Intelligent Fusion of Sensor Data for Product Quality Assessment in a Fishcutting Machine
Bibliographic record
Abstract
This article presents three techniques of knowledge-based fuzzy sensor fusion, which are based on (1) Mamdani sup-prod composition, (2) degree of certainty, and (3) compatibility of data. The first method of sensor fusion uses Mamdani's sup-prod (or max-prod) composition, and it places equal weights on all the data sources, without considering their merit or importance. The second method uses the concept of degree of certainty. It assigns weights proportional to the degree of certainty of sensor data, and in addition to the fused output, it provides information about the certainty of the output. The third method of sensor fusion uses the idea of compatibility of data. It provides a fused output and additional knowledge about the degree of confidence in that output. This method is particularly effective when sensors provide conflicting information. The three techniques are implemented in an automated machine for mechanical processing of salmon, to determine the level of product quality (i.e., the quality of processed fish), and thereby evaluate the relative performance of the techniques. In this machine, process information is available from disparate sensors like CCD cameras, optical encoders, and an ultrasonic displacement sensor. Three sets of fish-cut data for a good, a bad, and a conflicting data cut are used in the illustrative example. The results indicate that the three methods are equally effective, but method 2, which is more sophisticated, has a slight advantage in performance over the other, at the expense of added complexity.
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 | 0.002 | 0.003 |
| 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 | 0.001 | 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".