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/

Zendy Plus

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

Zendy Tools

Zendy Open

Outlier detection has received special attention in various fields, mainlyfor those dealing with machine learning and artificial intelligence. As strongoutliers, anomalies are divided into the point, contextual and collectiveoutliers. The most important challenges in outlier detection include the thinboundary between the remote points and natural area, the tendency of new dataand noise to mimic the real data, unlabelled datasets and different definitionsfor outliers in different applications. Considering the stated challenges, wedefined new types of anomalies called Collective Normal Anomaly and CollectivePoint Anomaly in order to improve a much better detection of the thin boundarybetween different types of anomalies. Basic domain-independent methods areintroduced to detect these defined anomalies in both unsupervised andsupervised datasets. The Multi-Layer Perceptron Neural Network is enhancedusing the Genetic Algorithm to detect newly defined anomalies with higherprecision so as to ensure a test error less than that calculated for theconventional Multi-Layer Perceptron Neural Network. Experimental results onbenchmark datasets indicated reduced error of anomaly detection process incomparison to baselines.

Detection of Thin Boundaries between Different Types of Anomalies in Outlier Detection using Enhanced Neural Networks