Matches in SemOpenAlex for { <https://semopenalex.org/work/W4300560324> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4300560324 abstract "There is often a scarcity of training data for machine learning (ML) classification and regression models in industrial production, especially for time-consuming or sparsely run manufacturing processes. A majority of the limited ground-truth data is used for training, while a handful of samples are left for testing. Here, the number of test samples is inadequate to properly evaluate the robustness of the ML models under test for classification and regression. Furthermore, the output of these ML models may be inaccurate or even fail if the input data differ from the expected. This is the case for ML models used in the Electroslag Remelting (ESR) process in the refined steel industry to predict the pressure in a vacuum chamber. A vacuum pumping event that occurs once a workday generates a few hundred samples in a year of pumping for training and testing. In the absence of adequate training and test samples, this paper first presents a method to generate a fresh set of augmented samples based on vacuum pumping principles. Based on the generated augmented samples, three test scenarios and one test oracle are presented to assess the robustness of an ML model used for production on an industrial scale. Experiments are conducted with real industrial production data obtained from Uddeholms AB steel company. The evaluations indicate that Ensemble and Neural Network are the most robust when trained on augmented data using the proposed testing strategy. The evaluation also demonstrates the proposed method's effectiveness in checking and improving ML algorithms' robustness in such situations. The work improves software testing's state-of-the-art robustness testing in similar settings. Finally, the paper presents an MLOps implementation of the proposed approach for real-time ML model prediction and action on the edge node and automated continuous delivery of ML software from the cloud." @default.
- W4300560324 created "2022-10-03" @default.
- W4300560324 creator A5028031474 @default.
- W4300560324 creator A5031391282 @default.
- W4300560324 creator A5063683767 @default.
- W4300560324 creator A5064808748 @default.
- W4300560324 date "2022-08-08" @default.
- W4300560324 modified "2023-09-26" @default.
- W4300560324 title "Testing of Machine Learning Models with Limited Samples: An Industrial Vacuum Pumping Application" @default.
- W4300560324 doi "https://doi.org/10.48550/arxiv.2208.04062" @default.
- W4300560324 hasPublicationYear "2022" @default.
- W4300560324 type Work @default.
- W4300560324 citedByCount "0" @default.
- W4300560324 crossrefType "posted-content" @default.
- W4300560324 hasAuthorship W4300560324A5028031474 @default.
- W4300560324 hasAuthorship W4300560324A5031391282 @default.
- W4300560324 hasAuthorship W4300560324A5063683767 @default.
- W4300560324 hasAuthorship W4300560324A5064808748 @default.
- W4300560324 hasBestOaLocation W43005603241 @default.
- W4300560324 hasConcept C104317684 @default.
- W4300560324 hasConcept C105795698 @default.
- W4300560324 hasConcept C115903868 @default.
- W4300560324 hasConcept C119857082 @default.
- W4300560324 hasConcept C146849305 @default.
- W4300560324 hasConcept C154945302 @default.
- W4300560324 hasConcept C162324750 @default.
- W4300560324 hasConcept C165556158 @default.
- W4300560324 hasConcept C16910744 @default.
- W4300560324 hasConcept C169903167 @default.
- W4300560324 hasConcept C185592680 @default.
- W4300560324 hasConcept C199360897 @default.
- W4300560324 hasConcept C33923547 @default.
- W4300560324 hasConcept C41008148 @default.
- W4300560324 hasConcept C45942800 @default.
- W4300560324 hasConcept C48921125 @default.
- W4300560324 hasConcept C50644808 @default.
- W4300560324 hasConcept C51632099 @default.
- W4300560324 hasConcept C55166926 @default.
- W4300560324 hasConcept C55493867 @default.
- W4300560324 hasConcept C63479239 @default.
- W4300560324 hasConcept C82753439 @default.
- W4300560324 hasConcept C83546350 @default.
- W4300560324 hasConceptScore W4300560324C104317684 @default.
- W4300560324 hasConceptScore W4300560324C105795698 @default.
- W4300560324 hasConceptScore W4300560324C115903868 @default.
- W4300560324 hasConceptScore W4300560324C119857082 @default.
- W4300560324 hasConceptScore W4300560324C146849305 @default.
- W4300560324 hasConceptScore W4300560324C154945302 @default.
- W4300560324 hasConceptScore W4300560324C162324750 @default.
- W4300560324 hasConceptScore W4300560324C165556158 @default.
- W4300560324 hasConceptScore W4300560324C16910744 @default.
- W4300560324 hasConceptScore W4300560324C169903167 @default.
- W4300560324 hasConceptScore W4300560324C185592680 @default.
- W4300560324 hasConceptScore W4300560324C199360897 @default.
- W4300560324 hasConceptScore W4300560324C33923547 @default.
- W4300560324 hasConceptScore W4300560324C41008148 @default.
- W4300560324 hasConceptScore W4300560324C45942800 @default.
- W4300560324 hasConceptScore W4300560324C48921125 @default.
- W4300560324 hasConceptScore W4300560324C50644808 @default.
- W4300560324 hasConceptScore W4300560324C51632099 @default.
- W4300560324 hasConceptScore W4300560324C55166926 @default.
- W4300560324 hasConceptScore W4300560324C55493867 @default.
- W4300560324 hasConceptScore W4300560324C63479239 @default.
- W4300560324 hasConceptScore W4300560324C82753439 @default.
- W4300560324 hasConceptScore W4300560324C83546350 @default.
- W4300560324 hasLocation W43005603241 @default.
- W4300560324 hasOpenAccess W4300560324 @default.
- W4300560324 hasPrimaryLocation W43005603241 @default.
- W4300560324 hasRelatedWork W163918491 @default.
- W4300560324 hasRelatedWork W2012689841 @default.
- W4300560324 hasRelatedWork W2037021038 @default.
- W4300560324 hasRelatedWork W2161628345 @default.
- W4300560324 hasRelatedWork W2396366225 @default.
- W4300560324 hasRelatedWork W2792951589 @default.
- W4300560324 hasRelatedWork W2910903466 @default.
- W4300560324 hasRelatedWork W2977185326 @default.
- W4300560324 hasRelatedWork W3035729345 @default.
- W4300560324 hasRelatedWork W4280641190 @default.
- W4300560324 isParatext "false" @default.
- W4300560324 isRetracted "false" @default.
- W4300560324 workType "article" @default.