English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Nowadays, multi-sensor technologies are applied in many fields, e.g., HealthCare (HC), Human Activity Recognition (HAR), and Industrial Control System(ICS). These sensors can generate a substantial amount of multivariatetime-series data. Unsupervised anomaly detection on multi-sensor time-seriesdata has been proven critical in machine learning researches. The key challengeis to discover generalized normal patterns by capturing spatial-temporalcorrelation in multi-sensor data. Beyond this challenge, the noisy data isoften intertwined with the training data, which is likely to mislead the modelby making it hard to distinguish between the normal, abnormal, and noisy data.Few of previous researches can jointly address these two challenges. In thispaper, we propose a novel deep learning-based anomaly detection algorithmcalled Deep Convolutional Autoencoding Memory network (CAE-M). We first build aDeep Convolutional Autoencoder to characterize spatial dependence ofmulti-sensor data with a Maximum Mean Discrepancy (MMD) to better distinguishbetween the noisy, normal, and abnormal data. Then, we construct a MemoryNetwork consisting of linear (Autoregressive Model) and non-linear predictions(Bidirectional LSTM with Attention) to capture temporal dependence fromtime-series data. Finally, CAE-M jointly optimizes these two subnetworks. Weempirically compare the proposed approach with several state-of-the-art anomalydetection methods on HAR and HC datasets. Experimental results demonstrate thatour proposed model outperforms these existing methods.

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