The DOI matches its Crossref record; 97 of the 104 references it cites were found in a registry or an index, and 2 are not checked yet; none of the 49 sources its claims cite is checked for support yet.
Applications of machine learning in animal behaviour studies
Open accessAbstract
In many areas of animal behaviour research, improvements in our ability to collect large and detailed data sets are outstripping our ability to analyse them. These diverse, complex and often high-dimensional data sets exhibit nonlinear dependencies and unknown interactions across multiple variables, and may fail to conform to the assumptions of many classical statistical methods. The field of machine learning provides methodologies that are ideally suited to the task of extracting knowledge from these data. In this review, we aim to introduce animal behaviourists unfamiliar with machine learning (ML) to the promise of these techniques for the analysis of complex behavioural data. We start by describing the rationale behind ML and review a number of animal behaviour studies where ML has been successfully deployed. The ML framework is then introduced by presenting several unsupervised and supervised learning methods. Following this overview, we illustrate key ML approaches by developing data analytical pipelines for three different case studies that exemplify the types of behavioural and ecological questions ML can address. The first uses a large number of spectral and morphological characteristics that describe the appearance of pheasant, Phasianus colchicus, eggs to assign them to putative clutches. The second takes a continuous data stream of feeder visits from PIT (passive integrated transponder)-tagged jackdaws, Corvus monedula, and extracts foraging events from it, which permits the construction of social networks. Our final example uses aerial images to train a classifier that detects the presence of wildebeest, Connochaetes taurinus, to count individuals in a population. With the advent of cheaper sensing and tracking technologies an unprecedented amount of data on animal behaviour is becoming available. We believe that ML will play a central role in translating these data into scientific knowledge and become a useful addition to the animal behaviourist's analytical toolkit.
Checked 2026-10-09 · 2 references not checked yet
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
This review introduces machine learning to animal behaviourists and illustrates unsupervised and supervised workflows through three case studies: assigning pheasant eggs to clutches, extracting jackdaw foraging events to build social networks, and detecting wildebeest in aerial images. It argues ML is well suited to complex, high-dimensional behavioural data but is not a silver bullet and requires careful validation.
Key findings
- Pheasant eggs: 549 eggs from 30 females in 10 pens were described by 21 morphological and spectral measures; PCA retained four components explaining 96% of variance, and k-means/hierarchical clustering with silhouette width indicated k = 3 clutches.
- Jackdaws: around 1000 PIT-tagged individuals across three colonies were studied; an illustrative 4-week data set from 141 individuals at one feeder was modelled with a Gaussian mixture model and BIC, and the resulting network confirmed associations between mated adults, parents and offspring, and unrelated individuals.
- Wildebeest: 250 aerial images of 64 × 64 pixels (50 each for wildebeest, zebra, trees, rocks and grass) were classified using HOG features and random forests; 175 images were used for training and 75 for testing, and from over 1000 features only a couple of hundred were needed, though two wildebeest in the test set were misclassified as trees.
- The review states ML is hypothesis-free and prediction-focused, can handle nonlinearities and interactions, but can learn patterns different from human cues and is vulnerable to biased training data and mistaking correlation for causation.
Methods
- Narrative review plus three worked case studies, with documented code at https://github.com/jjvalletta/ML_Animal_Behaviour; methods covered include PCA, k-means, hierarchical clustering, Gaussian mixture models, decision trees, random forests, cross-validation and feature selection.
- Case-study data: pheasant eggs (30 females, 10 pens, 549 eggs, 21 morphological/spectral measures, reflectance spectra 300–700 nm); jackdaw PIT-tag feeder visits (around 1000 birds across three colonies; illustrative 4 weeks from 141 individuals at one feeder); wildebeest aerial photos (250 images, 64 × 64 pixels, five classes).
- Main analyses: PCA and clustering for pheasant eggs; GMM with BIC and adjacency-matrix construction for jackdaw social networks; HOG feature extraction, t-SNE visualization, random forests with variable importance and a confusion matrix for wildebeest detection.
Limitations
- The paper states ML is “no silver bullet”: models may use cues unlike human cues (e.g. wildebeest misclassified as trees), biased training data can cause erratic behaviour (the tank/no-tank anecdote), observational data can mistake correlation for causation, and reproducibility over independent data sets is the most rigorous validation.
- The paper states that determining the number of clusters k is a fundamental yet unsolved problem, is mathematically subjective, and the final decision rests with the practitioner.
- Evident from the text: the case studies are illustrative rather than fully validated—pheasant maternity validation by protein fingerprinting is proposed but not performed; the jackdaw analysis uses only 4 weeks, one feeder and 141 individuals; and the wildebeest classifier uses five classes for illustration although automated counting would require only two.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
29 Not checked yet · 23 No basis given · 18 Own interpretation · 13 Own result
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Thus, PC1 is a measure of eggshell brightness, PC2 is a measure of eggshell greenness, PC3 is a measure of egg size and PC4 is a measure of egg shape.”
§ Applications of machine learning in animal behaviour studies > Pheasant Eggs
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The jackdaw social network we generated (see Fig. 4e) confirms the existence of foraging associations between mated adults and between parents and offspring.”
§ Applications of machine learning in animal behaviour studies > Cluster validity
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As depicted in Fig. 4b, the data are dominated by short intervisit periods corresponding to foraging events, interleaved with long periods of inactivity.”
§ Applications of machine learning in animal behaviour studies > Jackdaw Associations
plainn = 141- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Fig. 3c depicts the PCA outcome, where the first four components explained 96% of the variance in the data and were kept as features for subsequent analysis.”
- Also stated in: § CONCLUDING REMARKS · plain
“The first four components explained 96% of the variance in the data and were kept as features for subsequent analysis.”
§ Applications of machine learning in animal behaviour studies > Pheasant Eggs
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § CONCLUDING REMARKS · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“From an initial pool of over 1000 features only a couple of hundred predictors were needed to achieve good predictive performance on the training data set.”
§ Applications of machine learning in animal behaviour studies > Wildebeest Identification
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We could use the 'raw' data, that is, the individual pixel intensities; however, when we projected them onto the first two principal components for visualization (see Appendix Fig. A5a) no obvious groupings were present.”
§ Applications of machine learning in animal behaviour studies > Wildebeest Identification
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Thus, PC1 is a measure of eggshell brightness, PC2 is a measure of eggshell greenness, PC3 is a measure of egg size and PC4 is a measure of egg shape.”
§ Applications of machine learning in animal behaviour studies > Pheasant Eggs
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Thus, PC1 is a measure of eggshell brightness, PC2 is a measure of eggshell greenness, PC3 is a measure of egg size and PC4 is a measure of egg shape.”
§ Applications of machine learning in animal behaviour studies > Pheasant Eggs
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The outcome was similar to that from k-means, but using dendrograms, the results can be visualized irrespective of dimensionality (as opposed to k-means where results had to be projected onto the first two PCs), and also allows us to identify subgroups within each cluster.”
§ Applications of machine learning in animal behaviour studies > Pheasant Eggs
plainSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“A correlogram of all 21 morphological and spectral measures showed strong linear associations between some of the variables (see Fig. 3b).”
§ Applications of machine learning in animal behaviour studies > Pheasant Eggs
boostedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- It may state two separate claims as one. 29
- Probably not a substantial claim. 39
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“When projected onto the first two PCs, the HOGs features showed promising grouping by class, although it was still somewhat concealed (see Appendix Fig. A5b).”
§ Applications of machine learning in animal behaviour studies > Wildebeest Identification
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It also reveals strong associations between unrelated individuals and shows how these associations relate to the spatial proximity between nestboxes.”
§ Applications of machine learning in animal behaviour studies > Cluster validity
boostedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For example, the confusion matrix in Fig. 5e shows how two wildebeests in the test data were mistakenly labelled as trees.”
