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

The Internet of Things (IoT) integrates more than billions of intelligentdevices over the globe with the capability of communicating with otherconnected devices with little to no human intervention. IoT enables dataaggregation and analysis on a large scale to improve life quality in manydomains. In particular, data collected by IoT contain a tremendous amount ofinformation for anomaly detection. The heterogeneous nature of IoT is both achallenge and an opportunity for cybersecurity. Traditional approaches incybersecurity monitoring often require different kinds of data pre-processingand handling for various data types, which might be problematic for datasetsthat contain heterogeneous features. However, heterogeneous types of networkdevices can often capture a more diverse set of signals than a single type ofdevice readings, which is particularly useful for anomaly detection. In thispaper, we present a comprehensive study on using ensemble machine learningmethods for enhancing IoT cybersecurity via anomaly detection. Rather thanusing one single machine learning model, ensemble learning combines thepredictive power from multiple models, enhancing their predictive accuracy inheterogeneous datasets rather than using one single machine learning model. Wepropose a unified framework with ensemble learning that utilises Bayesianhyperparameter optimisation to adapt to a network environment that containsmultiple IoT sensor readings. Experimentally, we illustrate their highpredictive power when compared to traditional methods.

Ensemble Learning based Anomaly Detection for IoT Cybersecurity via Bayesian Hyperparameters Sensitivity Analysis