Technical note: Evaluation of an ear-attached real-time location monitoring system
Bibliographic record
Abstract
Position tracking of cows within the barn environment allows for determining behavioral patterns and activities. Such data might be used for detection of estrus and disease. A newly marketed real-time location monitoring system (Smartbow, Smartbow GmbH, Weibern, Austria) was tested in this study. Cow location was continuously monitored with the Smartbow tags mounted on the cow's ear, which sends low-frequency signals to receivers further transmitting the information to a server. Through incoming data, the server triangulates the location of the cow within the barn environment in real time. The validation of the system was carried out in 4 steps. The first 2 steps served as static testing steps (tags and 1 cow positioned at 30 reference points), and steps 3 and 4 were dynamic steps with cows moving in the barn environment. For 48 h, locations of 15 cows were confirmed each hour by laser measurements performed by a team (step 3) or 1 observer (step 4). Interobserver variability was 0.83 m (range: 0.05 to 2.87 m), and intraobserver variability had a range of 0.02 to 0.31 m. In the 4 validation steps, the mean distance between observer laser measurements and Smartbow was between 1.22 and 1.80 m. Step 4, with 334 observations, resulted in a mean distance difference of 1.22 m (standard error = 1.32 m). Data can be used for development of algorithms to detect sick cows with changed behavioral patterns. Data may also be used to monitor cow responses to physical environment, potentially improving facility design. Time budgets in proximity to important barn features (i.e., feed bunk and water trough) and distances traveled can be calculated and used to identify cows in need of caretaker's attention and identify the cow's exact location in the barn.
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 | 0.006 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 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 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.002 |
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".