Wheat Kernel Classification Using Machine Learning
Bibliographic record
Abstract
Machine learning is mainly divided into two sections, specifically supervised and unsupervised learning. Supervised learning is additionally divided into two fundamental parts, that is, the regression type and classification type. Unsupervised learning additionally has its types like clustering, association, PCA, and so on. Here, we consider the use case from the supervised machine learning approach. We consider the dataset of the wheat kernel, used to classify 3 types of wheat, specifically Kama, Rosa, and Canadian, consisting of properties of the wheat kernel like area, compactness, perimeter, and so on. So, as this dataset comprises 3 classes or 3 distinct results, it is called multi-class data, which is multiple classes. Various machine learning algorithms can assist us in solving this multi-class classification problem. Some of the algorithms from Bagging [Ensemble Technique] are Random Forest, Boosting [Ensemble Technique] are LightGBM, XGBoost, Gradient Boosting, Support Vector Machine Classifier, Decision Tree Classifier, Logistic Regression, and so on. The above-mentioned algorithms work in different ways to find the solution to multi-class classification problems. In a large number of problems, we use an SVM classifier to solve the wheat kernel identifier use case. The SVM classifier is essential in solving binary classification problems. Nonetheless, here, in the wheat kernel identification case, multiple classes are three types of classes of items in the original dataset. This work focuses on learning the approaches for improving the results by using the support vector classifier and applying legitimate hyper-parameter tuning to get generalized output.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.002 |
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".