Research on Wheat Seed Classification Based on Machine Learning Algorithms and Data Analysis Visualization
Bibliographic record
Abstract
This study addresses the problem of wheat seed classification by employing three machine learning algorithms—Random Forest (RF), Naïve Bayes (NB), and Support Vector Machine (SVM)—on the Wheat Seeds Dataset from the UCI database. Through comprehensive data preprocessing, feature analysis, and model construction, the impact of different feature combinations on classification accuracy was systematically investigated. The dataset, comprising 210 samples with seven attributes (e.g., area, perimeter, and kernel groove length), was standardized and split into training and testing sets to ensure robust evaluation. The experimental results demonstrate that RF and SVM significantly outperform NB in classification performance, with SVM achieving the highest accuracy of 97.61% when combining area or width with kernel groove length. Notably, the combination of perimeter and kernel groove length yielded the highest accuracy (96.67%) in RF, while compactness and asymmetry coefficient consistently performed poorly across all algorithms, with accuracy as low as 60.71% in SVM. These findings highlight the critical role of feature selection in classification tasks, with kernel groove length emerging as a key determinant. This research not only provides an effective technical reference for wheat variety classification but also underscores the practical value of machine learning in agricultural applications, offering insights for optimizing efficiency and reducing costs in food security initiatives.
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 | 0.005 | 0.017 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.005 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".