Detecting Unknown Behaviors by Pre-defined Behaviours: An Bayesian Non-parametric Approach

TL;DR

This paper introduces a semi-supervised Bayesian non-parametric model that effectively detects and labels both predefined and undefined mouse behaviors, improving analysis accuracy and reducing manual effort.

Contribution

It proposes the SsIGMM model, a novel approach that incorporates labeled and unlabeled data to identify unknown behaviors using a mixture of Gaussians.

Findings

SsIGMM outperforms existing methods in behavior segmentation and labeling.

The model effectively detects undefined behaviors.

Experimental results confirm the model's superiority.

Abstract

An automatic mouse behavior recognition system can considerably reduce the workload of experimenters and facilitate the analysis process. Typically, supervised approaches, unsupervised approaches and semi-supervised approaches are applied for behavior recognition purpose under a setting which has all of predefined behaviors. In the real situation, however, as mouses can show various types of behaviors, besides the predefined behaviors that we want to analyze, there are many undefined behaviors existing. Both supervised approaches and conventional semi-supervised approaches cannot identify these undefined behaviors. Though unsupervised approaches can detect these undefined behaviors, a post-hoc labeling is needed. In this paper, we propose a semi-supervised infinite Gaussian mixture model (SsIGMM), to incorporate both labeled and unlabelled information in learning process while considering undefined behaviors. It also generates the distribution of the predefined and undefined behaviors by mixture Gaussians, which can be used for further analysis. In our experiments, we confirmed the superiority of SsIGMM for segmenting and labelling mouse-behavior videos.