Unsupervised Deep Learning for IoT Time Series
This is an incremental survey paper that organizes existing knowledge for researchers in IoT and time series analysis.
This paper addresses the lack of systematic discussion on unsupervised deep learning methods for IoT time series analysis by investigating unsupervised anomaly detection and clustering under a unified framework, while also covering application scenarios, datasets, challenges, and future directions.
IoT time series analysis has found numerous applications in a wide variety of areas, ranging from health informatics to network security. Nevertheless, the complex spatial temporal dynamics and high dimensionality of IoT time series make the analysis increasingly challenging. In recent years, the powerful feature extraction and representation learning capabilities of deep learning (DL) have provided an effective means for IoT time series analysis. However, few existing surveys on time series have systematically discussed unsupervised DL-based methods. To fill this void, we investigate unsupervised deep learning for IoT time series, i.e., unsupervised anomaly detection and clustering, under a unified framework. We also discuss the application scenarios, public datasets, existing challenges, and future research directions in this area.