Models’ performance when using oversampling to balance the training dataset.
<p>Models’ performance when using oversampling to balance the training dataset.</p>
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | , , |
| منشور في: |
2025
|
| الموضوعات: | |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1852021595925643264 |
|---|---|
| author | Anna Beatriz Silva (20989245) |
| author2 | Elisson da Silva Rocha (17222272) João Fausto Lorenzato (20989248) Patricia Takako Endo (10373252) |
| author2_role | author author author |
| author_facet | Anna Beatriz Silva (20989245) Elisson da Silva Rocha (17222272) João Fausto Lorenzato (20989248) Patricia Takako Endo (10373252) |
| author_role | author |
| dc.creator.none.fl_str_mv | Anna Beatriz Silva (20989245) Elisson da Silva Rocha (17222272) João Fausto Lorenzato (20989248) Patricia Takako Endo (10373252) |
| dc.date.none.fl_str_mv | 2025-04-02T20:04:55Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0316574.g005 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/figure/Models_performance_when_using_oversampling_to_balance_the_training_dataset_/28719438 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Science Policy Biological Sciences not elsewhere classified Information Systems not elsewhere classified three hybridsampling configurations risk pregnancies earlier including decision tree hybridsampling approach resulted decision tree model machine learning models proper data balancing premature birth predictions predictive models biased predictions obstetric data data imbalance timely interventions sus ). results show random forest preterm births preterm birth performance compared particularly significant neonatal deaths neonatal care minority class main cause factors 2 common problem 70 %, 64 %, 37 weeks 000 cases |
| dc.title.none.fl_str_mv | Models’ performance when using oversampling to balance the training dataset. |
| dc.type.none.fl_str_mv | Image Figure info:eu-repo/semantics/publishedVersion image |
| description | <p>Models’ performance when using oversampling to balance the training dataset.</p> |
| eu_rights_str_mv | openAccess |
| id | Manara_962aa45f86dfaffd10ea1894de8131bb |
| identifier_str_mv | 10.1371/journal.pone.0316574.g005 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/28719438 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Models’ performance when using oversampling to balance the training dataset.Anna Beatriz Silva (20989245)Elisson da Silva Rocha (17222272)João Fausto Lorenzato (20989248)Patricia Takako Endo (10373252)Science PolicyBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedthree hybridsampling configurationsrisk pregnancies earlierincluding decision treehybridsampling approach resulteddecision tree modelmachine learning modelsproper data balancingpremature birth predictionspredictive modelsbiased predictionsobstetric datadata imbalancetimely interventionssus ).results showrandom forestpreterm birthspreterm birthperformance comparedparticularly significantneonatal deathsneonatal careminority classmain causefactors 2common problem70 %,64 %,37 weeks000 cases<p>Models’ performance when using oversampling to balance the training dataset.</p>2025-04-02T20:04:55ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0316574.g005https://figshare.com/articles/figure/Models_performance_when_using_oversampling_to_balance_the_training_dataset_/28719438CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/287194382025-04-02T20:04:55Z |
| spellingShingle | Models’ performance when using oversampling to balance the training dataset. Anna Beatriz Silva (20989245) Science Policy Biological Sciences not elsewhere classified Information Systems not elsewhere classified three hybridsampling configurations risk pregnancies earlier including decision tree hybridsampling approach resulted decision tree model machine learning models proper data balancing premature birth predictions predictive models biased predictions obstetric data data imbalance timely interventions sus ). results show random forest preterm births preterm birth performance compared particularly significant neonatal deaths neonatal care minority class main cause factors 2 common problem 70 %, 64 %, 37 weeks 000 cases |
| status_str | publishedVersion |
| title | Models’ performance when using oversampling to balance the training dataset. |
| title_full | Models’ performance when using oversampling to balance the training dataset. |
| title_fullStr | Models’ performance when using oversampling to balance the training dataset. |
| title_full_unstemmed | Models’ performance when using oversampling to balance the training dataset. |
| title_short | Models’ performance when using oversampling to balance the training dataset. |
| title_sort | Models’ performance when using oversampling to balance the training dataset. |
| topic | Science Policy Biological Sciences not elsewhere classified Information Systems not elsewhere classified three hybridsampling configurations risk pregnancies earlier including decision tree hybridsampling approach resulted decision tree model machine learning models proper data balancing premature birth predictions predictive models biased predictions obstetric data data imbalance timely interventions sus ). results show random forest preterm births preterm birth performance compared particularly significant neonatal deaths neonatal care minority class main cause factors 2 common problem 70 %, 64 %, 37 weeks 000 cases |