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

This paper explores a semi-supervised object detection approach to detect hotspots on the internal wall of Tokamaks. A huge amount of data is producedduring an experimental campaign by the infrared (IR) viewing systems used tomonitor the inner thermal shields during machine operation. The amount of datato be processed and analysed is such that protecting the first wall is anoverwhelming job. Automatizing this job with artificial intelligence (AI) is anattractive solution, but AI requires large labelled databases which are notreadily available for Tokamak walls. Semi-supervised learning (SSL) is apossible solution to being able to train deep learning models with a smallamount of labelled data and a large amount of unlabelled data. SSL is exploredas a possible tool to rapidly adapt a model trained on an experimental campaignA of Tokamak WEST to a new experimental campaign B by using labelled data fromcampaign A, a little labelled data from campaign B and a lot of unlabelled datafrom campaign B. Model performances are evaluated on two labelled datasets andtwo methods including semi-supervised learning. Semi-supervised learningincreased the mAP metric by over six percentage points on the first smallerscale database and over four percentage points on the second larger scaledataset depending on the employed method.

Detection of Thermal Events by Semi-Supervised Learning for Tokamak First Wall Safety