Automated behavioral scoring: Do we even need humans?

Abstract

The development of automated behavior scoring technology has been a tremendous boon to the study of social behavior. However, completely outsourcing behavioral analysis to a computer runs the risk of overlooking important nuances, and researchers risk distancing themselves from their very object of study. Here, I make the case that while automating analysis has been valuable, and overautomating analysis is risky, more effort should be spent automating the collection of behavioral data. Continuous automated behavioral observations conducted in situ have the promise to reduce confounding elements of social behavior research, such as handling stress, novel environments, one‐time “snapshot” measures, and experimenter presence. Now that we have the capability to automatically process behavioral observations thanks to machine vision and machine learning, we would do well to leverage the same open‐source ethos to increase the throughput of behavioral observation and collection. Fortunately, several such platforms have recently been developed. Repeated testing in the home environment will produce higher qualities and quantities of data, bringing us closer to realizing the ethological goals of studying animal behavior in a naturalistic context.

NeurostimML: A machine learning model for predicting neurostimulation-induced tissue damage

“…In supervised learning (e.g., k-nearest neighbours or multilayer perceptron), the non-linear relationship between input variables (features) and output targets (labels) is uncovered using training instances, which can be subsequently used for prediction on new instances (testing instances) 29 . Supervised learning algorithms have been widely used in areas of neuroscience and neural engineering research including brain imaging analysis [30][31][32] , neuroinformatics [33][34][35] , and behavioural analysis [36][37][38] .…”

NeurostimML: a machine learning model for predicting neurostimulation-induced tissue damage

“…Subsequently the trained algorithm may be used for prediction on new, untested stimulation parameters (testing instances) [29]. The machine learning approach has been widely used in areas of neuroscience and neural engineering research including brain imaging analysis [30][31][32], neuroinformatics [33][34][35], and behavioral analysis [36][37][38]. Herein, we extend the application of machine learning models to predict electrical stimulation-induced neural tissue damage.…”

Focus on novel approaches: Home-cage monitoring of laboratory mice

“…As working with laboratory animals requires broad expertise beyond basic neuroscience, TEATIME also includes experts in animal welfare, veterinary, and laboratory animal science. Moreover, as recording animal behaviour has advanced through artificial intelligence and machine learning, making routine tasks previously done by the experimenter more automated and sophisticated, it became evident that additional expertise from data science and machine learning was also warranted [9]. TEATIME has therefore grown significantly since its original proposal.…”