Feature Selection and Comparison of Machine Learning Algorithms in Classification of Grazing and Rumination Behaviour in Sheep
Grazing and ruminating are the most important behaviours for ruminants, as they spend most of their daily time budget performing these. Continuous surveillance of eating behaviour is an important means for monitoring ruminant health, productivity and welfare. However, surveillance performed by human...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/18/10/3532 |
| _version_ | 1818015352710234112 |
|---|---|
| author | Nicola Mansbridge Jurgen Mitsch Nicola Bollard Keith Ellis Giuliana G. Miguel-Pacheco Tania Dottorini Jasmeet Kaler |
| author_facet | Nicola Mansbridge Jurgen Mitsch Nicola Bollard Keith Ellis Giuliana G. Miguel-Pacheco Tania Dottorini Jasmeet Kaler |
| author_sort | Nicola Mansbridge |
| collection | DOAJ |
| description | Grazing and ruminating are the most important behaviours for ruminants, as they spend most of their daily time budget performing these. Continuous surveillance of eating behaviour is an important means for monitoring ruminant health, productivity and welfare. However, surveillance performed by human operators is prone to human variance, time-consuming and costly, especially on animals kept at pasture or free-ranging. The use of sensors to automatically acquire data, and software to classify and identify behaviours, offers significant potential in addressing such issues. In this work, data collected from sheep by means of an accelerometer/gyroscope sensor attached to the ear and collar, sampled at 16 Hz, were used to develop classifiers for grazing and ruminating behaviour using various machine learning algorithms: random forest (RF), support vector machine (SVM), k nearest neighbour (kNN) and adaptive boosting (Adaboost). Multiple features extracted from the signals were ranked on their importance for classification. Several performance indicators were considered when comparing classifiers as a function of algorithm used, sensor localisation and number of used features. Random forest yielded the highest overall accuracies: 92% for collar and 91% for ear. Gyroscope-based features were shown to have the greatest relative importance for eating behaviours. The optimum number of feature characteristics to be incorporated into the model was 39, from both ear and collar data. The findings suggest that one can successfully classify eating behaviours in sheep with very high accuracy; this could be used to develop a device for automatic monitoring of feed intake in the sheep sector to monitor health and welfare. |
| first_indexed | 2024-04-14T06:55:49Z |
| format | Article |
| id | doaj.art-0c491c80df754ce6a77a435f862895f6 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-14T06:55:49Z |
| publishDate | 2018-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-0c491c80df754ce6a77a435f862895f62022-12-22T02:06:53ZengMDPI AGSensors1424-82202018-10-011810353210.3390/s18103532s18103532Feature Selection and Comparison of Machine Learning Algorithms in Classification of Grazing and Rumination Behaviour in SheepNicola Mansbridge0Jurgen Mitsch1Nicola Bollard2Keith Ellis3Giuliana G. Miguel-Pacheco4Tania Dottorini5Jasmeet Kaler6School of Veterinary Medicine and Science, University of Nottingham, Sutton Bonington Campus, Leicestershire LE12 5RD, UKSchool of Computer Science, Jubilee Campus, University of Nottingham, Nottingham NG8 1BB, UKSchool of Veterinary Medicine and Science, University of Nottingham, Sutton Bonington Campus, Leicestershire LE12 5RD, UKInternet of Things Systems Research, Intel Labs, Leixlip W23 CX68, IrelandSchool of Veterinary Medicine and Science, University of Nottingham, Sutton Bonington Campus, Leicestershire LE12 5RD, UKSchool of Veterinary Medicine and Science, University of Nottingham, Sutton Bonington Campus, Leicestershire LE12 5RD, UKSchool of Veterinary Medicine and Science, University of Nottingham, Sutton Bonington Campus, Leicestershire LE12 5RD, UKGrazing and ruminating are the most important behaviours for ruminants, as they spend most of their daily time budget performing these. Continuous surveillance of eating behaviour