Electromagnetic characteristic estimation on spiral antennas through AOI, ML, and AI
Bibliographic record
Abstract
Abstract In this study, a method that is able to estimate the electromagnetic characteristic of spiral antennas was proposed and realized through consecutive procedures of automatic optical inspection (AOI), machine learning (ML), and artificial intelligence (AI), providing a solution to smart manufacturing. Two-arm self-complementary Archimedean spiral antennas (SCASAs) were introduced as examination targets with pattern distortions from potential process variations, in which bulges and neckings were mathematically generated to imitate uncontrollable ink rheology in printed and flexible electronics, covering the unexplored parts in previous works. The SCASAs in the training group were fabricated by standard printed circuit board procedures, and their pattern integrity in terms of line edge roughness (LER) and coupling frequency were collected through AOI for ML as the feature and label, respectively. The established AI model was based on Gaussian process regression with covariance function of exponential that showed the smallest root-mean-square-error and the largest coefficient of determination through iterative lazy-learning. By feeding the LERs of the SCASAs into the testing group, their corresponding coupling frequencies were estimated by the established AI model with high confidence level. Good linearity between the estimated and measured responses indicated that a reliable AI model and procedure were built, which outperforms existing methods that are unable to project off-line active characteristics of microelectronic components from their in-line pattern integrities.
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) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 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".