Data that are collected from various heterogeneous internet of things (IoT) devices.
Published in Chapter:
Animal Activity Recognition From Sensor Data Using Ensemble Learning
Derya Birant (Dokuz Eylul University, Turkey) and Kadircan Yalniz (Dokuz Eylul University, Turkey)
Copyright: © 2022
|Pages: 16
DOI: 10.4018/978-1-7998-4186-9.ch009
Abstract
Animal activity recognition is an important task to monitor the behavior of animals to know their health condition and psychological state. To provide a solution for this need, this study is aimed to build an internet of things (IoT) system that predicts the activities of animals based on sensor data obtained from embedded devices attached to animals. This chapter especially considers the problem of prediction of goat activity using three types of sensors: accelerometer, gyroscope, and magnetometer. Five possible goat activities are of interest, including stationary, grazing, walking, trotting, and running. The utility of five ensemble learning methods was investigated, including random forest, extremely randomized trees, bagging trees, gradient boosting, and extreme gradient boosting. The results showed that all these methods achieved good performance (>94%) on the datasets. Therefore, this study can be successfully used by professionals such as farmers, vets, and animal behaviorists where animal tracking may be crucial.