Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signals

Nowadays, multi-sensor technologies are applied in many fields, e.g., Health Care (HC) and Human Activity Recognition (HAR). These sensors can generate a substantial amount of multivariate time-series data. Unsupervised anomaly detection on multi-sensor time-series data has been proven critical in machine learning researches. The key challenge is to discover generalized normal patterns by capturing spatial-temporal correlation in time series. Beyond this challenge, noisy data is often intertwined with training data, which is likely to mislead the model by making it hard to distinguish between normal, abnormal, and noisy data. Few of previous researches can jointly address these two challenges. In this paper, we propose a novel deep learning-based anomaly detection algorithm called Deep Convolutional Autoencoding Memory network (CAE-M). We first build a Deep Convolutional Autoencoder to characterize spatial dependence of high-dimensional data with a Maximum Mean Discrepancy (MMD) to better distinguish between the noisy, normal, and abnormal data. Then, we construct a Memory Network consisting of linear (Autoregressive Model) and non-linear predictions (Bidirectional LSTM with Attention) to capture temporal dependence from time-series data. Finally, CAE-M jointly optimizes these two subnetworks. We compare the proposed approach with several state-of-the-art anomaly detection methods on HAR and HC datasets. Experimental results demonstrate that our proposed model outperforms these existing method