§ Applications of machine learning in animal behaviour studies > CONCLUDING REMARKS
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Visual inspection of eggs suggested that withinindividual variation in egg morphology may be low while interindividual variation is high.”
§ Applications of machine learning in animal behaviour studies > Pheasant Eggs
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“The focus is on inference; estimating the parameters of the statistical model that most likely gave rise to the observed data, and providing uncertainty bounds for these estimates.”
§ Applications of machine learning in animal behaviour studies > Abstract
What the sources say
- Not checked yetcites Breiman, 2001b
- Not checked yetcites Friedman, 2001 source
- Not checked yetcites Zoubin Ghahramani, 2015
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Statistical models start with an assumption about the underlying data distribution (e.g.Gaussian, Poisson).”
§ Applications of machine learning in animal behaviour studies > Abstract
What the sources say
- Not checked yetcites Breiman, 2001b
- Not checked yetcites Friedman, 2001 source
- Not checked yetcites Zoubin Ghahramani, 2015
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“This allows us to answer important questions across a range of topics, including movement ecology, social structure, collective behaviour, communication and welfare.”
§ Applications of machine learning in animal behaviour studies > Abstract
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
- Rests on an assumption: In many areas of animal behaviour research, improvements in the ability to collect large and detailed data sets are outstripping the ability to analyse them.
- Rests on an assumption: Animal behaviour researchers are in a position where automatically collecting detailed data sets is becoming commonplace, but extracting knowledge from them is a daunting task, mainly due to the lack of accessible analytical tools.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The field of machine learning provides methodologies that are ideally suited to the task of extracting knowledge from these data.”
§ Applications of machine learning in animal behaviour studies > Abstract
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
- Rests on an assumption: In many areas of animal behaviour research, improvements in the ability to collect large and detailed data sets are outstripping the ability to analyse them.
- Rests on an assumption: These diverse, complex and often high-dimensional data sets exhibit nonlinear dependencies and unknown interactions across multiple variables, and may fail to conform to the assumptions of many classical statistical methods.
- Rests on an assumption: Animal behaviour researchers are in a position where automatically collecting detailed data sets is becoming commonplace, but extracting knowledge from them is a daunting task, mainly due to the lack of accessible analytical tools.
None of the sources cited for this claim have been checked yet.
In the paper
“Both statistical modelling and ML seek to build a mathematical description, a model, of the data and the underlying mechanism it represents; thus inevitably there is substantial overlap between the two”
§ Applications of machine learning in animal behaviour studies > Abstract
What the sources say
- Not checked yetcites Breiman, 2001b
- Not checked yetcites Friedman, 2001 source
- Not checked yetcites Zoubin Ghahramani, 2015
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In animal behaviour, ML approaches can address otherwise intractable tasks, such as classifying species, individuals, vocalizations or behaviours within complex data sets.”
§ Applications of machine learning in animal behaviour studies > Abstract
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
- Rests on an assumption: In many areas of animal behaviour research, improvements in the ability to collect large and detailed data sets are outstripping the ability to analyse them.
- Rests on an assumption: Animal behaviour researchers are in a position where automatically collecting detailed data sets is becoming commonplace, but extracting knowledge from them is a daunting task, mainly due to the lack of accessible analytical tools.
None of the sources cited for this claim have been checked yet.
In the paper
“For ML, the focus is typically on prediction; without necessarily assuming a functional distribution for the data, a model that achieves optimal predictive performance is identified.”
§ Applications of machine learning in animal behaviour studies > Abstract
What the sources say
- Not checked yetcites Breiman, 2001b
- Not checked yetcites Friedman, 2001 source
- Not checked yetcites Zoubin Ghahramani, 2015
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may state two separate claims as one.
In the paper
“ML was used in a comparative assessment of welfare across multiple laboratory populations of mice (Chesler et al., 2002) permitting a wide range of potential explanatory factors, each with diverse distribution, to be considered simultaneously as well as the interactions between them.”
§ Applications of machine learning in animal behaviour studies > Abstract
What the sources say
- Not checked yetcites Chesler et al., 2002 source
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In this case, the individual pixel intensities are not explicitly related to the image's class, suggesting the need for hand-crafted features that describe the object in each image.”
§ Applications of machine learning in animal behaviour studies > Wildebeest Identification
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The OOB data are also used to compute an estimate of the importance of every predictor, which can be subsequently used for feature selection.”
§ Applications of machine learning in animal behaviour studies > Random Forests
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Using such a classifier may soon enable the fully automated detection and identification of animals from aerial count images.”
§ Applications of machine learning in animal behaviour studies > Wildebeest Identification
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
- Rests on an assumption: Machine learning can relieve this burden by detecting wildebeest in an image and therefore automating this aspect of the count.
None of the sources cited for this claim have been checked yet.
In the paper
“Random forests (Breiman, 2001a;Cutler et al., 2007) is an ensemble method developed to mitigate the problem of overfitting in decision trees.”
§ Applications of machine learning in animal behaviour studies > Random Forests
What the sources say
- Not checked yetcites Breiman, 2001a
- Not checked yetcites Cutler et al., 2007 source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“While in traditional statistical modelling a hypothesis (model) is put forward and is then accepted/rejected depending on how consistent it is with the measured observations, ML methods learn this hypothesis directly from the training data set.”
§ Applications of machine learning in animal behaviour studies > Abstract
What the sources say
- Not checked yetcites Breiman, 2001b
- Not checked yetcites Friedman, 2001 source
- Not checked yetcites Zoubin Ghahramani, 2015
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“ML algorithms can deal with nonlinearities and interactions among variables because the models are flexible enough to fit the data (as opposed to rigid linear regression models, for example).”
§ Applications of machine learning in animal behaviour studies > SUPERVISED LEARNING
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Random forests can handle thousands of mixed categorical and continuous predictors and are robust to outliers; however, the interpretability of plain decision trees is lost.”
§ Applications of machine learning in animal behaviour studies > Random Forests
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“However, this flexibility needs to be constrained to avoid fitting noise (overfitting).”
§ Applications of machine learning in animal behaviour studies > SUPERVISED LEARNING
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“It is clear that ML can address different objectives in numerous distinct fields of animal behaviour and is thus becoming a staple approach for novel methods (Dankert, Wang, Hoopfer, Anderson, & Perona, 2009;Kabra et al., 2013).”
§ Applications of machine learning in animal behaviour studies > Abstract
What the sources say
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Finer scale discriminations are possible at both the individual level (Cheng, Xie, Lin, & Ji, 2012) and the bird song elements level (Ranjard & Ross, 2008).”
§ Applications of machine learning in animal behaviour studies > Abstract
What the sources say
- Not checked yetcites Cheng et al., 2012 source
- Not checked yetcites Ranjard & Ross, 2008
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Co-occurrences in time could be determined by ML clustering methods with individuals in the same foraging event (cluster) considered to have a social affiliation (Psorakis et al., 2015).”
§ Applications of machine learning in animal behaviour studies > Abstract
What the sources say
- Not checked yetcites Psorakis et al., 2015 source
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Female pheasants may nest communally or lay eggs in multiple nests (Yom-Tov, 1980).”
§ Applications of machine learning in animal behaviour studies > Pheasant Eggs
What the sources say
- Not checked yetcites Yom-Tov, 1980 source
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“k-means clustering is popular because it is intuitive and computationally inexpensive.”
§ Applications of machine learning in animal behaviour studies > k-means
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“ML is used to automate the classification of behaviours/activities (Kabra et al., 2013) and tracking movement trajectories (Dell et al., 2014).”
§ Applications of machine learning in animal behaviour studies > Abstract
What the sources say
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It is this hypothesis-free approach that makes ML an attractive choice for dealing with complex data sets.”
