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

Risk assessment is relevant in any workplace, however there is a degree ofunpredictability when dealing with flammable or hazardous materials so thatdetection of fire accidents by itself may not be enough. An example of this isthe impingement of jet fires, where the heat fluxes of the flame could reachnearby equipment and dramatically increase the probability of a domino effectwith catastrophic results. Because of this, the characterization of such fireaccidents is important from a risk management point of view. One suchcharacterization would be the segmentation of different radiation zones withinthe flame, so this paper presents an exploratory research regarding severaltraditional computer vision and Deep Learning segmentation approaches to solvethis specific problem. A data set of propane jet fires is used to train andevaluate the different approaches and given the difference in the distributionof the zones and background of the images, different loss functions, that seekto alleviate data imbalance, are also explored. Additionally, different metricsare correlated to a manual ranking performed by experts to make an evaluationthat closely resembles the expert's criteria. The Hausdorff Distance andAdjusted Random Index were the metrics with the highest correlation and thebest results were obtained from the UNet architecture with a WeightedCross-Entropy Loss. These results can be used in future research to extractmore geometric information from the segmentation masks or could even beimplemented on other types of fire accidents.

Comparing Machine Learning based Segmentation Models on Jet Fire Radiation Zones