Edge computing empowered anomaly detection framework with dynamic insertion and deletion schemes on data streams

Abstract Anomaly detection plays a crucial role in many Internet of Things (IoT) applications such as traffic anomaly for smart transportation and medical diagnosis healthcare. With the explosion IoT data, on data streams raises higher requirements real-time response strong robustness large-scale arriving at same time various application fields. However, existing methods are either slow or application-specific. Inspired by edge computing generic technique, we propose an isolation forest based framework with dynamic Insertion Deletion schemes (IDForest), which can incrementally update to detect anomalies streams. Besides, IDForest is deployed servers parallel through packing each tree into subtask, facilitates fast Extensive experiments both synthetic real-life datasets demonstrate efficiency our detection.