Time Series Anomaly Detection

Time series anomaly detection is a fundamental data mining task that aims to identify data points that significantly differ from the majority of the dataset. It extracts useful information from the data and establishes a corresponding detection model through deep learning from time series data. Such techniques find applications across various domains, including industries, CPS (Cyber-Physical Systems), aerospace anomaly detection, network intrusion detection, and personal privacy data protection. This Research Topic focuses on time series anomaly detection within the context of big data technology. The interactions between the time series anomaly detection field and deep learning theory allow for making the time series anomaly detection field more efficient and intelligent.

Our objective is to foster collaboration and knowledge sharing among researchers and practitioners in the field of time series anomaly detection, big data mining, Artificial Intelligence and deep learning, network security and privacy protection. We aim to provide a platform for in-depth discussion of the latest trends and achievements in the realm of time series anomaly detection.

This Research Topic aims to highlight the latest research development of Artificial Intelligence, deep learning, feature engineering, big data, network cyber security, privacy and trust, and other cutting-edge technologies in time series anomaly detection within the context of big data technology. In particular, it aims to promote the application of these emerging technologies in the field of time series anomaly detection, so as to promote the overall development of this Research Topic.

1. The latest theories, technologies, development trends and future challenges of time series anomaly detection.
2. Cybersecurity and time series anomaly detection.
3. The application and practice of time series anomaly detection under CPS security and Industry 4.0.
4. The research on big data-related technology under time series anomaly detection (data acquisition, feature extraction, processing and visualization technology, data security and privacy protection).
5. The novel technology of multivariable time series anomaly detection (unsupervised learning, graph attention network model, Blockchain transaction security and privacy protection, etc.).
6. The frontier learning model of time series anomaly detection (such as the forecasting-based model, reconstruction-based model, fusion model, dynamic learning model, transformer-based model, etc.).
7. The threshold selection approaches for time series anomaly detection.
8. The understanding and interpretation of time series anomaly detection (the interpretation of the exception pattern, attack behaviour interpretation, the interpretation of the cause of the anomaly and the interpretation of the anomaly detection results).
9. Time series anomaly detection service and its security, privacy and trustworthiness.
10. The emergency processing strategies and management for time series anomaly detection, particularly in cybersecurity.
11. Social network user behaviour security and privacy protection related to time series anomaly detection.

Keywords: Anomaly Detection, Cyber-Physical Systems, Time series analysis, Cyber Security, Big Data Technology, Interpretation, Machine Learning Models

Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.