years. However, they are prone to performance anomalies due to various reasons, including software bugs, hardware failures, and resource contentions. Performance metrics represent the average load on the system and do not help discover the cause of the problem if abnormal behavior occurs during software execution. Consequently, system experts have to examine a massive amount of low-level tracing data to determine the cause of a performance issue. In this work, we propose an anomaly detection framework that reduces troubleshooting time, besides guiding developers to discover performance problems by highlighting anomalous parts in trace data. Our framework works by collecting streams of system calls during the execution of a process using the Linux Trace Toolkit Next Generation(LTTng), sending them to a machine learning module that reveals anomalous subsequences of system calls based on their execution times and frequency. Extensive experiments on real datasets from two different applications (e.g., MySQL and Chrome), for varying scenarios in terms of available labeled data, demonstrate the effectiveness of our approach to distinguish normal sequences from abnormal ones. Full article
(This article belongs to the Special Issue Information Theory for Anomaly Detection in Complex Systems)
Show Figures

Figure 1

Back to TopTop