FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4280490610> ?p ?o ?g. }

• W4280490610 endingPage "127933" @default.
• W4280490610 startingPage "127933" @default.
• W4280490610 abstract "• Class-imbalanced data lead to huge gap in sensitivity and specificity of ANN models. • ADASYN increases the G-Mean of ANN models by an average of 41.6% • ADASYN-optimized models predict higher As exposure risk in Ghana than that in Ethiopia. • Predictors characterizing redox conditions are most important for the Ghana model. • Predictors characterizing clay and pH are most important for the Ethiopian model. Data-driven machine learning models have been used to predict hazardous substances levels in groundwater. However, class-imbalanced data results in models that may show grossly low sensitivity even though they show high overall accuracy. To address this issue, four algorithms - weighted cross-entropy loss, Random oversampling, Random undersampling, and Adaptive synthetic sampling (ADASYN) - were tested for their validity in improving model sensitivity. Testing of the above four algorithms using geogenic high arsenic groundwater data from the Datong Basin, the Red River Delta of Vietnam, Bangladesh, Texas and California showed that all four algorithms produced more accurate predictions with an average increase in sensitivity of 53.8% compared to the raw models. The ADASYN is the best of the four algorithms and can increase model G-means (geometric mean of sensitivity and specificity) by >40% on average. The ADASYN-optimized ANN models predicted higher groundwater As exposure risk in Ghana than that in Ethiopia." @default.
• W4280490610 created "2022-05-22" @default.
• W4280490610 creator A5062416632 @default.
• W4280490610 creator A5078324743 @default.
• W4280490610 creator A5081456949 @default.
• W4280490610 creator A5083417541 @default.
• W4280490610 date "2022-07-01" @default.
• W4280490610 modified "2023-10-01" @default.
• W4280490610 title "Evaluating the validity of class balancing algorithms-based machine learning models for geogenic contaminated groundwaters prediction" @default.
• W4280490610 cites W1488107395 @default.
• W4280490610 cites W1941659294 @default.
• W4280490610 cites W1963839303 @default.
• W4280490610 cites W1982546148 @default.
• W4280490610 cites W1988687886 @default.
• W4280490610 cites W1990596380 @default.
• W4280490610 cites W1994447719 @default.
• W4280490610 cites W2029570914 @default.
• W4280490610 cites W2070164699 @default.
• W4280490610 cites W2071994244 @default.
• W4280490610 cites W2077556080 @default.
• W4280490610 cites W2083505941 @default.
• W4280490610 cites W2085070141 @default.
• W4280490610 cites W2104933073 @default.
• W4280490610 cites W2122549607 @default.
• W4280490610 cites W2124337990 @default.
• W4280490610 cites W2138539078 @default.
• W4280490610 cites W2149602337 @default.
• W4280490610 cites W2189265340 @default.
• W4280490610 cites W2237884911 @default.
• W4280490610 cites W2315860835 @default.
• W4280490610 cites W2466788594 @default.
• W4280490610 cites W2473042227 @default.
• W4280490610 cites W2544836728 @default.
• W4280490610 cites W2749465180 @default.
• W4280490610 cites W2765613654 @default.
• W4280490610 cites W2794365240 @default.
• W4280490610 cites W2883377287 @default.
• W4280490610 cites W2902220643 @default.
• W4280490610 cites W2910187721 @default.
• W4280490610 cites W2947681949 @default.
• W4280490610 cites W2981679084 @default.
• W4280490610 cites W2993709659 @default.
• W4280490610 cites W3000057629 @default.
• W4280490610 cites W3028066085 @default.
• W4280490610 cites W3033743109 @default.
• W4280490610 cites W3070311419 @default.
• W4280490610 cites W3136410796 @default.
• W4280490610 cites W3137072041 @default.
• W4280490610 cites W3137218622 @default.
• W4280490610 cites W3137512151 @default.
• W4280490610 cites W3144233634 @default.
• W4280490610 cites W3192647379 @default.
• W4280490610 cites W3200011989 @default.
• W4280490610 cites W3209425565 @default.
• W4280490610 cites W3210466241 @default.
• W4280490610 cites W4210770998 @default.
• W4280490610 cites W4211088767 @default.
• W4280490610 doi "https://doi.org/10.1016/j.jhydrol.2022.127933" @default.
• W4280490610 hasPublicationYear "2022" @default.
• W4280490610 type Work @default.
• W4280490610 citedByCount "1" @default.
• W4280490610 countsByYear W42804906102023 @default.
• W4280490610 crossrefType "journal-article" @default.
• W4280490610 hasAuthorship W4280490610A5062416632 @default.
• W4280490610 hasAuthorship W4280490610A5078324743 @default.
• W4280490610 hasAuthorship W4280490610A5081456949 @default.
• W4280490610 hasAuthorship W4280490610A5083417541 @default.
• W4280490610 hasConcept C11413529 @default.
• W4280490610 hasConcept C119857082 @default.
• W4280490610 hasConcept C127313418 @default.
• W4280490610 hasConcept C127413603 @default.
• W4280490610 hasConcept C159390177 @default.
• W4280490610 hasConcept C169258074 @default.
• W4280490610 hasConcept C187320778 @default.
• W4280490610 hasConcept C21200559 @default.
• W4280490610 hasConcept C24326235 @default.
• W4280490610 hasConcept C33923547 @default.
• W4280490610 hasConcept C39432304 @default.
• W4280490610 hasConcept C41008148 @default.
• W4280490610 hasConcept C76177295 @default.
• W4280490610 hasConceptScore W4280490610C11413529 @default.
• W4280490610 hasConceptScore W4280490610C119857082 @default.
• W4280490610 hasConceptScore W4280490610C127313418 @default.
• W4280490610 hasConceptScore W4280490610C127413603 @default.
• W4280490610 hasConceptScore W4280490610C159390177 @default.
• W4280490610 hasConceptScore W4280490610C169258074 @default.
• W4280490610 hasConceptScore W4280490610C187320778 @default.
• W4280490610 hasConceptScore W4280490610C21200559 @default.
• W4280490610 hasConceptScore W4280490610C24326235 @default.
• W4280490610 hasConceptScore W4280490610C33923547 @default.
• W4280490610 hasConceptScore W4280490610C39432304 @default.
• W4280490610 hasConceptScore W4280490610C41008148 @default.
• W4280490610 hasConceptScore W4280490610C76177295 @default.
• W4280490610 hasLocation W42804906101 @default.
• W4280490610 hasOpenAccess W4280490610 @default.
• W4280490610 hasPrimaryLocation W42804906101 @default.
• W4280490610 hasRelatedWork W2908849530 @default.
• W4280490610 hasRelatedWork W3203515236 @default.

• next