Comparison of the Application of Different Machine Learning Outlier Detection Methods on Actual Chemical Process Plant Data
Bibliographic record
Abstract
Recent advancements in supervised machine learning tools have proven their capability to act as accurate approximation surrogate models for complex the chemical production processes. In this approach, complex unit models are replaced with surrogate models built from actual chemical plant Nevertheless, real data should be handled with caution as it isn't devoid of missing points, outliers, and faulty measurement, and using them without pre-processing could lead to inaccurate prediction models. Moreover, it is well-known that ideal real data without any outliers is almost nonexistence. Hence, cleaning data from outliers is very important step in data-driven modeling development Therefore, in this study different machine learning outlier detection method are implemented and compared to clean actual plant data before they are introduced to the data-driven surrogate models. Outliers are observations that do not follow bulk pattern of the data points and are unlikely observation of data. it is worth mentioning that identifying outliers by simple inspection and visualizing data set is challenging. There are different methods that can be used to identify outliers some of these methods are based on univariate statistical methods (Interquartile Range Method) and the others are based on unsupervised machine learning methods (Local outlier Factor, Isolation Forest, and One Class Support Vector Machine) The performances of these outlier detection methods on understudy data sets, are evaluated using linear regression that is used to predict certain process variables. Results show that removing outliers using these outlier detection
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 | 0.004 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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".