is an important means for monitoring ruminant health, productivity and welfare. However, surveillance performed by human operators is prone to human variance, time-consuming and costly, especially on animals kept at pasture or free-ranging. The use of sensors to automatically acquire data, and software to classify and identify behaviours, offers significant potential in addressing such issues. In this work, data collected from sheep by means of an accelerometer/gyroscope sensor attached to the ear and collar, sampled at 16 Hz, were used to develop classifiers for grazing and ruminating behaviour using various machine learning algorithms: random forest (RF), support vector machine (SVM), k nearest neighbour (kNN) and adaptive boosting (Adaboost). Multiple features extracted from the signals were ranked on their importance for classification. Several performance indicators were considered when comparing classifiers as a function of algorithm used, sensor localisation and number of used features. Random forest yielded the highest overall accuracies: 92% for collar and 91% for ear. Gyroscope-based features were shown to have the greatest relative importance for eating behaviours. The optimum number of feature characteristics to be incorporated into the model was 39, from both ear and collar data. The findings suggest that one can successfully classify eating behaviours in sheep with very high accuracy; this could be used to develop a device for automatic monitoring of feed intake in the sheep sector to monitor health and welfare.http://www.mdpi.com/1424-8220/18/10/3532sheep behaviourgrazingrumination behaviourclassification algorithmaccelerometer and gyroscopesensormachine learningprecision livestock monitoring |
| spellingShingle | Nicola Mansbridge Jurgen Mitsch Nicola Bollard Keith Ellis Giuliana G. Miguel-Pacheco Tania Dottorini Jasmeet Kaler Feature Selection and Comparison of Machine Learning Algorithms in Classification of Grazing and Rumination Behaviour in Sheep Sensors sheep behaviour grazing rumination behaviour classification algorithm accelerometer and gyroscope sensor machine learning precision livestock monitoring |
| title | Feature Selection and Comparison of Machine Learning Algorithms in Classification of Grazing and Rumination Behaviour in Sheep |
| title_full | Feature Selection and Comparison of Machine Learning Algorithms in Classification of Grazing and Rumination Behaviour in Sheep |
| title_fullStr | Feature Selection and Comparison of Machine Learning Algorithms in Classification of Grazing and Rumination Behaviour in Sheep |
| title_full_unstemmed | Feature Selection and Comparison of Machine Learning Algorithms in Classification of Grazing and Rumination Behaviour in Sheep |
| title_short | Feature Selection and Comparison of Machine Learning Algorithms in Classification of Grazing and Rumination Behaviour in Sheep |
| title_sort | feature selection and comparison of machine learning algorithms in classification of grazing and rumination behaviour in sheep |
| topic | sheep behaviour grazing rumination behaviour classification algorithm accelerometer and gyroscope sensor machine learning precision livestock monitoring |
| url | http://www.mdpi.com/1424-8220/18/10/3532 |
| work_keys_str_mv | AT nicolamansbridge featureselectionandcomparisonofmachinelearningalgorithmsinclassificationofgrazingandruminationbehaviourinsheep AT jurgenmitsch featureselectionandcomparisonofmachinelearningalgorithmsinclassificationofgrazingandruminationbehaviourinsheep AT nicolabollard featureselectionandcomparisonofmachinelearningalgorithmsinclassificationofgrazingandruminationbehaviourinsheep AT keithellis featureselectionandcomparisonofmachinelearningalgorithmsinclassificationofgrazingandruminationbehaviourinsheep AT giulianagmiguelpacheco featureselectionandcomparisonofmachinelearningalgorithmsinclassificationofgrazingandruminationbehaviourinsheep AT taniadottorini featureselectionandcomparisonofmachinelearningalgorithmsinclassificationofgrazingandruminationbehaviourinsheep AT jasmeetkaler featureselectionandcomparisonofmachinelearningalgorithmsinclassificationofgrazingandruminationbehaviourinsheep |