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
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.