Validation of an automated method to count steps while cows stand on a weighing platform and its application as a measure to detect lameness
Bibliographic record
Abstract
Weight shifting between legs and steps taken when cows stand may be a useful tool to assess cow comfort and lameness. Weight shifting is assessed by measuring the distribution of weight applied to each leg when standing on a weighing platform, whereas frequency of steps is traditionally measured with live observation or video recording. The objectives of this study were to validate an automated method to count steps from weight distribution measurements (experiment 1) and to assess the accuracy of the frequency of steps in detecting lameness (experiment 2). In experiment 1, 6 nonlame multiparous cows stood on a weighing platform covered with either concrete or rubber (1h/cow per surface) while stepping behavior was video recorded. Receiver operating characteristic curves were constructed, using the steps observed in the video recordings as the gold standard, to calculate the optimal threshold (based on the sum of sensitivity and specificity) of the weight applied to a leg to define a step. Optimal thresholds were similar between surfaces. The optimal thresholds, when pooling the 2 surfaces, were 127 and 98 kg for the front and rear pair for legs, respectively, with a specificity and sensitivity ≥0.96. Thresholds were used to construct an algorithm to count steps. In experiment 2, 57 cows (26 of them considered lame according to their gait score) stood for 15 min on the weighing platform. Frequency of steps taken with the front and rear pair of legs was calculated from the weight distribution measurements using the algorithm calculated in experiment 1. Lame cows took more steps per minute with the rear legs than did nonlame cows (1.6 vs. 1.0 steps/min; SE of the difference=0.2). As previously shown for weight shifting, the frequency of steps taken with the rear legs was a good predictor of lameness (area under the curve of the receiver operating characteristic curve=0.67; 95% confidence interval=0.52, 0.81). A positive relationship was observed between the frequency of steps and weight shifting (measured as SD of the weight applied over time to the legs) in both the front (R(2)=0.35) and rear (R(2)=0.49) legs, yet the slopes differed from 1 and the intercepts differed from 0, indicating that the 2 measures were related but not the same. In conclusion, weighing platforms can accurately calculate the frequency of steps automatically, and this measure shows promise as a tool to assess lameness.
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 | 0.002 | 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".