§ Applications of machine learning in animal behaviour studies > Abstract
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“However, they are prone to overfitting (small changes in the training data set may lead to significantly different trees) and their predictive performance can be poor compared to other algorithms.”
§ Applications of machine learning in animal behaviour studies > Decision Trees
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“If achieved, this will have major implications for conservation as currently the process of detecting and identifying animals within images is the main bottleneck for estimating population sizes from aerial surveys (Torney et al., 2016).”
§ Applications of machine learning in animal behaviour studies > Wildebeest Identification
What the sources say
- Not checked yetcites Torney et al., 2016 source
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may state two separate claims as one.
- Rests on an assumption: Currently counting wildebeest from aerial photos is time consuming, as thousands of aerial photos need to be counted manually.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“GMMs, however, assume that data are generated from a mixture of multivariate Gaussians and lack a global optimum solution.”
§ Applications of machine learning in animal behaviour studies > Gaussian mixture model (GMM)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Determining the number of distinct clusters k in a data set is a fundamental yet unsolved problem.”
§ Applications of machine learning in animal behaviour studies > How many clusters?
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
In the paper
“Such methods appear to be robust and capture real-life pair bonds well (Psorakis, Roberts, Rezek, & Sheldon, 2012).”
§ Applications of machine learning in animal behaviour studies > Abstract
What the sources say
- Not checked yetcites Psorakis et al., 2012 source
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Decision trees are readily interpretable, directly used to generate rules, and computationally inexpensive to train, evaluate and store.”
§ Applications of machine learning in animal behaviour studies > Decision Trees
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The rationale behind dimensionality reduction is simple; although the collected data may seem high dimensional, the structure of the data can be represented by fewer variables.”
§ Applications of machine learning in animal behaviour studies > Dimensionality Reduction
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Using unsupervised learning methods, we were able to reduce the dimensionality of the problem to a few biologically meaningful features, and subsequently assign eggs to females.”
§ Applications of machine learning in animal behaviour studies > Pheasant Eggs
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: Without direct observation of laying or destructive genetic sampling from eggs, it is not possible to assign eggs to females.
In the paper
“Based on the work of Psorakis et al. (2012), Fig. 4a summarizes the workflow used to convert a long series of time stamps into a social network.”
§ Applications of machine learning in animal behaviour studies > Jackdaw Associations
What the sources say
- Not checked yetcites Psorakis et al. (2012) source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“They can handle both categorical and continuous data, and are fairly robust to outliers.”
§ Applications of machine learning in animal behaviour studies > Decision Trees
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“However, it is only applicable to continuous data where a mean is defined.”
§ Applications of machine learning in animal behaviour studies > k-means
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Feature extraction is a key step in ML; finding representations that are directly relevant to the task at hand (e.g.discriminating between two classes) will almost always result in better predictive accuracy than employing more complex models.”
§ Applications of machine learning in animal behaviour studies > Feature extraction
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“There is also no guarantee of a global optimum solution; thus, the user is advised to start the algorithm at multiple distinct centroids.”
§ Applications of machine learning in animal behaviour studies > k-means
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“ML can tackle a wide range of tasks, including classifying observations into predefined sets (Kabra, Robie, Rivera-Alba, Branson, & Branson, 2013), clustering data into groups that share an underlying process (Zhang, O'Reilly, Perry, Taylor, & Dennis, 2015) and regressing an outcome of interest against multiple factors and elucidating their contributory effect (Chesler, Wilson, Lariviere, Rodrig”
§ Applications of machine learning in animal behaviour studies > Abstract
What the sources say
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“This knowledge can then be used to infer individual decision rules in collective motion (Katz, Tunstrom, Ioannou, Huepe, & Couzin, 2011;Nagy, Kos, Biro, & Vicsek, 2010) and to compute activity budgets for individuals without the need for continuous human observation or time-consuming video analysis.”
§ Applications of machine learning in animal behaviour studies > Abstract
What the sources say
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“There are also cases where a mix of labelled and unlabelled data are available, which would require the use of a different type of ML methods: semisupervised learning (Chapelle, Sch€ olkopf, & Zien, 2006).”
§ Applications of machine learning in animal behaviour studies > CONCLUDING REMARKS
What the sources say
- Not checked yetcites Chapelle, Schölkopf, & Zien, 2006
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“PC1 is a measure of eggshell brightness, PC2 is a measure of eggshell greenness, PC3 is a measure of egg size and PC4 is a measure of egg shape.”
§ Applications of machine learning in animal behaviour studies > Additional information
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, as we have seen earlier, unsupervised learning methods are routinely used with labelled data during the data exploration stage.”
§ Applications of machine learning in animal behaviour studies > CONCLUDING REMARKS
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“PC1 is a measure of eggshell brightness, PC2 is a measure of eggshell greenness, PC3 is a measure of egg size and PC4 is a measure of egg shape.”
§ Applications of machine learning in animal behaviour studies > Additional information
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“To this end, automatically extracting predictive features from 'raw' data is the central theme of a new set of methods, in an active area of research, called Deep Learning (LeCun, Bengio, & Hinton, 2015).”
§ Applications of machine learning in animal behaviour studies > CONCLUDING REMARKS
What the sources say
- Not checked yetcites LeCun, Bengio, & Hinton, 2015 source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“High-profile failures highlight how even experts in the field of ML can fall victim of common pitfalls in data-driven analytics.”
§ Applications of machine learning in animal behaviour studies > CONCLUDING REMARKS
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The type of data (labelled or unlabelled) and the particular task at hand ultimately dictate the category of algorithms to choose from (see Table 1).”
§ Applications of machine learning in animal behaviour studies > CONCLUDING REMARKS
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Instead of using hand-crafted features (as we did in the wildebeest identification problem), Deep Learning automatically discovers features amenable for prediction by recursively applying simple but nonlinear transformations to the data.”
§ Applications of machine learning in animal behaviour studies > CONCLUDING REMARKS
What the sources say
- Not checked yetcites LeCun, Bengio, & Hinton, 2015 source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“Associations between an outcome and a set of inputs could have occurred by chance, owing to a confounding factor or a biased data set.”
§ Applications of machine learning in animal behaviour studies > CONCLUDING REMARKS
What the sources say
- Not checked yetcites MacKinnon, Krull, & Lockwood, 2000 source
- Not checked yetcites Zuur, Ieno, & Elphick, 2010
- Not checked yetcites A. Liu & Ziebart, 2014
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Reproducibility of a predictive model over multiple independent data sets over time is ultimately the most rigorous form of validation.”
§ Applications of machine learning in animal behaviour studies > CONCLUDING REMARKS
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
In the paper
“These methods make use of unlabelled data to improve the performance of predictive models identified from labelled observations.”
§ Applications of machine learning in animal behaviour studies > CONCLUDING REMARKS
What the sources say
- Not checked yetcites Chapelle, Schölkopf, & Zien, 2006
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“However, there are no hard and fast rules to this process and it has been shown that the performance of several state-of-the-art supervised learning algorithms are similar (Fern andez-Delgado, Cernadas, Barro, & Amorim, 2014).”
§ Applications of machine learning in animal behaviour studies > CONCLUDING REMARKS
What the sources say
- Not checked yetcites Fernandez-Delgado, Cernadas, Barro, & Amorim, 2014
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“PC1 is a measure of eggshell brightness, PC2 is a measure of eggshell greenness, PC3 is a measure of egg size and PC4 is a measure of egg shape.”
§ Applications of machine learning in animal behaviour studies > Additional information
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“PC1 is a measure of eggshell brightness, PC2 is a measure of eggshell greenness, PC3 is a measure of egg size and PC4 is a measure of egg shape.”
§ Applications of machine learning in animal behaviour studies > Additional information
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper relies on this without support.
