Classifying active and inactive states of growing rabbits from accelerometer data using machine learning algorithms

TL;DR

This paper demonstrates how accelerometer data combined with machine learning can accurately classify active and inactive states in growing rabbits, aiding in animal behavior monitoring and management.

Contribution

It introduces a novel approach using wearable accelerometers and machine learning to classify rabbit activity states, enhancing behavioral analysis methods.

Findings

High accuracy in classifying rabbit activity states

Effective use of accelerometer data for behavior monitoring

Potential for improved animal management practices

Abstract

This study explores how wearable accelerometers, small devices that measure acceleration, can help monitor the activity of growing rabbits. We equipped 16 rabbits with these devices and filmed them for two weeks. By watching the videos and using a special software we figure out what the rabbits were doing -- things like lying down, eating, moving around, and more. These activitties were grouped into two states: active or inactive. Then, this information along acceleration data was used to teach a computer program to recognize when the rabbits were active or not. This technology offers a reliable way to understand rabbit behavior, which could lead to better management practices in animal production.