Using a three-axis accelerometer to identify and classify sheep behaviour at pasture

Alvarenga, Flavio A. P.; Borges, Isabela Nascimento; Palkovič, Lukáš; Rodina, Jozef; Oddy, V. H.; Dobos, Robin

doi:10.1016/j.applanim.2016.05.026

Cited by 129 publications

(99 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We also compared the ability of the model to discriminate behaviours over a range of discrete periods. We tested four epochs (number of accelerometer samples): 7 (0.28 s), 13 (0.52 s), 25 (1 s) and 75 (3 s) [24]. Behaviours could also be "contaminated" where two behaviours occur in the same time window.…”

Section: Behaviour Segmentingmentioning

confidence: 99%

“…Accuracy was the proportion of true positives identified by the model, while kappa was employed as more than two observers were used to classify data, thereby providing a measure for the fact that some of their observations will agree or disagree by chance [32]. This value was used to assess agreement of observed and predicted values in the confusion tables [24]. Precision and sensitivity are reported in the confusion matrix (Table 4) where precision is defined as the proportion of predictions from a behaviour category that were actually that behaviour, and sensitivity is the proportion of behaviours from a category that were classified as that behaviour [16].…”

Section: Classification Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Super machine learning: improving accuracy and reducing variance of behaviour classification from accelerometry

Ladds

Thompson²,

Kadar

et al. 2017

Anim Biotelemetry

View full text Add to dashboard Cite

Background: Semi-automating the analyses of accelerometry data makes it possible to synthesize large data sets. However, when constructing activity budgets from accelerometry data, there are many methods to extract, analyse and report data and results. For instance, machine learning is a robust approach to classifying data. We used a new method, super learning, that combines base learners (different machine learning methods) in an optimal manner to achieve overall improved accuracy. Other facets of super learning include the number of behavioural categories to predict, the number of epochs (sample window size) used to split data for training and testing and the parameters on which to train the models. Results:The super learner accurately classified behaviour categories with higher accuracy and lower variance than comparative models. For all models tested, using four behaviours, in comparison with six, achieved higher rates of accuracy. The number of epochs chosen also affected the accuracy with smaller epochs (7 and 13) performing better than longer epochs (25 and 75). Conclusions:Correct model selection, training and testing are imperative to creating reliable and valid classification models. To do so means model fitting must use a wide array of selection criteria. We evaluated a number of these including model, number of behaviours to classify and epoch length and then used a parameter grid search to implement the models. We found that all criteria tested contributed to the models' overall accuracies. Fewer behaviour categories and shorter epoch length improved the performance of all models tested. The super learner classified behaviours with higher accuracy and lower variance than other models tested. However, when using this model, users need to consider the additional human and computational time required for implementation. Machine learning is a powerful method for classifying the behaviour of animals from accelerometers. Care and consideration of the modelling parameters evaluated in this study are essential when using this type of statistical analysis.

show abstract

Section: Behaviour Segmentingmentioning

confidence: 99%

Section: Classification Modelsmentioning

confidence: 99%

Super machine learning: improving accuracy and reducing variance of behaviour classification from accelerometry

Ladds

Thompson²,

Kadar

et al. 2017

Anim Biotelemetry

View full text Add to dashboard Cite

show abstract

“…non-walking activities) can identify lameness. This goes beyond the current knowledge that suggests that lameness can influence the activity budget of animals [9] (i.e. how much time they spend lying, etc.…”

Section: Discussionmentioning

confidence: 85%

Automated detection of lameness in sheep using machine learning approaches: novel insights into behavioural differences among lame and non-lame sheep

et al. 2020

View full text Add to dashboard Cite

Lameness in sheep is the biggest cause of concern regarding poor health and welfare among sheep-producing countries. Best practice for lameness relies on rapid treatment, yet there are no objective measures of lameness detection. Accelerometers and gyroscopes have been widely used in human activity studies and their use is becoming increasingly common in livestock. In this study, we used 23 datasets (10 non-lame and 13 lame sheep) from an accelerometer-and gyroscope-based ear sensor with a sampling frequency of 16 Hz to develop and compare algorithms that can differentiate lameness within three different activities (walking, standing and lying). We show for the first time that features extracted from accelerometer and gyroscope signals can differentiate between lame and non-lame sheep while standing, walking and lying. The random forest algorithm performed best for classifying lameness with an accuracy of 84.91% within lying, 81.15% within standing and 76.83% within walking and overall correctly classified over 80% sheep within activities. Both accelerometer-and gyroscope-based features ranked among the top 10 features for classification. Our results suggest that novel behavioural differences between lame and non-lame sheep across all three activities could be used to develop an automated system for lameness detection.

show abstract

“…Such equipment also tends to be bulky and poorly transferrable between different individuals. One relatively small transducer-based emerging technology with promise uses accelerometers (Watanabe et al, 2008; Naito et al, 2010; Iwata et al, 2012; Andriamandroso, Lebeau & Bindelle, 2015; Alvarenga et al, 2016) attached to the mandibles of subject animals to monitor jaw movements associated with food ingestion. However, thus far, this approach seems unable to quantify masses ingested (Viviant et al, 2010).…”

Section: Introductionmentioning

confidence: 99%

The ability of magnetic field sensors to monitor feeding in three domestic herbivores

Mulvenna

Wilson

Marks

et al. 2018

PeerJ

View full text Add to dashboard Cite

The rate at which animals ingest food is a fundamental part of animal ecology although it is rarely quantified, with recently-developed animal-attached tags providing a potentially viable approach. However, to date, these methods lack clarity in differentiating various eating behaviours, such as ‘chewing’ from ‘biting’. The aims of this study were to examine the use of inter-mandibular angle sensors (IMASENs), to quantify grazing behaviour in herbivores including cattle (Bos taurus), sheep (Ovis aries) and pygmy goats (Capra aegagrus hircus) eating different foodstuffs. Specifically, we aimed to: (1) quantify jaw movements of each species and determine differences between biting and chewing; (2) assess whether different food types can be discerned from jaw movements; and (3) determine whether species-specific differences in jaw movements can be detected. Subjects were filmed while consuming concentrate, hay, grass and browse to allow comparison of observed and IMASEN-recorded jaw movements. This study shows that IMASENs can accurately detect jaw movements of feeding herbivores, and, based on the rate of jaw movements, can classify biting (taking new material into the mouth) from chewing (masticating material already in the mouth). The biting behaviours associated with concentrate pellets could be identified easily as these occurred at the fastest rate for all species. However, the rates of chewing different food items were more difficult to discern from one another. Comparison of chew:bite ratios of the various food types eaten by each species showed no differences. Species differences could be identified using bite and chew rates. Cattle consistently displayed slower bite and chew rates to sheep and pygmy goats when feeding, while sheep and pygmy goats showed similar bite and chew rates when feeding on concentrate pellets. Species-specific differences in chew:bite ratios were not identified. Magnetometry has the potential to record quantitative aspects of foraging such as the feeding duration, food handling time and food type. This is of major importance for researchers interested in both captive (e.g., agricultural productivity) and wild animal foraging dynamics as it can provide quantitative data with minimal observer interference.

show abstract

Using a three-axis accelerometer to identify and classify sheep behaviour at pasture

Cited by 129 publications

References 20 publications

Super machine learning: improving accuracy and reducing variance of behaviour classification from accelerometry

Super machine learning: improving accuracy and reducing variance of behaviour classification from accelerometry

Automated detection of lameness in sheep using machine learning approaches: novel insights into behavioural differences among lame and non-lame sheep

The ability of magnetic field sensors to monitor feeding in three domestic herbivores

Contact Info

Product

Resources

About