In many areas of animal behaviour research, improvements in the ability to collect large and detailed data sets are outstripping the ability to analyse them.
“In many areas of animal behaviour research, improvements in our ability to collect large and detailed data sets are outstripping our ability to analyse them.”
The paper relies on this without support.
These diverse, complex and often high-dimensional data sets exhibit nonlinear dependencies and unknown interactions across multiple variables, and may fail to conform to the assumptions of many classical statistical methods.
“These diverse, complex and often highdimensional data sets exhibit nonlinear dependencies and unknown interactions across multiple variables, and may fail to conform to the assumptions of many classical statistical methods.”
The paper relies on this without support.
Animal behaviour researchers are in a position where automatically collecting detailed data sets is becoming commonplace, but extracting knowledge from them is a daunting task, mainly due to the lack of accessible analytical tools.
“Animal behaviour researchers are thus in a position where automatically collecting detailed data sets is becoming commonplace, but extracting knowledge from them is a daunting task, mainly due to the lack of accessible analytical tools.”
The paper relies on this without support.
Without direct observation of laying or destructive genetic sampling from eggs, it is not possible to assign eggs to females.
“Without direct observation of laying or destructive genetic sampling from eggs, it is not possible to assign eggs to females.”
The paper relies on this without support.
Uncovering social structures in jackdaws allows us to infer individualized social relationships and determine how novel information spreads through social groups.
“Uncovering social structures in jackdaws allows us to infer individualized social relationships and determine how novel information spreads through social groups.”
The paper relies on this without support.
It is unclear how one specifies the length of foraging events without fixing an arbitrary time window.
“It is unclear, however, how one specifies the length of these foraging events without fixing an arbitrary time window.”
The paper relies on this without support.
Currently counting wildebeest from aerial photos is time consuming, as thousands of aerial photos need to be counted manually.
“Currently this process is time consuming, as thousands of aerial photos need to be counted manually.”
The paper relies on this without support.
Machine learning can relieve this burden by detecting wildebeest in an image and therefore automating this aspect of the count.
“Machine learning can relieve this burden by detecting wildebeest in an image and therefore automating this aspect of the count.”
The paper relies on this without support.
Research on jackdaw social structure has largely been confined to captive studies and there is limited information on patterns of association in natural populations.
“However, research has largely been confined to captive studies and there is limited information on patterns of association in natural populations.”
The paper relies on this without support.
HOGs features are hard to interpret and are likely to exhibit nonlinear interactions among them.
“HOGs features are hard to interpret and are likely to exhibit nonlinear interactions among them (a stark contrast to the pheasant eggs data where PCA was justified by the linear relationships between variables of the same theme).”
The paper relies on this without support.
Biased training data sets cause erratic behaviour of the predictive model.
“For example, biased training data sets cause erratic behaviour of the predictive model.”
The paper relies on this without support.
Features that are directly relevant to the outcome being predicted tend to make the predictive performance insensitive to the choice of algorithm.
“Features that are directly relevant to the outcome being predicted tend to make the predictive performance insensitive to the choice of algorithm.”
The paper relies on this without support.
ML offers a hypothesis-free approach to model complex data sets where the type of relationship between measured variables is unknown.
“ML offers a hypothesis-free approach to model complex data sets where the type of relationship between measured variables is unknown.”
The paper relies on this without support.
ML algorithms mine for patterns in the data that are best at predicting an outcome.
“ML algorithms mine for patterns in the data that are best at predicting an outcome.”
The paper relies on this without support.
Typically, ML algorithms mine for patterns in observational data, rather than experimental data, where correlation can be mistaken for causation.
“Typically, ML algorithms mine for patterns in observational data, rather than experimental data, where correlation can be mistaken for causation.”
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Applications of machine learning in animal behaviour studies > Clustering
“each cluster should be sufficiently different (maximize intercluster similarity; see Appendix Fig. A1).”
§ Applications of machine learning in animal behaviour studies > Additional information
“maximize the distance between distinct clusters (intercluster distance).”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Applications of machine learning in animal behaviour studies > Clustering
“The data in each group should be similar (minimize intracluster distance)”
§ Applications of machine learning in animal behaviour studies > Additional information
“to minimize the within-group similarity (intracluster distance)”
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · cited 2×
“Both statistical modelling and ML seek to build a mathematical description, a model, of the data and the underlying mechanism it represents; thus inevitably there is substantial overlap between the two (Breiman, 2001b; Friedman, 2001; Zoubin Ghahramani, 2015).”
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016 · cited 2×
“The caret package in R (Kuhn, 2008) and scikit-learn module in Python (Pedregosa et al., 2011) provide a common interface to a wide range of ML algorithms, together with numerous auxiliary functions to perform visualization, cross-validation, model evaluation and more.”
Regression shrinkage and selection via the lasso
Tibshirani, R. (1996) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1996.tb02080.x · Cited by 51,482 · cited 1×
“Examples of these techniques include LASSO (Tibshirani, 1996), where within a linear regression framework coefficients of poor predictors are ‘shrunk’ to zero.”
Histograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584 · cited 1×
“Such higher-order structures were extracted using rotation-invariant histograms of oriented gradients (HOGs; Dalal & Triggs, 2005; Liu et al., 2014; Torney et al., 2016).”
(2008) · Journal of Machine Learning Research · Cited by 33,051
The Elements of Statistical Learning
Hastie, T., Tibshirani, R., & Friedman, J. (2009) · Springer Series in Statistics · doi:10.1007/978-0-387-84858-7 · Cited by 25,970
Data Mining: Practical Machine Learning Tools and Techniques
Witten, I. H., Frank, E., & Hall, M. A. (2011) · Elsevier eBooks · doi:10.1016/c2009-0-19715-5 · Cited by 25,543
Book Review: Pattern Recognition and Machine Learning
Nasrabadi, N. M. (2007) · Journal of Electronic Imaging · doi:10.1117/1.2819119 · Cited by 22,066
Silhouettes: A graphical aid to the interpretation and validation of cluster analysis
Rousseeuw, P. J. (1987) · Journal of Computational and Applied Mathematics · doi:10.1016/0377-0427(87)90125-7 · Cited by 21,392 · cited 2×
“In the section Case Studies, we present two approaches to estimating k, using silhouette width (Rousseeuw, 1987) and the Bayesian information criterion (BIC).”
Building Predictive Models in R Using the caret Package
Kuhn, M. (2008) · Journal of Statistical Software · doi:10.18637/jss.v028.i05 · Cited by 8,863 · cited 1×
“The caret package in R (Kuhn, 2008) and scikit-learn module in Python (Pedregosa et al., 2011) provide a common interface to a wide range of ML algorithms, together with numerous auxiliary functions to perform visualization, cross-validation, model evaluation and more.”
An introduction to variable and feature selection
GuyonIsabelle, & ElisseeffAndré (2003) · Journal of Machine Learning Research · doi:10.5555/944919.944968 · Cited by 8,354
A protocol for data exploration to avoid common statistical problems: Data exploration
Zuur, A. F., Ieno, E. N., & Elphick, C. S. (2010) · Methods in Ecology and Evolution · doi:10.1111/j.2041-210x.2009.00001.x · Cited by 8,228
Random forests for classification in ecology
Cutler, D. R., Edwards, T. C., Beard, K. H., Cutler, A., Hess, K. T., Gibson, J., & Lawler, J. J. (2007) · Ecology · doi:10.1890/07-0539.1 · Cited by 4,950
Chapelle, O., Schölkopf, B., & Zien, A. (2006) · The MIT Press eBooks · doi:10.7551/mitpress/9780262033589.001.0001 · Cited by 4,642
Statistical Modeling: The Two Cultures (with comments and a rejoinder by the author)
Breiman, L. (2001) · Statistical Science · doi:10.1214/ss/1009213726 · Cited by 4,340 · cited 2×
“Both statistical modelling and ML seek to build a mathematical description, a model, of the data and the underlying mechanism it represents; thus inevitably there is substantial overlap between the two (Breiman, 2001b; Friedman, 2001; Zoubin Ghahramani, 2015).”
