Fuzzy-CL: Fuzzy Rank-Based Ensembling Aided Contrastive Learning for Malaria Detection Using Red Blood Cell Smears
Bibliographic record
Abstract
Many academics have worked to identify malaria-parasitized cells in blood sample images using Deep Learning algorithms throughout the years. Even though malaria is quite harmful, it can be controlled if caught early enough. This provides motivation to put in place a precise malaria detection method that can take the place of the current labor-intensive manual procedure. The manual procedure entails counting the red blood cells that are parasitized and those that are not, as well as visually inspecting the blood samples. This is a labor-intensive procedure that can be botched by an untrained medical staff member and takes a long time. Keeping these factors in mind, our goal was to create a solution that would require less training for medical personnel to utilize, saving them time and labor. After reading through a number of research studies on the application of deep learning methods to malaria detection, we have developed a model that fills in the gaps in existing systems without sacrificing the precision of the findings. With a 97.61% accuracy rate, our suggested model—which combines fuzzy ranking based ensembling with triplet loss aided contrastive learning (CL)—performs better than several state-of-the-art models.
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".