Identification and Classification of Snack-Type Watermelon (Citrullus lanatus) Genotypes Using Seed Morphology and Machine Learning Techniques
Bibliographic record
Abstract
). Nine genotypes with red, white, and black seed coats were assessed in total. For each genotype, 200 seeds were analyzed using high-resolution imaging and digital measurement techniques for the extraction of morphological characteristics (length, width, thickness, area, perimeter, equivalent diameter, etc., and physical (weight) and colorimetric attributes of the (L, a, b). The resulting dataset was modeled using Artificial Neural Network (ANN), Random Forest (RF) and Extra Tree (ET) algorithms and performance was validated by a 10-fold cross-validation. The primary objective of the study was to match (identify) each seed accurately with its respective genotype by using the morphological, physical, and colorimetric characteristics of the seed and thus to perform genotypic classification. The comparative results showed that the RF model had the highest genotypic performance (accuracy 92.22%, F1-score 91.87%, Cohen's Kappa 0.9118), followed by the ET (accuracy, 90.00%) and ANN models with a relatively lower precision (86.11%). Statistical analysis using the Wilcoxon signed-rank test confirmed that both RF and ET significantly outperformed ANN, with RF providing superior balance and stability over ET. The findings highlight that machine learning-based frameworks enable rapid, reliable, and non-destructive classification (identification) of snack-type watermelon seeds according to their genotypes. Such approaches hold strong potential for enhancing varietal traceability in breeding programs, improving quality control in commercial seed production, and meeting the high-throughput demands of seed processing industries.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 teacher head, 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".