A Hybrid Resampling Method with K-Nearest Neighbour (FHR-KNN) for Imbalanced Preeclampsia Dataset
Bibliographic record
Abstract
The medical preeclampsia dataset emphasizes the possession of very large data by a majority class, compared to a minority class.This condition often leads to imbalanced classes in the training datasets, which then affects model prediction negatively.However, a standard classifier is likely to perform adequately on a balanced sample.Asides from the imbalance class issue, another problem in the medical dataset is irrelevant features, which cause poor model accuracy.In this case, several techniques such as SMOTE, as well as random oversampling and undersampling (ROS and RUS) have been used as problemsolving approaches, although they also contained some negative impacts, such as overfitting, loss of information, and overlapping.Therefore, this study aims to propose a model, which combines Features selection, a Hybrid Resampling technique, and a K-Nearest Neighbor algorithm (FHR-KNN), to overcome this problem.This model was implemented to the imbalanced datasets, with the average values of the accuracy, precision, and recall of the FHR-KNN obtained at 99%, 95%, and 95%, which is 0.03% higher than another classifier, respectively.Based on the results, the strategy implemented consistently outperformed other methods and classifiers regarding performance levels.The accuracy of individual classifiers showed the elevation of almost all classifier appropriateness.Additionally, an increase was observed within the average accuracy indices FHR-KNN algorithm compared to the traditional oversampling technique.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".