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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Abnormality detection is essential to the performance of safety-critical andlatency-constrained systems. However, as systems are becoming increasinglycomplicated with a large quantity of heterogeneous data, conventionalstatistical change point detection methods are becoming less effective andefficient. Although Deep Learning (DL) and Deep Neural Networks (DNNs) areincreasingly employed to handle heterogeneous data, they still lack theoreticassurable performance and explainability. This paper integrates zero-bias DNNand Quickest Event Detection algorithms to provide a holistic framework forquick and reliable detection of both abnormalities and time-dependent abnormalevents in the Internet of Things (IoT). We first use the zero-bias dense layerto increase the explainability of DNN. We provide a solution to convertzero-bias DNN classifiers into performance assured binary abnormalitydetectors. Using the converted abnormality detector, we then present asequential quickest detection scheme that provides the theoretically assuredlowest abnormal event detection delay under false alarm constraints. Finally,we demonstrate the effectiveness of the framework using both massive signalrecords from real-world aviation communication systems and simulated data. Codeand data of our work is available at\url{https://github.com/pcwhy/AbnormalityDetectionInZbDNN}

Zero-bias Deep Learning Enabled Quick and Reliable Abnormality Detection in IoT