Open access
Aug 2026
IoT Time-series Anomaly Detection Using a Hybrid Transformer-GRU Fusion Model
This work proposes Residual GRU-Attention Anomaly Detector (RGAAD), an unsupervised framework for IoT time-series anomaly detection that achieves highly competitive performance and consistently outperforms strong baseline methods.
Yi-Tao Liang, Yuan-Gang Li, Ying-Ying Xu
· Periodica Polytechnica Elect... · 0 citations