Classifying horse activities with big data using machine learning

10.48129/kjs.splml.19571

Abstract

Using big data-assisted machine learning methods in animal science has received increasing attention in recent years since they extract useful insights from large-scale animal datasets. Especially, animal activity recognition can provide rich insight into their health, welfare, reproduction, and interaction with humans. This paper aims to propose a new solution for this need by building a machine learning model that classifies the actions of horses based on big sensor data. Five horse activities are of interest: walking, standing, grazing, galloping, and trotting. It is the first study that especially compares different ensemble learning algorithms for horse activity recognition in terms of classification accuracy, including bagging trees, extremely randomized trees, random forest, extreme gradient boosting, light gradient boosting, gradient boosting, and categorical boosting. Our study is also original in that it compares the accuracies of per-subject (personalized) and cross-subject (generalized) models. The experimental results showed that our solution achieved very good performance (94.62%) on average on a real-world dataset.