Technical note: Mining data from on-farm electronic equipment to identify the time dairy cows spend away from the pen
Bibliographic record
Abstract
The electronic equipment used on farms can be creatively co-opted to collect data for which it was not originally designed. In the current study, we describe 2 novel algorithms that harvest data from electronic feeding equipment and data loggers used to record standing and lying behavior, to estimate the time that dairy cows spend away from their pen to be milked. Our 2 objectives were to (1) measure the ability of the first algorithm to estimate the time cows spend away from the pen as a group and (2) determine the capability of a second algorithm to estimate the time it takes for individual cows to return to their pen after being milked. To achieve these objectives, we conducted 2 separate experiments: first, to estimate group time away, the feeding behavior of 1 pen of 20 Holstein cows was monitored electronically for 1 mo; second, to measure individual latency to return to the pen, feeding and lying behavior of 12 healthy Holstein cows was monitored electronically from parturition to 21 d in milk. For both experiments, we monitored the time each individual cow exited the pen before each milking and when she returned to the pen after milking using video recordings. Estimates generated by our algorithms were then compared with the times captured from the video recordings. Our first algorithm provided reliable pen-based estimates for the minimum time cows spent away from the pen to be milked in the morning [coefficient of determination (R 2 ) = 0.92] and afternoon (R 2 = 0.96). The second algorithm was able to estimate of the time it took for individual cows to return to the pen after being milked in the morning (R 2 = 0.98), but less so in the afternoon (R 2 = 0.67). This study illustrates how data from electronic systems used to assess feeding and lying behavior can be mined to estimate novel measures. New work is now required to improve the estimates of our algorithm for individuals, for example by adding data from other electronic monitoring systems on the farm.
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 | 0.019 | 0.051 |
| 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 | 0.003 | 0.003 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.015 | 0.013 |
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".