Equivalence of the Mediation, Confounding and Suppression Effect
MacKinnon, D. P., Krull, J. L., & Lockwood, C. M. (2000) · Prevention Science · doi:10.1023/a:1026595011371 · Cited by 4,188
Model selection in ecology and evolution
Johnson, J. B., & Omland, K. S. (2004) · Trends in Ecology & Evolution · doi:10.1016/j.tree.2003.10.013 · Cited by 3,838 · cited 2×
“Akin to the concept of parsimony in ecological modelling (Johnson & Omland, 2004), feature selection methods select a subset of explanatory variables that are best at prediction.”
(2000) · Applied Physics Letters · doi:10.1162/153244303322753616 · Cited by 3,581 · cited 1×
“These techniques come in three flavours: filter, wrapper and embedded methods (Guyon & Elisseeff, 2003).”
NbClust : An R Package for Determining the Relevant Number of Clusters in a Data Set
Charrad, M., Ghazzali, N., Boiteau, V., & Niknafs, A. (2014) · Journal of Statistical Software · doi:10.18637/jss.v061.i06 · Cited by 3,396
What is principal component analysis?
Ringnér, M. (2008) · Nature Biotechnology · doi:10.1038/nbt0308-303 · Cited by 2,407
Democracy Barometer. Methodology. Version 4.
Merkel, W., Bochsler, D., Bousbah, K., Bühlmann, M., Giebler, H., Hänni, M., Heyne, L., Müller, L., Ruth, S., & Weßels, B. (2004) · Intellectum (Universidad de La Sabana) · doi:10.1007/s13398-014-0173-7.2 · Cited by 2,331
Dimensionality Reduction: A Comparative Review
van der Maaten, L. J. P., Postma, E. O., & van den Herik, H. J. (2009) · Cited by 2,062
Probabilistic machine learning and artificial intelligence
Ghahramani, Z. (2015) · Nature · doi:10.1038/nature14541 · Cited by 1,995 · cited 1×
“Both statistical modelling and ML seek to build a mathematical description, a model, of the data and the underlying mechanism it represents; thus inevitably there is substantial overlap between the two (Breiman, 2001b; Friedman, 2001; Zoubin Ghahramani, 2015).”
Graph-based approach for airborne light detection and ranging segmentation
Vilarino, D. L., Cabaleiro, J. C., Sánchez, J. M., Rivera, F. F., & Pena, T. F. (2017) · Journal of Applied Remote Sensing · doi:10.1117/1.jrs.11.015020 · Cited by 1,760
Terrestrial animal tracking as an eye on life and planet
Kays, R., Crofoot, M. C., Jetz, W., & Wikelski, M. (2015) · Science · doi:10.1126/science.aaa2478 · Cited by 1,638
Nonlinear Dimensionality Reduction
Lee, J. A., & Verleysen, M. (2007) · Springer eBooks · doi:10.1007/978-0-387-39351-3 · Cited by 1,548
GARCÍA-ALONSO, C. R., Pérez, L. M., & Fernández, J. C. F. (2011) · Annals of Operations Research · doi:10.1007/s10479-011-0841-3 · Cited by 1,435
Aquatic animal telemetry: A panoramic window into the underwater world
Hussey, N. E., Kessel, S. T., Aarestrup, K., Cooke, S. J., Cowley, P. D., Fisk, A. T., Harcourt, R. G., Holland, K. N., Iverson, S. J., Kocik, J. F., et al. (2015) · Science · doi:10.1126/science.1255642 · Cited by 1,418 · cited 1×
“Recent technological advances mean that large data sets can be collected on the movement (Hussey et al., 2015; Kays, Crofoot, Jetz, &Wikelski, 2015; Tomkiewicz, Fuller, Kie, & Bates, 2010), fine-scale motion (Brown, Kays, Wikelski, Wilson, & Klimley, 2013), social interactions (Krause et al.,…”
Statistical modeling: The two cultures
Breiman, L. (2001) · Cited by 1,314
Computational Methods of Feature Selection
(2007) · Chapman & Hall/CRC eBooks · doi:10.1201/9781584888796 · Cited by 1,282
Hierarchical group dynamics in pigeon flocks
Nagy, M., Ákos, Z., Biro, D., & Vicsek, T. (2010) · Nature · doi:10.1038/nature08891 · Cited by 1,053
Inferring the structure and dynamics of interactions in schooling fish
Katz, Y., Tunstrøm, K., Ioannou, C. C., Huepe, C., & Couzin, I. D. (2011) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1107583108 · Cited by 927
A procedure for an automated measurement of song similarity
Tchernichovski, O., Nottebohm, F., Ho, C. E., Pesaran, B., & Mitra, P. P. (2000) · Animal Behaviour · doi:10.1006/anbe.1999.1416 · Cited by 749
pavo: an R package for the analysis, visualization and organization of spectral data
Maia, R., Eliason, C. M., Bitton, P., Doucet, S. M., & Shawkey, M. D. (2013) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.12069 · Cited by 675
Observing the unwatchable through acceleration logging of animal behavior
Brown, D. D., Kays, R., Wikelski, M. C., Wilson, R. P., & Klimley, A. P. (2013) · Animal Biotelemetry · doi:10.1186/2050-3385-1-20 · Cited by 659
Blumstein, D. T., Mennill, D. J., Clemins, P. J., Girod, L., Yao, K., Patricelli, G. L., Deppe, J. L., Krakauer, A. H., Clark, C. W., Cortopassi, K. A., et al. (2011) · Journal of Applied Ecology · doi:10.1111/j.1365-2664.2011.01993.x · Cited by 657 · cited 2×
“…Crofoot, Jetz, &Wikelski, 2015; Tomkiewicz, Fuller, Kie, & Bates, 2010), fine-scale motion (Brown, Kays, Wikelski, Wilson, & Klimley, 2013), social interactions (Krause et al., 2013), vocalizations (Blumstein et al., 2011) and physiological responses (Kramer & Kinter, 2003) of individual animals.”
Scheffer, T. (2005) · IGI Global eBooks · doi:10.4018/978-1-59140-557-3.ch192 · Cited by 649
JAABA: Interactive machine learning for automatic annotation of animal behavior
Kabra, M., Robie, A. A., Rivera-Alba, M., Branson, S., & Branson, K. (2013) · Nature Methods · doi:10.1038/nmeth.2281 · Cited by 644 · cited 3×
“ML is used to automate the classification of behaviours/activities (Kabra et al., 2013) and tracking movement trajectories (Dell et al., 2014).”
A survey on filter techniques for feature selection in gene expression microarray analysis
Lazar, C., Taminau, J., Meganck, S., Steenhoff, D., Coletta, A., Molter, C., de Schaetzen, V., Duque, R., Bersini, H., & Nowe, A. (2012) · IEEE/ACM Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2012.33 · Cited by 619 · cited 1×
“The relevance of each variable is assessed using measures such as correlation with the outcome and statistical significance for differences across classes (Lazar et al., 2012).”
How does gene expression clustering work?
D’haeseleer, P. (2005) · Nature Biotechnology · doi:10.1038/nbt1205-1499 · Cited by 529 · cited 2×
“complete or average) need to be defined (D'haeseleer, 2005).”
