Impact Score 0.49
In data analysis, anomaly detection is generally defined as the identification of rare items, events or observations that differ significantly from the majority of the data. In complex intelligent systems such as the Internet of Things (IoT), we often have to deduce whether a new data sample comes from an unknown class or from one of the known classes that have been already learned from the previous data. Samples from the unknown class are defined as anomalies or novelties. Anomalies or novelties widely exist in real-life applications of intelligent systems, such as illegal intrusion in Internet services, irregular access in edge computing, and abnormal events in IoT to name just a few. Detecting anomalies or novelties is a challenging task in the field of machine learning and the IoT applications. With recent advances in the field of artificial intelligence (AI), it is becoming increasingly possible to detect anomalies or novelties automatically in complex intelligent systems. On the other hand, the massive data generated from numerous IoT devices and applications might be inevitably corrupted due to various reasons, where the corrupted data can be seen as anomalies among the normal data. Anomalies may have detrimental effects on system performance. Therefore, anomaly detection is one of the critical technical challenges in the IoT applications.This special issue is expected to spur further research and development efforts in AI-driven anomaly detection and to provide a unique opportunity to allow researchers from different domains of computing research to contribute to the AI-driven anomaly detection to support pervasive edge computing for the IoT applications. A thorough review process will be employed to ensure the quality of the special issue.
We invite researchers to contribute original and high-quality research articles that are focused on the state-of-the-art technologies for anomaly detection in the edge computing and IoT applications. The original papers are solicited on topics of interest that include, but are not limited to, the following:
Submission of manuscript deadline: June 30, 2021 First notification: July 31, 2021Submission of revised manuscript: August 31, 2021 Final notification: September 30, 2021Guest Editors:Fa Zhu, Nanjing Forestry University, China ([email protected])Rajan Shankaran, Macquarie University, Australia ([email protected])Lei Xu, City University of Hong Kong, ([email protected])Xinrong Li, University of North Texas ([email protected])