Wanja Rast
YOU?
Author Swipe
Using animal tracking for early detection of mass poisoning events Open
Amidst the sixth mass extinction, some animal groups, such as vultures, the only obligate scavengers among vertebrates, are disappearing at an unprecedented rate. Vulture populations worldwide are declining, primarily due to poisoning. As …
Morphology-based tool for sexing White-backed Vultures in the field Open
We explored the reliability of sex determination based on morphometric measurements in African White-backed Vultures ( Gyps africanus ), a species that has been known to lack sexual dimorphism. Examining 61 adults, we measured 13 morpholog…
Using animal tracking for early detection of mass poisoning events Open
1 Amidst the sixth mass extinction, some groups, such as vultures, the only obligate scavengers among vertebrates, are disappearing at an unprecedented rate. Vulture populations worldwide are largely threatened by poisoning. As many vultur…
Death detector: Using vultures as sentinels to detect carcasses by combining bio‐logging and machine learning Open
Bio‐logging technologies allow scientists to remotely monitor animal behaviour and the environment. In this study, we used the combination of natural abilities of African white‐backed vultures Gyps africanus and state‐of‐the‐art bio‐loggin…
Advantages and disadvantages of using social information for carcass detection–A case study using white-backed vultures Open
Utilizing social information during foraging, wherein individuals observe how others interact with their environment rather than relying solely on individually acquired information, is a widely used strategy across the animal kingdom. Neve…
Wildlife Species Classification on the Edge: A Deep Learning Perspective Open
600
Using Machine Learning for Remote Behaviour Classification—Verifying Acceleration Data to Infer Feeding Events in Free-Ranging Cheetahs Open
Behavioural studies of elusive wildlife species are challenging but important when they are threatened and involved in human-wildlife conflicts. Accelerometers (ACCs) and supervised machine learning algorithms (MLAs) are valuable tools to …
Urban Hedgehog Behavioural Responses to Temporary Habitat Disturbance versus Permanent Fragmentation Open
Anthropogenic activities can result in both transient and permanent changes in the environment. We studied spatial and temporal behavioural responses of European hedgehogs (Erinaceus europaeus) to a transient (open-air music festival) and …
Confusion matrix for the support vector machine (SVM) validation. Open
Columns show expected behaviours known from observation, rows show behaviours assigned by the SVM. Values on the diagonal (bold) represent behaviours assigned correctly. All values off the diagonal are incorrect assignments that show which…
Confusion matrix for the random forest (RF) validation. Open
Columns show expected behaviours known from observation, rows show behaviours assigned by the RF. Values on the diagonal (bold) represent behaviours assigned correctly. All values off the diagonal are incorrect assignments that show which …
Ethogram for the captive foxes—Modified from [16]. Open
Behavioural observations were restricted to the listed categories. Each burst could only have one behaviour assigned. Observations not matching any description as well as observations of more than one behaviour per burst were excluded from…
Confusion matrix for the artificial neural network (ANN) validation. Open
Columns show expected behaviours known from observation, rows show behaviours assigned by the ANN. Values on the diagonal (bold) represent behaviours assigned correctly. All values off the diagonal are incorrect assignments that show which…
List of all predictors and how they were calculated. Open
References refer to when the respective predictor was first introduced in the context of behaviour prediction. All predictors except the Fast Fourier Transformation can be considered summary statistics because they result in a single numbe…
Proportion of data used for the speed analysis. Open
Most of the times GPS and acceleration data were not recorded simultaneously. For the speed analysis we considered only acceleration data that was recorded within 10 seconds of a GPS recording. (DOCX)
Machine learning goes wild: Using data from captive individuals to infer wildlife behaviours Open
1. Remotely tracking distinct behaviours of animals using acceleration data and machine learning has been carried out successfully in several species in captive settings. In order to study the ecology of animals in natural habitats, such b…
Machine learning goes wild: Using data from captive individuals to infer wildlife behaviour Open
Remotely tracking distinct behaviours of animals using acceleration data and machine learning has been carried out successfully in several species in captive settings. In order to study the ecology of animals in natural habitats, such beha…
Music Festival Makes Hedgehogs Move: How Individuals Cope Behaviorally in Response to Human-Induced Stressors Open
Understanding the impact of human activities on wildlife behavior and fitness can improve their sustainability. In a pilot study, we wanted to identify behavioral responses to anthropogenic stress in an urban species during a semi-experime…