Global positioning system and associated technologies in animal behaviour and ecological research
Tomkiewicz, S. M., Fuller, M. R., Kie, J. G., & Bates, K. K. (2010) · Philosophical Transactions of the Royal Society B: Biological Sciences · doi:10.1098/rstb.2010.0090 · Cited by 528
Automated image-based tracking and its application in ecology
Dell, A. I., Bender, J. A., Branson, K., Couzin, I. D., de Polavieja, G. G., Noldus, L. P. J. J., Pérez-Escudero, A., Perona, P., Straw, A. D., Wikelski, M., et al. (2014) · Trends in Ecology & Evolution · doi:10.1016/j.tree.2014.05.004 · Cited by 492 · cited 2×
“ML is used to automate the classification of behaviours/activities (Kabra et al., 2013) and tracking movement trajectories (Dell et al., 2014).”
Stoddard, M. C., & Prum, R. O. (2008) · The American Naturalist · doi:10.1086/587526 · Cited by 445 · cited 1×
“PC2 is specifically related to how the eggshell stimulates the cone sensitive to medium wavelengths with a peak sensitivity of 537 nm, and includes both the absolute quantum catch by that cone and the relative cone stimulation, for a given hue, as a function of saturation (Stoddard & Prum, 2008).”
Simple heuristics and rules of thumb: Where psychologists and behavioural biologists might meet
Hutchinson, J. M. C., & Gigerenzer, G. (2005) · Behavioural Processes · doi:10.1016/j.beproc.2005.02.019 · Cited by 404
Intraspecific nest parasitism in birds
YOM‐TOV, Y. (1980) · Biological Reviews · doi:10.1111/j.1469-185x.1980.tb00689.x · Cited by 403 · cited 1×
“Female pheasants may nest communally or lay eggs in multiple nests (Yom-Tov, 1980).”
Hypothesis testing in animal social networks
Croft, D. P., Madden, J. R., Franks, D. W., & James, R. (2011) · Trends in Ecology & Evolution · doi:10.1016/j.tree.2011.05.012 · Cited by 388
Self-citationAutomated monitoring and analysis of social behavior in Drosophila
Dankert, H., Wang, L., Hoopfer, E. D., Anderson, D. J., & Perona, P. (2009) · Nature Methods · doi:10.1038/nmeth.1310 · Cited by 382
Vision-Based Analysis of Small Groups in Pedestrian Crowds
Ge, W., Collins, R. T., & Ruback, R. B. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.176 · Cited by 354
Acoustic sequences in non‐human animals: a tutorial review and prospectus
Kershenbaum, A., Blumstein, D. T., Roch, M. A., Akçay, Ç., Backus, G., Bee, M. A., Bohn, K., Cao, Y., Carter, G., Cäsar, C., et al. (2016) · Biological Reviews · doi:10.1111/brv.12160 · Cited by 337 · cited 1×
“Classification of calls from different species and subspecies is robust (Fagerlund, 2007; Kershenbaum et al., 2016) and permits assessment of community structure (e.g. frogs: Taylor, Watson, Grigg,&McCallum,1996; birds: Brandes, 2008).”
Recognising Human Emotions from Body Movement and Gesture Dynamics
Castellano, G., Villalba, S. D., & Camurri, A. (2007) · Lecture notes in computer science · doi:10.1007/978-3-540-74889-2_7 · Cited by 335
Chesler, E. J., Wilson, S. G., Lariviere, W. R., Rodriguez-Zas, S. L., & Mogil, J. S. (2002) · Neuroscience & Biobehavioral Reviews · doi:10.1016/s0149-7634(02)00103-3 · Cited by 331 · cited 1×
“ML was used in a comparative assessment of welfare across multiple laboratory populations of mice (Chesler et al., 2002) permitting a wide range of potential explanatory factors, each with diverse distribution, to be considered simultaneously as well as the interactions between them.”
Automated classification of bird and amphibian calls using machine learning: A comparison of methods
Acevedo, M. A., Corrada-Bravo, C. J., Corrada-Bravo, H., Villanueva-Rivera, L. J., & Aide, T. M. (2009) · Ecological Informatics · doi:10.1016/j.ecoinf.2009.06.005 · Cited by 317
Dimension Reduction: A Guided Tour
Burges, C. J. C. (2009) · now publishers, Inc. eBooks · doi:10.1561/2200000002 · Cited by 314 · cited 1×
“Reducing the dimensionality of a problem is achieved by mapping the original data to a new feature set, feature extraction (Burges, 2009; van Der Maaten, Postma, & van Den Herik, 2009; Lee & Verleysen, 2007), and/or selecting a subset of attributes, feature selection (Liu & Motoda, 2008).”
Real time facial expression recognition in video using support vector machines
Michel, P., & el Kaliouby, R. (2003) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/958432.958479 · Cited by 311
Automated sound recording and analysis techniques for bird surveys and conservation
Brandes, T. (2008) · Bird Conservation International · doi:10.1017/s0959270908000415 · Cited by 300 · cited 1×
“Classification of calls from different species and subspecies is robust (Fagerlund, 2007; Kershenbaum et al., 2016) and permits assessment of community structure (e.g. frogs: Taylor, Watson, Grigg,&McCallum,1996; birds: Brandes, 2008).”
Bird species recognition using support vector machines
Fagerlund, S. (2007) · EURASIP Journal on Advances in Signal Processing · doi:10.1155/2007/38637 · Cited by 276 · cited 2×
“Classification of calls from different species and subspecies is robust (Fagerlund, 2007; Kershenbaum et al., 2016) and permits assessment of community structure (e.”
Reality mining of animal social systems
Krause, J., Krause, S., Arlinghaus, R., Psorakis, I., Roberts, S., & Rutz, C. (2013) · Trends in Ecology & Evolution · doi:10.1016/j.tree.2013.06.002 · Cited by 269 · cited 1×
“…Crofoot, Jetz, &Wikelski, 2015; Tomkiewicz, Fuller, Kie, & Bates, 2010), fine-scale motion (Brown, Kays, Wikelski, Wilson, & Klimley, 2013), social interactions (Krause et al., 2013), vocalizations (Blumstein et al., 2011) and physiological responses (Kramer & Kinter, 2003) of individual animals.”
Sinusoidal Endothelial Dysfunction Precedes Inflammation and Fibrosis in a Model of NAFLD
Pasarín, M., Mura, V. L., Gracia‐Sancho, J., García‐Calderó, H., Rodrı́guez-Vilarrupla, A., García‐Pagán, J. C., Bosch, J., & Abraldeṣ, J. G. (2012) · PLoS ONE · doi:10.1371/journal.pone.0032785 · Cited by 251
Vision in the peafowl (Aves:Pavo cristatus)
Hart, N. S. (2002) · Journal of Experimental Biology · doi:10.1242/jeb.205.24.3925 · Cited by 239
Network-based diffusion analysis: a new method for detecting social learning
Franz, M., & Nunn, C. L. (2009) · Proceedings of the Royal Society B Biological Sciences · doi:10.1098/rspb.2008.1824 · Cited by 233 · cited 1×
“This characterization of jackdaw social structure can provide a useful tool for examining population level processes, such as epidemiology and social learning (Croft, Madden, Franks, & James, 2011; Franz & Nunn, 2009).”
(2014) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780199679041.001.0001 · Cited by 224
Evaluation and applications of radiotelemetry in small laboratory animals
Kramer, K., & Kinter, L. B. (2003) · Physiological Genomics · doi:10.1152/physiolgenomics.00164.2002 · Cited by 224 · cited 1×
“…Crofoot, Jetz, &Wikelski, 2015; Tomkiewicz, Fuller, Kie, & Bates, 2010), fine-scale motion (Brown, Kays, Wikelski, Wilson, & Klimley, 2013), social interactions (Krause et al., 2013), vocalizations (Blumstein et al., 2011) and physiological responses (Kramer & Kinter, 2003) of individual animals.”
