AI-DRIVEN ANOMALY DETECTION IN IOT SENSOR DATA BY USING ADVANCED PRE-PROCESSING AND GRU-BASED MODELING
Keywords:
Anomaly Detection, IoT Sensor Data, Machine Learning (ML), Deep Learning (DL), Principal Component Analysis (PCA), Gated Recurrent Units (GRU), Particle Swarm Optimization (PSO), t-SNE, Outlier Detection, Time-Series Analysis.Abstract
Anomaly detection has grown increasingly challenging as the number of connected devices continues to skyrocket, necessitating state-of-the-art methods to ensure the security,reliability, and sustainability of IoT networks. This study describes an AI-driven method for
finding anomalies in data acquired by IoT devices. A deep learning model utilising Gated Recurrent Units (GRU) is a part of the technique, along with enhanced pre-processing algorithms.
References
Abbasi, F., Naderan, M., Alavi, S. E. (2021). Anomaly detection in Internet of Things using feature selection and classification based on Logistic Regression and Artificial Neural Network on N-BaIoT dataset. In Proceedings of the 2021 5th International Conference on Internet of Things and Applications (IoT) (pp. 1-7). Online.
Achiluzzi, E., Li, M., Georgy, M. F. A., &Kashef, R. (2023). Exploring the Use of Data Driven Approaches for Anomaly Detection in the Internet of Things (IoT) Environment. In arXiv (Cornell https://doi.org/10.48550/arxiv.2301.00134 University). Cornell University.
