Evaluating Behavior Recognition Pipeline of Laying Hens Using Wearable Inertial Sensors
Open Access
Abstract
Recently, animal welfare has gained worldwide attention. The concept of animal welfare encompasses the physical and mental well-being of animals. Rearing layers in battery cages (conventional cages) may violate their instinctive behaviors and health, resulting in increased animal welfare concerns. Therefore, welfare-oriented rearing systems have been explored to improve their welfare while maintaining productivity. In this study, we explore a behavior recognition system using a wearable inertial sensor to improve the rearing system based on continuous monitoring and quantifying behaviors. Supervised machine learning recognizes a variety of 12 hen behaviors where various parameters in the processing pipeline are considered, including the classifier, sampling frequency, window length, data imbalance handling, and sensor modality. A reference configuration utilizes a multi-layer perceptron as a classifier; feature vectors are calculated from the accelerometer and angular velocity sensor in a 1.28 s window sampled at 100 Hz; the training data are unbalanced. In addition, the accompanying results would allow for a more intensive design of similar systems, estimation of the impact of specific constraints on parameters, and recognition of specific behaviors.Keywords
Funding Information
- Kayamori Foundation of Informational Science Advancement (K32XXV562, FY2020)
- Tokyo University of Agriculture and Technology (K32XXV562, FY2020)
This publication has 46 references indexed in Scilit:
- Machine vision to identify broiler breeder behaviorComputers and Electronics in Agriculture, 2013
- Activity Classification Using the GENEAMedicine & Science in Sports & Exercise, 2012
- Using tri-axial acceleration data to identify behavioral modes of free-ranging animals: general concepts and tools illustrated for griffon vulturesJournal of Experimental Biology, 2012
- Accelerometer‐informed GPS telemetry: Reducing the trade‐off between resolution and longevityWildlife Society Bulletin, 2012
- Multi-factorial investigation of various housing systems for laying hensBritish Poultry Science, 2010
- A survey of cross-validation procedures for model selectionStatistics Surveys, 2010
- Development of a Wireless Body-Mounted Sensor to Monitor Location and Activity of Laying Hens in a Non-Cage Housing SystemTransactions of the ASABE, 2010
- A study of the behavior of several methods for balancing machine learning training dataACM SIGKDD Explorations Newsletter, 2004
- Low incidence of aggression in large flocks of laying hensApplied Animal Behaviour Science, 1997
- Support-vector networksMachine Learning, 1995