Multichannel Compressive Sensing MRI Using Noiselet Encoding
Pawar, K., Egan, G. F., & Zhang, J. (2015) · PLoS ONE · doi:10.1371/journal.pone.0126386 · Cited by 213
Multimodal emotion recognition from expressive faces, body gestures and speech
Caridakis, G., Castellano, G., Kessous, L., Raouzaiou, A., Malatesta, L., Asteriadis, S., & Karpouzis, K. (2007) · IFIP The International Federation for Information Processing · doi:10.1007/978-0-387-74161-1_41 · Cited by 183 · cited 1×
“ML also permits integration of multiple sets of these cues to further enhance emotion detection (Caridakis et al., 2007).”
Fuzzy overlapping communities in networks
Gregory, S. (2011) · Journal of Statistical Mechanics Theory and Experiment · doi:10.1088/1742-5468/2011/02/p02017 · Cited by 183 · cited 1×
“Alternatively, ML techniques could be deployed to account for such ‘fuzzy overlapping’ (Gregory, 2011), and individuals can have their relative membership of each group determined.”
Inferring social network structure in ecological systems from spatio-temporal data streams
Psorakis, I., Roberts, S. J., Rezek, I., & Sheldon, B. C. (2012) · Journal of The Royal Society Interface · doi:10.1098/rsif.2012.0223 · Cited by 171 · cited 3×
“For illustrative purposes, we focus on 4 weeks of data from 141 individuals visiting a single feeder located near Stithians, Cornwall, U.K. Based on the work of Psorakis et al. (2012), Fig.”
InfluentialWang, Y., Nickel, B. A., Rutishauser, M., Bryce, C. M., Williams, T. M., Elkaim, G., & Wilmers, C. C. (2015) · Movement Ecology · doi:10.1186/s40462-015-0030-0 · Cited by 154 · cited 1×
“…Broell et al., 2013; whale sharks, Rhincodon typus: Gleiss, Wright, Liebsch, Wilson, & Norman, 2013), or those that are hard to follow continuously owing to their speed or covertness (e.g. cheetahs, Acinonyx jubatus: Grünew€alder et al., 2012; pumas, Puma concolor: Wang et al., 2015).”
Rotation-Invariant HOG Descriptors Using Fourier Analysis in Polar and Spherical Coordinates
Liu, K., Skibbe, H., Schmidt, T., Blein, T., Palme, K. J., Brox, T., & Ronneberger, O. (2013) · International Journal of Computer Vision · doi:10.1007/s11263-013-0634-z · Cited by 151 · cited 1×
“Such higher-order structures were extracted using rotation-invariant histograms of oriented gradients (HOGs; Dalal & Triggs, 2005; Liu et al., 2014; Torney et al., 2016).”
Clayton, N. S., & Emery, N. J. (2007) · Current Biology · doi:10.1016/j.cub.2007.05.070 · Cited by 131 · cited 1×
“Jackdaw social structure, as for most corvids, is generally assumed to be characterized by monogamous breeding pairs and prolonged association between parents and offspring following fledging (Clayton & Emery, 2007).”
Shami, M., & Verhelst, W. (2007) · Speech Communication · doi:10.1016/j.specom.2007.01.006 · Cited by 129 · cited 1×
“Such techniques have already been used in humans looking at facial (Michel & El Kaliouby, 2003), physiological (Shi et al., 2010), vocal (Shami & Verhelst, 2007) and gestural (Castellano, Villalba, & Camurri, 2007) cues of emotions.”
Huynh‐Thu, V. A., Saeys, Y., Wehenkel, L. A., & Geurts, P. (2012) · Bioinformatics · doi:10.1093/bioinformatics/bts238 · Cited by 124
Real time facial expression recognition in video using support vector machines
Michel, P., & el Kaliouby, R. (2003) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/958468.958479 · Cited by 114
Gleiss, A. C., Wright, S. R., Liebsch, N., Wilson, R. P., & Norman, B. M. (2013) · Marine Biology · doi:10.1007/s00227-013-2288-3 · Cited by 104
Roughan, J. V., Wright-Williams, S. L., & Flecknell, P. A. (2009) · Laboratory Animals · doi:10.1258/la.2008.007156 · Cited by 101
Grünewälder, S., Broekhuis, F., Macdonald, D. W., et al. (2012) · PLoS ONE · doi:10.1371/journal.pone.0049120 · Cited by 100 · cited 1×
“…Broell et al., 2013; whale sharks, Rhincodon typus: Gleiss, Wright, Liebsch, Wilson, & Norman, 2013), or those that are hard to follow continuously owing to their speed or covertness (e.g. cheetahs, Acinonyx jubatus: Grünew€alder et al., 2012; pumas, Puma concolor: Wang et al., 2015).”
Supervised accelerometry analysis can identify prey capture by penguins at sea
Carroll, G., Slip, D. J., Jonsen, I. D., & Harcourt, R. G. (2014) · Journal of Experimental Biology · doi:10.1242/jeb.113076 · Cited by 96
Inferring social structure from temporal data
Psorakis, I., Voelkl, B., Garroway, C. J., Radersma, R., Aplin, L. M., Crates, R. A., Culina, A., Farine, D. R., Firth, J. A., Hinde, C. A., et al. (2015) · Behavioral Ecology and Sociobiology · doi:10.1007/s00265-015-1906-0 · Cited by 95 · cited 1×
“Co-occurrences in time could be determined by ML clustering methods with individuals in the same foraging event (cluster) considered to have a social affiliation (Psorakis et al., 2015).”
Broell, F., Noda, T., Wright, S. R., Domenici, P., Steffensen, J. F., Auclair, J.-P., & Taggart, C. T. (2012) · Journal of Experimental Biology · doi:10.1242/jeb.077396 · Cited by 94
Nadimi, E. S., Søgaard, H. T., & Bak, T. (2008) · Biosystems Engineering · doi:10.1016/j.biosystemseng.2008.03.003 · Cited by 94
Therrien, J., Pinaud, D., Gauthier, G., Lecomte, N., Bildstein, K. L., & Bêty, J. (2015) · Movement Ecology · doi:10.1186/s40462-015-0028-7 · Cited by 85
McClune, D. W., Marks, N. J., Wilson, R. P., Houghton, J. D. R., Montgomery, I. W., McGowan, N. E., Gormley, E. P., & Scantlebury, M. (2014) · Animal Biotelemetry · doi:10.1186/2050-3385-2-5 · Cited by 85 · cited 1×
“This is especially suitable for organisms that are hard to observe directly, such as nocturnal (badgers, Meles meles: McClune et al., 2014), pelagic (little penguins, Eudyptula minor: Carroll, Slip, Jonsen,&Harcourt, 2014) and aquatic species (great sculpins,Myoxocephalus polyacanthocephallus:…”
Robust Classification Under Sample Selection Bias
Liu, A., & Ziebart, B. D. (2014) · neural information processing systems · Cited by 79
PROTEIN FINGERPRINTING: A NEW TECHNIQUE REVEALS EXTENSIVE CONSPECIFIC BROOD PARASITISM
Andersson, M., & Åhlund, M. (2001) · Ecology · doi:10.1890/0012-9658(2001)082[1433:pfantr]2.0.co;2 · Cited by 76 · cited 1×
“The generalization performance of this model can be estimated by determining the maternity of a subsample of the eggs using protein fingerprinting (Andersson & Åhlund, 2001).”
The role of statistics in the data revolution?
Friedman, J. H. (2001) · International Statistical Review · doi:10.1111/j.1751-5823.2001.tb00474.x · Cited by 64 · cited 1×
“Both statistical modelling and ML seek to build a mathematical description, a model, of the data and the underlying mechanism it represents; thus inevitably there is substantial overlap between the two (Breiman, 2001b; Friedman, 2001; Zoubin Ghahramani, 2015).”
Monitoring Frog Communities: An Application of Machine Learning.
