Rapid determination of the roasting degree of cocoa beans by extreme learning machine (ELM)-based imaging analysis
Bibliographic record
Abstract
The determination of the levels of roasting of cocoa relies on expensive analytical equipment, sensory panel, and, in the cases of small processors and growers, empiricism. In this study, cocoa beans were roasted for 10–40 min to obtain different levels of roasting, and the images of the beans were captured by a smartphone camera. An extreme learning machine (ELM)-based algorithm was developed to predict the roasting degree of cocoa beans using the images of the cocoa bean cross-sections. A 22-dimension feature vector, including color and texture features, is extracted from each sample, and a total of 350 samples are used to train an ELM network. A majority rule-based voting method was used to make the decision. Experimental results showed that the proposed method achieved a classification accuracy of 93.75%. GC-MS analysis was conducted to determine the chemical compounds in the raw and roasted cocoa beans, and enrichment analysis, principal components analysis, partial least-squares–discriminant analysis, and Pearson correlation analysis were conducted to identify major chemicals respond to roasting time and classify the cocoa beans samples. Caffeine and theobromine were identified as primary chemical compounds that responded to roasting time, and cocoa beans with different levels of roasting were successfully classified.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| 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 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".