Advanced Neural Architectures for Anomaly Detection in Sensory Data
A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Internet of Things".
Deadline for manuscript submissions: 31 January 2026 | Viewed by 913
Special Issue Editors
Interests: visual computing; artificial intelligence robotics; virtual reality; urban visual intelligence; multisensory systems; human-computer interactions
Special Issues, Collections and Topics in MDPI journals
2. Google, Alphabet Inc., Mountain View, CA 94043, USA
Interests: AI in healthcare; generative modeling; virtual reality; time series data
Special Issue Information
Dear Colleagues,
Anomaly detection is the process of identifying unusual patterns, behaviors, or data points that deviate significantly from expected norms within a dataset. It is a critical tool in various domains, including security, surveillance, and healthcare, where identifying outliers can signal potential problems, risks, or opportunities. Techniques for anomaly detection range from simple statistical methods, such as identifying values beyond a certain threshold, to complex machine learning algorithms that leverage patterns and relationships within high-dimensional data. By detecting anomalies early, applications can mitigate risks, improve interactivity, and optimize processes.
With the advent of novel neural architectures new advances have been made in anomaly detection, especially in complex and high-dimensional datasets. Traditional methods often struggle to capture intricate patterns or adapt to evolving data distributions, limiting their effectiveness in dynamic environments. Modern neural architectures, such as autoencoders, graph neural networks, and transformers, offer the ability to learn hierarchical, contextual, and relational features, making them highly effective for identifying subtle anomalies. These architectures can uncover hidden dependencies, handle unstructured data like images or text, and adapt to real-time data streams. Furthermore, innovations in attention mechanisms and generative models enable more precise and interpretable anomaly detection, enhancing trust in critical applications like cybersecurity, finance, and healthcare. By leveraging these cutting-edge designs, researchers and practitioners can address the growing complexity of anomaly detection challenges, paving the way for more robust and scalable solutions.
This Special Issue will focus on the latest theoretical developments and applications of advanced neural architectures for anomaly detection acquired from a vast range of sensors in the form of time-series, image-based, and hyper-dimensional data. Articles focusing of multisensory systems, health care, and human-computer interactions are highly encouraged.
Dr. Alireza Tavakkoli
Dr. Prithul Sarker
Guest Editors
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. Sensors is an international peer-reviewed open access semimonthly 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.
Keywords
- anomaly detection
- neural architectures
- generative models
- density estimation
- data description
Benefits of Publishing in a Special Issue
- Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
- Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
- Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
- External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
- Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.
Further information on MDPI's Special Issue policies can be found here.
