Denoising stacked autoencoders‐based near‐infrared quality monitoring method via robust samples evaluation
Bibliographic record
Abstract
Abstract This paper proposes a denoising stacked autoencoders‐based near‐infrared spectroscopy on‐line quality monitoring model via robust sample evaluation. The previous related work tends to focus on the near infrared spectrum data from the high dimension, multicollinearity, and information redundancy, and so on, but pays less attention to its inherent nonlinearity and sensitivity caused by internal and external factors (i.e., particle size, colour, moisture, uniformity, temperature, and so on). First, this paper aims to achieve feature extraction in nonlinearity with a denoising stack autoencoder, overcoming the impact of over‐sensitivity described as given distributed noise. Second, we propose a robust sample evaluation method derived from the robust statistics to tell and eliminate the individual samples contrary to the potentially statistical rules learned by the established model from the population samples and retrain the model with a more robust training set. The near‐infrared spectrum data derived from the distillation process of 2, 6 xylenol are used as a case in this paper to verify the validity and accuracy of the monitoring model proposed above.
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 | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".