On the Benefits of Deep Convolutional Neural Networks on Animal Activity Recognition
Authors:
- 14 October 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 83-88
Abstract
Monitoring the behavior of animals (e.g., eating habits) can lead to conclusions regarding animal's welfare. To achieve this, remote monitoring of animal activity with the aid of inertial sensors and use of machine learning algorithms over the collected data can be used. However, these algorithms rely on handcrafted features extracted by statistical or heuristic functions over raw motion data. To this purpose, we employ deep Convolutional Neural Networks (ConvNets) for activity recognition of livestock animals, such as goats and horses. We investigate the potential gains of ConvNets compared with other machine learning algorithms of the literature, which are about 12.5% greater accuracy and more than 7% higher F1-score. Moreover, we designate the advantages of late sensor fusion (2D convolution) and also show that an increase on the number of filters on each layer does not necessarily lead to a greater classification accuracy. To this end, we benchmark various ConvNet architectures and demonstrate the role of hyperparameter tuning to optimize the overall accuracy. To the best of our knowledge, ConvNets are employed for animal activity recognition here for the first time.Keywords
Funding Information
- European Union
This publication has 20 references indexed in Scilit:
- Embedded neural network for real-time animal behavior classificationNeurocomputing, 2018
- An Overview of Automatic Behaviour Classification for Animal-Borne Sensor Applications in South Africa2017
- Generic online animal activity recognition on collar tags2017
- Automated Classification of a Calf’s Feeding State Based on Data Collected by Active Sensors with 3D-Accelerometer2017
- Behavior classification of cows fitted with motion collars: Decomposing multi-class classification into a set of binary problemsComputers and Electronics in Agriculture, 2016
- Accelerometer based solution for precision livestock farming: geolocation enhancement and animal activity identificationIOP Conference Series: Materials Science and Engineering, 2016
- Dynamic cattle behavioural classification using supervised ensemble classifiersComputers and Electronics in Agriculture, 2015
- Characterising the spatial and temporal activities of free-ranging cows from GPS dataThe Rangeland Journal, 2012
- Monitoring and classifying animal behavior using ZigBee-based mobile ad hoc wireless sensor networks and artificial neural networksComputers and Electronics in Agriculture, 2012
- Cow behaviour pattern recognition using a three-dimensional accelerometer and support vector machinesApplied Animal Behaviour Science, 2009