Squeezed Convolutional Variational AutoEncoder for Unsupervised Anomaly Detection in Edge Device Industrial Internet of Things
This work addresses anomaly detection for Edge Device Industrial IoT, but it is incremental as it builds on existing methods like SqueezeNet and VAE.
The paper tackles anomaly detection in time series data for Edge Computing in Industrial IoT by proposing a Squeezed Convolutional Variational AutoEncoder (SCVAE), which reduces model size and inference times while maintaining similar performance levels, as shown through comparisons on UCI datasets and real-world data.
In this paper, we propose Squeezed Convolutional Variational AutoEncoder (SCVAE) for anomaly detection in time series data for Edge Computing in Industrial Internet of Things (IIoT). The proposed model is applied to labeled time series data from UCI datasets for exact performance evaluation, and applied to real world data for indirect model performance comparison. In addition, by comparing the models before and after applying Fire Modules from SqueezeNet, we show that model size and inference times are reduced while similar levels of performance is maintained.