Search Results (5)

For decades, bovine mastitis and milk quality have been a focus area for research, agricultural extension, and dairy processors worldwide, yet employee management as a factor in udder health management has received limited attention. This is mainly because the focus has previously been on more classical areas covered by the National Mastitis Council Mastitis Control Program (NMC 10-point plan) in English-speaking countries. Therefore, we wanted more background information on employee management on dairy farms, to identify the human factor of udder health management. The method of investigating employee management and the impact of employee management on udder health was conducting a study of 88 Danish dairy farms with hired employees and parlor or rotary milking systems. An interview-based questionnaire on individual dairy farmers’ human resource management was developed based on the current literature and multiple discussions among the authors. The results we found through analyzing associations between the dependent variable BTSCC and employee management, using a regression model, was that providing a generic SOP was associated with a 21,600 cells/mL increase in BTSCC, with estimates in the range (507; 42,674 cells/mL). We also analyzed, applying a Poisson model, that there was a 0.16% reduction in new infection risk if the training was based on a herd-specific SOP and educated employees. In contrast, we identified a 0.15% increase in new infection risk in herds where SOPs were available but not incorporated, both modest but significant results. In conclusion, farms with educated employees and trained by an SOP achieve the lowest new infection risk, but education has no impact on BTSCC. Full article

A novel method of monitoring the health of dairy cows in large-scale dairy farms is proposed via image-based analysis of cows on rotary-based milking platforms, where deep learning is used to classify the extent of teat-end hyperkeratosis. The videos can be analyzed to segment the teats for feature analysis, which can then be used to assess the risk of infections and other diseases. This analysis can be performed more efficiently by using the key frames of each cow as they pass through the image frame. Extracting key frames from these videos would greatly simplify this analysis, but there are several challenges. First, data collection in the farm setting is harsh, resulting in unpredictable temporal key frame positions; empty, obfuscated, or shifted images of the cow’s teats; frequently empty stalls due to challenges with herding cows into the parlor; and regular interruptions and reversals in the direction of the parlor. Second, supervised learning requires expensive and time-consuming human annotation of key frames, which is impractical in large commercial dairy farms housing thousands of cows. Unsupervised learning methods rely on large frame differences and often suffer low performance. In this paper, we propose a novel unsupervised few-shot learning model which extracts key frames from large (∼21,000 frames) video streams. Using a simple L1 distance metric that combines both image and deep features between each unlabeled frame and a few (32) labeled key frames, a key frame selection mechanism, and a quality check process, key frames can be extracted with sufficient accuracy (F score 63.6%) and timeliness (<10 min per 21,000 frames) for commercial dairy farm setting demands. Full article

The aims of the research were to: (1) describe a protocol for the identification of cows that are subjected repeatedly to a forced retraction event at the end of milking; (2) study risk factors of repeated forced take-off (RFTO); and (3) assess the average milk flow rate at which the forced retraction event occurred. In a retrospective study, we collected milk flow data over a 1-week period from a 4300-cow dairy with a rotary milking parlor and a thrice-daily milking schedule. We identified 109 cases of RFTO and 2467 controls. A multivariable logistic regression model revealed associations of parity, stage of lactation, average daily milk production, and milking speed with RFTO. Cows in parity 3 or greater, animals ≤100 days in milk, high-producing animals, and cows with low milking speed had higher odds of RFTO. The average (least squares means (95% CI)) milk flow rates at the time of removal of the milking unit were 2.1 (2.0–2.1) kg/min in milking observations that were terminated with the forced retract and 1.5 (1.4–1.5) kg/min when milking units were removed with the automatic cluster remover. Future research to better understand the effect of RFTO on milk production, udder health, and animal well-being is warranted. Full article

Dairy farms are growing in several areas of the world, with consequent need for a modernization of milking equipment. The objective of this research is to evaluate milking parlors in current and future situations in modern farms. Several Italian farms were studied: three farms with side-by-side milking parlors (50 cows, 82 cows, and 100 cows), two with herringbone milking parlors (70 cows and 90 cows) and two with rotary milking parlors (360 cows and 900 cows). The choosing and evaluation of milking parlor parameters is based on results of previous research, using the mathematical model developed in the Czech University. The time for milking and the final specific direct costs are the main parameters which enable evaluation and choosing of suitable milking parlor from the dairy; neglect or promotion of only one of the mentioned criteria may lead to uneconomic investment or impaired operation of a farm. The evaluation of existing milking parlors can help to enhance the milking process and operations from the point of view of either technical improvement or improved activity of milkers. The results of measurement and calculation in current farms are compared with possible future enlarged farms. The study demonstrated that increasing the capacity of dairy farms enables a reduction of the final specific direct costs for milking. Full article

The Body Condition Score (BCS) for cows indicates their energy reserves, the scoring for which ranges from very thin to overweight. These measurements are especially useful during calving, as well as early lactation. Achieving a correct BCS helps avoid calving difficulties, losses and other health problems. Although BCS can be rated by experts, it is time-consuming and often inconsistent when performed by different experts. Therefore, the aim of our system is to develop a computerized system to reduce inconsistencies and to provide a time-saving solution. In our proposed system, the automatic body condition scoring system is introduced by using a 3D camera, image processing techniques and regression models. The experimental data were collected on a rotary parlor milking station on a large-scale dairy farm in Japan. The system includes an application platform for automatic image selection as a primary step, which was developed for smart monitoring of individual cows on large-scale farms. Moreover, two analytical models are proposed in two regions of interest (ROI) by extracting 3D surface roughness parameters. By applying the extracted parameters in mathematical equations, the BCS is automatically evaluated based on measurements of model accuracy, with one of the two models achieving a mean absolute percentage error (MAPE) of 3.9%, and a mean absolute error (MAE) of 0.13. Full article