245 Standardizing infrared thermography (IRT) and micro-behavioral biometrics for estrus detection in dairy cows
Bibliographic record
Abstract
Most Canadian dairy herds operate in tie-stall housing (61%) where estrus detection rates may be lower than 35%. Infrared thermography (IRT) is a non-invasive technology which can predict ovulation by measuring radiated heat. Complementary behavioral biometric algorithms may improve accuracy (>40%) and specificity (>6.7%). The objective of this study was to standardize infrared thermography and micro-behavioral biometrics for estrus detection in dairy cows. Thirty-six cows were divided into 2 treatments with 18 pregnant (CON) and 18 open (OPEN) cows. Open cows were synchronized with GnRH and CIDR protocol on (-14 d) and 2 injections of PGF2α 12 hours apart on (-7 d). Pregnant cows received a sham injection and CIDR on the same schedule and frequency as OPEN cows on the synchronization protocol. Cows were monitored via visual cameras (Swann DVR) 5 minutes before, during, and after milking to establish the frequency of treading, drinking, neighbor interactions, tail movements, and laying and shifting behaviors. Radiated heat and physiological changes were monitored relative to estrus using an infrared camera (FLIR T450s). Infrared measurements were adjusted by recording environmental and relative humidity before and after thermogram collection. Infrared images were recorded for the eye, muzzle, cheeks, neck, front feet, round, heart girth, vulva surround, tail head, and withers and analyzed using FLIR Tools software. Data were analyzed using the Glimmix procedure in SAS (v9.4) with cow as the experimental unit. All results are reported as LSmeans ± SEM. Thermal biometrics differed by imaging location in CON versus OPEN cows (e.g., vulva: CON 34.8°C ± 0.047; P < 0.0001, OPEN 35.32°C ± 0.047; P < 0.0001; muzzle: CON 32.51°C ± 0.09; P < 0.0001, OPEN 33.45°C ± 0.091; P < 0.0001, and cheeks: CON 32.30°C ± 0.084; P < 0.0001, OPEN 31.22°C ± 0.083; P < 0.0001). Thermograms found OPEN cows cooled at the tail head and heart girth as ovulation approached (tail head: -3 d 33.2°C ± 0.2 vs. 0 d 32.7°C ± 0.23; P < 0.0367; heart girth: -3 d 33.21°C ± 0.19 vs. 0 d 32.66°C ± 0.22; P < 0.0097). Treading behavior was significantly higher in CON (20.84 ± 0.39; P < 0.0001) and OPEN (16.35 ± 0.34; P < 0.0001) cows. Tail movements increased 72 hours before ovulation (-3 d 9.95 ± 1.18) compared with ovulation day (0 d 5.1 ± 1.03; P < 0.0001). Results indicate there is variation in temperature and micro-behaviors in the days leading up to ovulation as well as between CON and OPEN cows.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".