Applying Deep Learning Models to Mouse Behavior Recognition

Abstract

In many animal-related studies, a high-performance animal behavior recognition system can help researchers reduce or get rid of the limitation of human assessments and make the experiments easier to reproduce. Recently, although deep learning models are holding state-of-the-art performances in human action recognition tasks, these models are not well-studied in applying to animal behavior recognition tasks. One reason is the lack of extensive datasets which are required to train these deep models for good performances. In this research, we investigated two current state-of-the-art deep learning models in human action recognition tasks, the I3D model and the R(2 + 1)D model, in solving a mouse behavior recognition task. We compared their performances with other models from previous researches and the results showed that the deep learning models that pre-trained using human action datasets then fine-tuned using the mouse behavior dataset can outperform other models from previous researches. It also shows promises of applying these deep learning models to other animal behavior recognition tasks without any significant modification in the models' architecture, all we need to do is collecting proper datasets for the tasks and fine-tuning the pre-trained models using the collected data.

Big behavior: challenges and opportunities in a new era of deep behavior profiling

“…In most cases the ground truth is not perfectly defined and contains a lot of variability. Additionally, there is currently a lack of extensive, well-annotated data-sets, and many studies use older labeled data from previous studies [52][53][54]. A potential approach could be to create extensive, well-annotated labeling sets, which include only examples where all raters agree with one another, however these would omit difficult cases from the training set and thus limit the sensitivity of the classifier.…”

“…However, this was only the case when heavy data augmentation was applied and the performance dropped a lot when videos from different set-ups/animals were used. A third study [ 54 ] showed a slight increase when using 3D-CNN models pre-trained to recognize human behaviors and retrained with mouse homecage behavior data from a previous study [ 27 ]. However, in this study only 12 similar side-view recordings from the same set-up are used, so it cannot be assessed how well it would perform with a different set-up.…”

Communication Emitter Motion Behavior’s Cognition Based on Deep Reinforcement Learning

“…Behavior modelling and activity interpretation are of increasing interest in the information society [5]. The research on behavior cognition mainly focuses on computer science and network and social psychology, and the research targets mainly include human [6], animal [7], traffic [8], [9] and robot [10]. The Google team proposed in 2006 that the motion behavior cognition system should be composed of four modules of ''sensor-identification-transformation-controlled system (SITR)'' [11].…”

An emergency response system created to combat injuries during physical education training in a university using deep learning

“…When an emergency situation arises, decision-making can be based on the gathered data which can be sometimes incomplete or irrelevant. An emergency response system created for the police station helps them to identify the terrorist outbreaks and criminal offenses in advance (Nguyen et al, 2019). By means of combining the different…”