An investigation into the use of machine learning for determining oestrus in cows

Mitchell, Rory; Sherlock, R.; Smith, Lloyd A.

doi:10.1016/0168-1699(96)00016-6

Cited by 31 publications

(15 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This represented an improvement in sensitivity, with equal specificity compared with results obtained using activity alone. Mitchell et al (1996) have carried out a preliminary investigation of the possibility of combining milk yield and data on milking order to detect oestrus. These variables were chosen because of appropriateness for New Zealand dairy herds.…”

Section: Oestrus Detectionmentioning

confidence: 99%

Animal board invited review: precision livestock farming for dairy cows with a focus on oestrus detection

Mottram

2016

Animal

View full text Add to dashboard Cite

Dairy cows are high value farm animals requiring careful management to achieve the best results. Since the advent of robotic and high throughput milking, the traditional few minutes available for individual human attention daily has disappeared and new automated technologies have been applied to improve monitoring of dairy cow production, nutrition, fertility, health and welfare. Cows milked by robots must meet legal requirements to detect healthy milk. This review focuses on emerging technical approaches in those areas of high cost to the farmer (fertility, metabolic disorders, mastitis, lameness and calving). The availability of low cost tri-axial accelerometers and wireless telemetry has allowed accurate models of behaviour to be developed and sometimes combined with rumination activity detected by acoustic sensors to detect oestrus; other measures (milk and skin temperature, electronic noses, milk yield) have been abandoned. In-line biosensors have been developed to detect markers for ovulation, pregnancy, lactose, mastitis and metabolic changes. Wireless telemetry has been applied to develop boluses for monitoring the rumen pH and temperature to detect metabolic disorders. Udder health requires a multisensing approach due to the varying inflammatory responses collectively described as mastitis. Lameness can be detected by walk over weigh cells, but also by various types of video image analysis and speed measurement. Prediction and detection of calving time is an area of active research mostly focused on behavioural change.Keywords: dairy cow, sensors, fertility, precision livestock farming, automation ImplicationsSince the introduction of robotic milking technologies to measure important parameters of cow health and fertility have moved from scientific concepts towards robust techniques routinely used on farms. There is still potential for developing new approaches but the main focus is on applying modelling to data sources that are already available such as tri-axial cow collars, in-line milk sensing and rumen telemetry. IntroductionIn the past century dairy farms have become larger, milk yields have risen, quality requirements have risen, labour has become less available and automated systems for milking and other farm tasks have become common all of these factors have created a need for automated monitoring of health and fertility. The first systems for recording milk yield electronically and allocating feed date back to the 1970s and automatic oestrus behaviour systems from the 1980s. As electronics have become cheaper and new sensing capabilities developed a variety of engineering options were reviewed for all animals by Frost et al. (1997). Mottram (1997) reviewed potential target disease conditions in dairy cows and identified parturition, mastitis and failures in nutrition as the most significant causes of loss. It was suggested that sensing should focus on the most directly measurable indicator of a condition such as rumen pH rather than proxy measures. Since then major developments have taken plac...

show abstract

Section: Oestrus Detectionmentioning

confidence: 99%

Animal board invited review: precision livestock farming for dairy cows with a focus on oestrus detection

Mottram

2016

Animal

View full text Add to dashboard Cite

show abstract

“…These approaches include the classical methods such as C4.5 and artificial neural networks, and the emerging methods such as support vector machine (SVM). The C4.5 (Quinlan, 1993) algorithm of machine learning is a well-known classification technique, which has been used for determining oestrus in cows (Mitchell, Sherlock, & Smith, 1996), and culling management of dairy herds (McQueen, Garner, Nevill-Manning, & Witten, 1995). The artificial neural networks have been applied to classify many types of food products, such as apple (Kavdir & Guyer, 2002), barley seed (Romaniuk, Sokhansanj, & Wood, 1993), poultry carcass (Park & Chen, 2000), and sweet onion (Shahin, Tollner, Gitaitis, Sumner, & Maw, 2002).…”

Section: Introductionmentioning

confidence: 99%

Comparison of three methods for classification of pizza topping using different colour space transformations

Sun

2005

Journal of Food Engineering

127

View full text Add to dashboard Cite

“…These classification rules were used to indicate the optimal range of these attributes for good service quality. Mitchell et al (1996) used a decision tree algorithm to detect estrus in cows. Kirchner et al (2004) used the decision tree technique to analyze pig production data, and used the classification algorithm to detect the threshold values of management decisions relating to sow replacement.…”

Section: Decision Tree Analysismentioning

confidence: 99%

Data-oriented analyses of ciliate foraging behaviors

et al. 2010

View full text Add to dashboard Cite

Optimal foraging theory states that natural selection makes foragers efficient food harvesters and maximizing a colony's energy intake. This study presumed that the ciliates foraging trajectories follow optimal foraging theory, verified the presumption and discover specific rules and patterns hidden in the ciliate's trajectories data using methodologies of statistical, cluster analyses, and decision tree analysis. This study examined the foraging behaviors of ciliates by video recordings and quantitative analyses of movement trajectories under four nourishment conditions (low, medium, high, and highest concentrations). Similar biological studies adopt statistical analyses to certain locomotion indices to determine the responses of plankton to various aquatic environments. In addition to statistical analyses, cluster analysis was used in this study to confirm the observations of the statistical analyses. The statistical analysis and cluster analysis results in this study revealed two distinct groups of trajectories or behaviors, which matched the optimal foraging theory. Decision tree analysis was then applied to acquire objective information regarding foraging behaviors, and further detailed the foraging behaviors with explicit classification rules using locomotion indices. The production rules can play an alternative role to assess the sustainability of an aquatic environment in terms of algae concentration.

show abstract

An investigation into the use of machine learning for determining oestrus in cows

Cited by 31 publications

References 11 publications

Animal board invited review: precision livestock farming for dairy cows with a focus on oestrus detection

Animal board invited review: precision livestock farming for dairy cows with a focus on oestrus detection

Comparison of three methods for classification of pizza topping using different colour space transformations

Data-oriented analyses of ciliate foraging behaviors

Contact Info

Product

Resources

About