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

The interaction of a gas particle with a metal-oxide based gas sensor changesthe sensor irreversibly. The compounded changes, referred to as sensor drift,are unstable, but adaptive algorithms can sustain the accuracy of odor sensorsystems. This paper shows how such a system can be defined without additionaldata acquisition by transfering knowledge from one time window to a subsequentone after drift has occurred. A context-based neural network model is used toform a latent representation of sensor state, thus making it possible togeneralize across a sequence of states. When tested on samples from unseensubsequent time windows, the approach performed better than drift-naive andensemble methods on a gas sensor array drift dataset. By reducing the effectthat sensor drift has on classification accuracy, context-based models may beused to extend the effective lifetime of gas identification systems inpractical settings.

Using context to make gas classifiers robust to sensor drift