Clustering for Automated Exploratory Pattern Discovery in Animal Behavioral Data

Abstract

Traditional methods of data analysis in animal behavior research are usually based on measuring behavior by manually coding a set of chosen behavioral parameters, which is naturally prone to human bias and error, and is also a tedious labor-intensive task. Machine learning techniques are increasingly applied to support researchers in this field, mostly in a supervised manner: for tracking animals, detecting land marks or recognizing actions. Unsupervised methods are increasingly used, but are under-explored in the context of behavior studies and applied contexts such as behavioral testing of dogs. This study explores the potential of unsupervised approaches such as clustering for the automated discovery of patterns in data which have potential behavioral meaning. We aim to demonstrate that such patterns can be useful at exploratory stages of data analysis before forming specific hypotheses. To this end, we propose a concrete method for grouping video trials of behavioral testing of animal individuals into clusters using a set of potentially relevant features. Using an example of protocol for testing in a “Stranger Test”, we compare the discovered clusters against the C-BARQ owner-based questionnaire, which is commonly used for dog behavioral trait assessment, showing that our method separated well between dogs with higher C-BARQ scores for stranger fear, and those with lower scores. This demonstrates potential use of such clustering approach for exploration prior to hypothesis forming and testing in behavioral research.

Digitally-enhanced dog behavioral testing

“…The BLYZER system is a self-developed platform that aims to provide a flexible automated behavior analysis which has been applied in several studies for analyzing dog behavior 37 – 40 . A similar approach was implemented on a smaller portion of the dataset used in this study in 41 , however in contrast to our approach here, features chosen manually were used for clustering.…”

SUBTLE: An unsupervised platform with temporal link embedding that maps animal behavior

“…As a next step, we identified unique stereotyped actions (e.g., lifting, stretching, and balancing) as behavioral states (subclusters) (14) which can be used as building blocks for behavioral repertoires (superclusters) that reflect sequential transitions of behavioral states (e.g., rearing) (18). Several options are available to support this stage, including the Watershed algorithm (14), ݇-Means clustering (34), Gaussian Mixture (35), and HDBSCAN (9). However, these algorithms require prior knowledge or assumptions about the embedding space, such as a probability density function, a predetermined number of clusters, or a threshold density.…”

Digitally-Enhanced Dog Behavioral Testing: Getting Help from the Machine

“…The BLYZER system is a self-developed platform that aims to provide a flexible automated behavior analysis which has been applied in several studies for analyzing dog behavior [31][32][33][34] . A similar approach was implemented on a smaller portion of the dataset used in this study in 35 , however in contrast to our approach here, features chosen manually were used for clustering.…”