Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200610514> ?p ?o ?g. }
Showing items 1 to 39 of
39
with 100 items per page.
- W4200610514 abstract "In machine learning, we often face the situation where the event we are interested in has very few data points buried in a massive amount of data. This is typical in network monitoring, where data are streamed from sensing or measuring units continuously but most data are not for events. With imbalanced datasets, the classifiers tend to be biased in favor of the main class. Rare event detection has received much attention in machine learning, and yet it is still a challenging problem. In this paper, we propose a remedy for the standing problem. Weighting and sampling are two fundamental approaches to address the problem. We focus on the weighting method in this paper. We first propose a boosting-style algorithm to compute class weights, which is proved to have excellent theoretical property. Then we propose an adaptive algorithm, which is suitable for real-time applications. The adaptive nature of the two algorithms allows a controlled tradeoff between true positive rate and false positive rate and avoids excessive weight on the rare class, which leads to poor performance on the main class. Experiments on power grid data and some public datasets show that the proposed algorithms outperform the existing weighting and boosting methods, and that their superiority is more noticeable with noisy data." @default.
- W4200610514 created "2021-12-31" @default.
- W4200610514 date "2021-12-23" @default.
- W4200610514 modified "2023-09-27" @default.
- W4200610514 title "fdata-04-715320-g003.tif" @default.
- W4200610514 doi "https://doi.org/10.3389/fdata.2021.715320.s007" @default.
- W4200610514 hasPublicationYear "2021" @default.
- W4200610514 type Work @default.
- W4200610514 citedByCount "0" @default.
- W4200610514 crossrefType "component" @default.
- W4200610514 hasBestOaLocation W42006105141 @default.
- W4200610514 hasConcept C11413529 @default.
- W4200610514 hasConcept C119857082 @default.
- W4200610514 hasConcept C124101348 @default.
- W4200610514 hasConcept C126838900 @default.
- W4200610514 hasConcept C154945302 @default.
- W4200610514 hasConcept C183115368 @default.
- W4200610514 hasConcept C2777212361 @default.
- W4200610514 hasConcept C41008148 @default.
- W4200610514 hasConcept C46686674 @default.
- W4200610514 hasConcept C70136482 @default.
- W4200610514 hasConcept C71924100 @default.
- W4200610514 hasConceptScore W4200610514C11413529 @default.
- W4200610514 hasConceptScore W4200610514C119857082 @default.
- W4200610514 hasConceptScore W4200610514C124101348 @default.
- W4200610514 hasConceptScore W4200610514C126838900 @default.
- W4200610514 hasConceptScore W4200610514C154945302 @default.
- W4200610514 hasConceptScore W4200610514C183115368 @default.
- W4200610514 hasConceptScore W4200610514C2777212361 @default.
- W4200610514 hasConceptScore W4200610514C41008148 @default.
- W4200610514 hasConceptScore W4200610514C46686674 @default.
- W4200610514 hasConceptScore W4200610514C70136482 @default.
- W4200610514 hasConceptScore W4200610514C71924100 @default.
- W4200610514 hasLocation W42006105141 @default.
- W4200610514 hasOpenAccess W4200610514 @default.
- W4200610514 hasPrimaryLocation W42006105141 @default.
- W4200610514 isParatext "false" @default.
- W4200610514 isRetracted "false" @default.
- W4200610514 workType "paratext" @default.