Inline mastitis detection system measuring the electrical conductivity of quarter milk
Bibliographic record
Abstract
Dairy profitability depends on the quantity and quality of the produced milk. Bovine mastitis is the infection of udder tissues of cows that reduces both, and therefore it causes considerable economic damage to milk producers. Nowadays, the most widely adopted method to detect mastitis is by determining the somatic cell count per milliliter of milk. However, it requires qualified personnel and sometimes the results take a long time to be available, hampering an effective solution. The electrical conductivity of the milk could also be used, but if the test is done manually by an operator neither is effective, since affects the normal operation of the parlour. In this work we propose a mastitis detection system based on the measuring of the electrical conductivity of the milk of each quarter during the milking. A new milking claw is designed to include the conductivity traducers inside it, which are connected to the rest of the measuring unit. As a result, the only necessary modification to the milking machine is to replace the original milking claw with the new one. The system also includes a central unit to process conductivity samples sent by each measuring unit to determine if a cow has mastitis or not. A prototype is successfully tested in field, obtaining a precision of 65% and a recall of 64% for infected cows, approaching to the state of the art. Nevertheless, our approach is, to the best of our knowledge, the first proposal that allows a cost-effective solution since it can be integrated to existing milking machines and capable of issuing early warnings.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.005 | 0.003 |
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".