Normalization and Dimension Reduction for Machine Learning in Advanced Manufacturing
Bibliographic record
Abstract
Abstract With the advances in sensing and communication techniques, data collection has become much easier in manufacturing processes. Machine learning (ML) is a vital tool for manufacturing data analytics to leverage the underlying informatics carried by data. However, the varieties of data formats, dimensionality, and manufacturing types hugely hinder the learning efficiency of ML methods. Data preparation is critical for exploiting the potential of ML in manufacturing problems. This paper investigates how data preparation affects the ML efficacy in manufacturing data. Specifically, we study the influences of data normalization and dimension reduction on the ML performance for various types of manufacturing problems. We conduct comparison studies of data with/without pre-processing on different manufacturing processes, such as casting, milling, and additive manufacturing. Experimental results reveal that different pre-processing methods have a distinct effect on learning efficiency. Normalization is helpful for both numerical and image data, while dimension reduction — this paper uses principal component analysis (PCA) — is not useful for low-dimensional numerical manufacturing data. Combining both normalization and PCA can significantly enhance the learning efficiency of high-dimensional data. After that, we summarize several practical guidelines for manufacturing data preparation for ML, which provide a valuable basis for future manufacturing data analysis with ML approaches.
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 | 0.003 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".