Taylor, A. M., Watson, G. F., Grigg, G. C., et al. (1996) · Cited by 63
Unsupervised bird song syllable classification using evolving neural networks
Ranjard, L., & Ross, H. A. (2008) · The Journal of the Acoustical Society of America · doi:10.1121/1.2903861 · Cited by 55 · cited 1×
“Finer scale discriminations are possible at both the individual level (Cheng, Xie, Lin, & Ji, 2012) and the bird song elements level (Ranjard & Ross, 2008).”
New technology facilitates the study of social networks
Krause, J., Wilson, A. D. M., & Croft, D. P. (2010) · Trends in Ecology & Evolution · doi:10.1016/j.tree.2010.10.004 · Cited by 55
Zhang, J., O’Reilly, K. M., Perry, G. L. W., Taylor, G. A., & Dennis, T. E. (2015) · PLoS ONE · doi:10.1371/journal.pone.0122811 · Cited by 44 · cited 1×
“…we present three popular algorithms of each type, followed by a brief discussion on the problem of estimating the correct number of clusters in the data. k-means Arguably the most widely used partitioning clustering method (e.g. to group behavioural modes in little penguins; Zhang et al., 2015).”
Cheng, J., Xie, B., Lin, C., & Ji, L. (2012) · Bioacoustics · doi:10.1080/09524622.2012.669664 · Cited by 42 · cited 1×
“…methods, they can be used to tackle both regression and classification problems; however, herewe focus on the latter owing to their popularity in animal behaviour studies (e.g. classifying behavioural modes: Kabra et al., 2013; discriminating between different bird call types: Cheng et al., 2012).”
What artificial experts can and cannot do
Dreyfus, H. L., & Dreyfus, S. E. (1992) · AI & Society · doi:10.1007/bf02472766 · Cited by 40 · cited 1×
“We highlight this issue by reciting an (arguably apocryphal) account of one of the first defence applications of ML (Dreyfus & Dreyfus, 1992).”
Kershenbaum, A., Root-Gutteridge, H., Habib, B., Koler-Matznick, J., Mitchell, B., Palacios, V., & Waller, S. (2016) · Behavioural Processes · doi:10.1016/j.beproc.2016.01.006 · Cited by 38 · cited 1×
“Classification of calls from different species and subspecies is robust (Fagerlund, 2007; Kershenbaum et al., 2016) and permits assessment of community structure (e.g. frogs: Taylor, Watson, Grigg,&McCallum,1996; birds: Brandes, 2008).”
Assessing rotation-invariant feature classification for automated wildebeest population counts
Torney, C. J., Dobson, A. P., Borner, F., Lloyd-Jones, D. J., Moyer, D., Maliti, H. T., Mwita, M., Fredrick, H., Borner, M., & Hopcraft, J. G. C. (2016) · PLoS ONE · doi:10.1371/journal.pone.0156342 · Cited by 32 · cited 2×
“If achieved, this will have major implications for conservation as currently the process of detecting and identifying animals within images is the main bottleneck for estimating population sizes from aerial surveys (Torney et al., 2016).”
Self-citationA Data Mining Approach to In Vivo Classification of Psychopharmacological Drugs
Kafkafi, N., Yekutieli, D., & Elmer, G. I. (2008) · Neuropsychopharmacology · doi:10.1038/npp.2008.103 · Cited by 23
The gnu's world: Serengeti wildebeest ecology and life history
(2014) · Choice Reviews Online · doi:10.5860/choice.185406 · Cited by 14
The Role of Statistics in the Data Revolution?
Friedman, J. H. (2001) · International Statistical Review · doi:10.2307/1403524 · Cited by 11
Piles, M., Díez, J., del Coz, J. J., et al. (2013) · Livestock Science · doi:10.1016/j.livsci.2013.03.019 · Cited by 10 · cited 2×
“…an experimental setup) of the underlying process (for example, which of 21 different seminal variables predicted fertilization success in rabbits: Piles et al., 2013); (2) visualization, to highlight the data's structure; (3) prediction, to improve the model's accuracy by removing uninformative…”
Koch, C. (2015) · Scientific American Mind · doi:10.1038/scientificamericanmind1115-24 · Cited by 7 · cited 1×
“Recently, Google released Deep Dream Generator in an attempt to begin to understand how trained models ‘view’ images (Koch, 2015).”
Research works printed but not linked: 3
- Bishop, 2006, Vol. 4
- Broom, 1993, Vol. 30
- Hastie, 2009, Vol. 1
Cited by
Sorted by citations
Leakage and the reproducibility crisis in machine-learning-based science
Kapoor, S., & Narayanan, A. (2023) · Patterns · doi:10.1016/j.patter.2023.100804 · Cited by 1,387
Perspectives in machine learning for wildlife conservation
Tuia, D., Kellenberger, B., Beery, S., Costelloe, B. R., Zuffi, S., Risse, B., Mathis, A., Mathis, M. W., van Langevelde, F., Burghardt, T., et al. (2022) · Nature Communications · doi:10.1038/s41467-022-27980-y · Cited by 740
“A growing body of literature promotes the use of ML in various ecological subfields by educating domain experts about ML approaches (35, 49, 50), their utility in capitalizing on big data (32, 51), and, more recently, their potential for ecolog-”
BackgroundApplications for deep learning in ecology
Christin, S., Hervet, É., & Lecomte, N. (2019) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.13256 · Cited by 724
“Machine learning has already been successfully applied to ecology to perform tasks such as acoustic classification 12 , ecological modelling 13 or studying animal behaviour 14 .”
MethodBenti, N. E., Chaka, M. D., & Semie, A. G. (2023) · Sustainability · doi:10.3390/su15097087 · Cited by 470
“The applications of ML span diverse industries such as healthcare, finance, e-commerce, and others [39–44].”
BackgroundMorota, G., Ventura, R. V., Silva, F. F. E., Koyama, M., & Fernando, S. C. (2018) · Journal of Animal Science · doi:10.1093/jas/sky014 · Cited by 245
“The prediction of imputation accuracy, based uniquely on the relatedness of low-density genotypes to those in a reference dataset using a high-density panel, was investigated by Ventura et al. (2016).”
Method
Metadata
- Authors
- Valletta, J. J., Torney, C., Kings, M., Thornton, A., & Madden, J.
- Affiliations
- University of Exeter (GB)
- Corresponding author
- Valletta, John Joseph
- Venue
- Animal Behaviour
- Publisher
- Elsevier BV
- Published
- 2017-02
- Volume
- 124
- Pages
- 203-220
- ISSN
- 0003-3472 (ISSN-L)
- OpenAlex
- W2581974582
- Cited by
- 505
- References
- 104
- Citations by year
- 2026: 29 · 2025: 57 · 2024: 68 · 2023: 70 · 2022: 84 · 2021: 69 · 2020: 47 · 2019: 48 · 2018: 27 · 2017: 5
- FWCI
- 26.26
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- Animal Behaviour (publishedVersion, cc-by)
- ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam) (acceptedVersion)
- Open Research Exeter (University of Exeter) (acceptedVersion, cc-by)
- Figshare (submittedVersion)
- Funders
- MRC (MR/M003906/1)
- BBSRC David Phillips Fellowship (BB/H021817/1)
- BBSRC SWDTP studentship (630051486)
- ERC consolidator award (616474)
- Topics
- Physical Sciences › Environmental Science › Ecology › Wildlife Ecology and Conservation
- Life Sciences › Agricultural and Biological Sciences › Ecology, Evolution, Behavior and Systematics › Animal Behavior and Reproduction
- Physical Sciences › Computer Science › Information Systems › Data Mining and Machine Learning Applications
- Keywords
- machine learning, behavioural data analysis, unsupervised learning, supervised learning, jackdaw, social networks, aerial imagery, population counting, passive integrated transponders
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-09, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-09 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
