Deep Learning-based Cattle Activity Classification Using Joint Time-frequency Data Representation

TL;DR

This paper presents a deep learning approach using joint time-frequency data representation for cattle activity classification, demonstrating improved accuracy and efficiency suitable for embedded devices.

Contribution

It introduces a novel joint time-frequency domain representation of sensor data for cattle activity classification, outperforming existing methods with potential for resource-constrained deployment.

Findings

Joint time-frequency representation outperforms previous classifiers.

Model size and complexity can be reduced with minimal accuracy loss.

Effective for deployment on embedded and IoT devices.

Abstract

Automated cattle activity classification allows herders to continuously monitor the health and well-being of livestock, resulting in increased quality and quantity of beef and dairy products. In this paper, a sequential deep neural network is used to develop a behavioural model and to classify cattle behaviour and activities. The key focus of this paper is the exploration of a joint time-frequency domain representation of the sensor data, which is provided as the input to the neural network classifier. Our exploration is based on a real-world data set with over 3 million samples, collected from sensors with a tri-axial accelerometer, magnetometer and gyroscope, attached to collar tags of 10 dairy cows and collected over a one month period. The key results of this paper is that the joint time-frequency data representation, even when used in conjunction with a relatively basic neural network classifier, can outperform the best cattle activity classifiers reported in the literature. With a more systematic exploration of neural network classifier architectures and hyper-parameters, there is potential for even further improvements. Finally, we demonstrate that the time-frequency domain data representation allows us to efficiently trade-off a large reduction of model size and computational complexity for a very minor reduction in classification accuracy. This shows the potential for our classification approach to run on resource-constrained embedded and IoT devices.