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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Physical event detection has long been the domain of static event processorsoperating on numeric sensor data. This works well for large scale strong-signalevents such as hurricanes, and important classes of events such as earthquakes.However, for a variety of domains there is insufficient sensor coverage, e.g.,landslides, wildfires, and flooding. Social networks have provided massivevolume of data from billions of users, but data from these generic socialsensors contain much more noise than physical sensors. One of the mostdifficult challenges presented by social sensors is \textit{concept drift},where the terms associated with a phenomenon evolve and change over time,rendering static machine learning (ML) classifiers less effective. To addressthis problem, we develop the ASSED (Adaptive Social Sensor Event Detection)framework with an ML-based event processing engine and show how it can performsimple and complex physical event detection on strong- \textit{and} weak-signalwith low-latency, high scalability, and accurate coverage. Specifically, ASSEDis a framework to support continuous filter generation and updates with machinelearning using streaming data from high-confidence sources (physical andannotated sensors) and social networks. We build ASSED to support proceduresfor integrating high-confidence sources into social sensor event detection togenerate high-quality filters and to perform dynamic filter selection bytracking its own performance. We demonstrate ASSED capabilities through alandslide detection application that detects almost 350\% more landslidescompared to static approaches. More importantly, ASSED automates the handlingof concept drift: four years after initial data collection and classifiertraining, ASSED achieves event detection accuracy of 0.988 (without expertmanual intervention), compared to 0.762 for static approaches.

ASSED -- A Framework for Identifying Physical Events through Adaptive Social Sensor Data Filtering