Technical note: Validation of an ear-tag accelerometer to identify feeding and activity behaviors of tiestall-housed dairy cattle
Bibliographic record
Abstract
The objective of this study was to validate the CowManager SensOor ear-tag accelerometer (Agis Automatisering BV, Harmelen, the Netherlands) against visual observations of feeding, rumination, resting, and active behaviors of tiestall-housed dairy cows. Prior validation of the sensor has been published for freestall and grazing dairy herds. However, the behavioral differences that exist among these and a tiestall system necessitate additional validation. Lactating Holstein cows (n = 10) at different lactation stages and parities were included in the study. Cows were monitored both visually and with the sensor for 10 h/d for 4 consecutive days (10 cows × 10 h × 4 d = 400 h of observation total). A single trained observer classified each minute of visual observation into 1 of 13 behaviors and then summarized them into the 4 behavioral categories of eating, rumination, not active, or active. The sensor registered ear movements continuously and, based on a proprietary model, converted them into the behavioral categories. Multivariate mixed models were run to obtain covariance estimates, from which correlation coefficients were computed to assess agreement between visual observation and sensor data. The models included the percentage of time spent performing each behavior per day as the dependent variable and technology (visual observation versus sensor) and day as fixed effects. The models also included the random effects of technology and the repeated effects of technology and day. The correlation strength between visual observation and sensor data varied from poor to almost perfect by behavioral category (eating: r = 0.27; rumination: r = 0.69; eating-rumination: r = 0.83; not active: r = 0.95; and active: r = 0.89). The results suggest that the sensor can be used to accurately monitor active and not-active behaviors of tiestall-housed dairy cows. The results also suggest that although the sensor shows promise for identifying feeding behaviors in general, the independent classification of rumination and eating requires additional sensitivity.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".