Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048118432> ?p ?o ?g. }
- W3048118432 abstract "The collected data from industrial machines are often imbalanced, which poses a negative effect on learning algorithms. However, this problem becomes more challenging for a mixed type of data or while there is overlapping between classes. Class-imbalance problem requires a robust learning system which can timely predict and classify the data. We propose a new adversarial network for simultaneous classification and fault detection. In particular, we restore the balance in the imbalanced dataset by generating faulty samples from the proposed mixture of data distribution. We designed the discriminator of our model to handle the generated faulty samples to prevent outlier and overfitting. We empirically demonstrate that; (i) the discriminator trained with a generator to generates samples from a mixture of normal and faulty data distribution which can be considered as a fault detector; (ii), the quality of the generated faulty samples outperforms the other synthetic resampling techniques. Experimental results show that the proposed model performs well when comparing to other fault diagnosis methods across several evaluation metrics; in particular, coalescing of generative adversarial network (GAN) and feature matching function is effective at recognizing faulty samples." @default.
- W3048118432 created "2020-08-13" @default.
- W3048118432 creator A5009550171 @default.
- W3048118432 creator A5068383847 @default.
- W3048118432 creator A5079232252 @default.
- W3048118432 date "2020-08-07" @default.
- W3048118432 modified "2023-09-26" @default.
- W3048118432 title "Oversampling Adversarial Network for Class-Imbalanced Fault Diagnosis" @default.
- W3048118432 cites W1991723619 @default.
- W3048118432 cites W2015605478 @default.
- W3048118432 cites W2099471712 @default.
- W3048118432 cites W2132791018 @default.
- W3048118432 cites W2148143831 @default.
- W3048118432 cites W2149298154 @default.
- W3048118432 cites W2173520492 @default.
- W3048118432 cites W2317595875 @default.
- W3048118432 cites W2404692435 @default.
- W3048118432 cites W2464878551 @default.
- W3048118432 cites W2480364715 @default.
- W3048118432 cites W2502312327 @default.
- W3048118432 cites W2548275288 @default.
- W3048118432 cites W2562741369 @default.
- W3048118432 cites W2584994008 @default.
- W3048118432 cites W2734669076 @default.
- W3048118432 cites W2738563279 @default.
- W3048118432 cites W2753797983 @default.
- W3048118432 cites W2760637973 @default.
- W3048118432 cites W2782742812 @default.
- W3048118432 cites W2785731816 @default.
- W3048118432 cites W2789811186 @default.
- W3048118432 cites W2791694051 @default.
- W3048118432 cites W2793167745 @default.
- W3048118432 cites W2794869810 @default.
- W3048118432 cites W2798673311 @default.
- W3048118432 cites W2886794804 @default.
- W3048118432 cites W2897680073 @default.
- W3048118432 cites W2900564203 @default.
- W3048118432 cites W2912412749 @default.
- W3048118432 cites W2933697479 @default.
- W3048118432 cites W2945178666 @default.
- W3048118432 cites W2963170156 @default.
- W3048118432 cites W2963373786 @default.
- W3048118432 cites W2964294029 @default.
- W3048118432 cites W2964971217 @default.
- W3048118432 cites W2965989168 @default.
- W3048118432 cites W2968409655 @default.
- W3048118432 cites W2999309480 @default.
- W3048118432 cites W3008309516 @default.
- W3048118432 cites W3025171967 @default.
- W3048118432 cites W3033043953 @default.
- W3048118432 cites W3046193758 @default.
- W3048118432 doi "https://doi.org/10.48550/arxiv.2008.03071" @default.
- W3048118432 hasPublicationYear "2020" @default.
- W3048118432 type Work @default.
- W3048118432 sameAs 3048118432 @default.
- W3048118432 citedByCount "0" @default.
- W3048118432 crossrefType "posted-content" @default.
- W3048118432 hasAuthorship W3048118432A5009550171 @default.
- W3048118432 hasAuthorship W3048118432A5068383847 @default.
- W3048118432 hasAuthorship W3048118432A5079232252 @default.
- W3048118432 hasBestOaLocation W30481184321 @default.
- W3048118432 hasConcept C119857082 @default.
- W3048118432 hasConcept C121332964 @default.
- W3048118432 hasConcept C124101348 @default.
- W3048118432 hasConcept C127313418 @default.
- W3048118432 hasConcept C150921843 @default.
- W3048118432 hasConcept C153180895 @default.
- W3048118432 hasConcept C154945302 @default.
- W3048118432 hasConcept C163258240 @default.
- W3048118432 hasConcept C165205528 @default.
- W3048118432 hasConcept C175551986 @default.
- W3048118432 hasConcept C197323446 @default.
- W3048118432 hasConcept C21308566 @default.
- W3048118432 hasConcept C22019652 @default.
- W3048118432 hasConcept C24890656 @default.
- W3048118432 hasConcept C2776257435 @default.
- W3048118432 hasConcept C2777212361 @default.
- W3048118432 hasConcept C2779803651 @default.
- W3048118432 hasConcept C2780992000 @default.
- W3048118432 hasConcept C31258907 @default.
- W3048118432 hasConcept C41008148 @default.
- W3048118432 hasConcept C50644808 @default.
- W3048118432 hasConcept C62520636 @default.
- W3048118432 hasConcept C76155785 @default.
- W3048118432 hasConcept C79337645 @default.
- W3048118432 hasConcept C94915269 @default.
- W3048118432 hasConceptScore W3048118432C119857082 @default.
- W3048118432 hasConceptScore W3048118432C121332964 @default.
- W3048118432 hasConceptScore W3048118432C124101348 @default.
- W3048118432 hasConceptScore W3048118432C127313418 @default.
- W3048118432 hasConceptScore W3048118432C150921843 @default.
- W3048118432 hasConceptScore W3048118432C153180895 @default.
- W3048118432 hasConceptScore W3048118432C154945302 @default.
- W3048118432 hasConceptScore W3048118432C163258240 @default.
- W3048118432 hasConceptScore W3048118432C165205528 @default.
- W3048118432 hasConceptScore W3048118432C175551986 @default.
- W3048118432 hasConceptScore W3048118432C197323446 @default.
- W3048118432 hasConceptScore W3048118432C21308566 @default.
- W3048118432 hasConceptScore W3048118432C22019652 @default.
- W3048118432 hasConceptScore W3048118432C24890656 @default.