Automated Grading of Salvia miltiorrhiza Roots Using Neural Network
Bibliographic record
Abstract
With the development of artificial intelligence technology at present, neural networks have been widely applied to different types of Chinese herbal medicine classification tasks and have achieved very good results. However, there is currently a lack of sufficient experiments to demonstrate that neural networks have the same ability in different quality grading tasks for a single type of medicinal material. The subject of our research, Salvia miltiorrhiza, has been a very valuable traditional Chinese medicine since ancient times and has been widely used in the treatment of cardiovascular diseases. At present, the screening of high-quality S.miltiorrhiza heavily relies on experienced pharmacists for manual screening, which is not only time-consuming and labor-intensive, but also unable to be widely popularized. Therefore, achieving the automation of S.miltiorrhiza quality grading tasks has important economic value. In this article, we constructed a small dataset on S.miltiorrhiza, which includes a total of 91 S.miltiorrhiza samples, classified by traditional Chinese medicine experts into two categories: A and B. Due to the difficulty in obtaining samples of S.miltiorrhiza, we used methods such as data expansion and parameter optimization to improve the quality grading effect of S.miltiorrhiza the absence of sufficient data. These experiments demonstrate that neural networks are also effective in quality grading tasks for individual species. Finally, we also provided evidence for neural network prediction through thermodynamic diagrams. And emphasized the future work direction and potential applications.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".