Energy-aware feature and classifier for behaviour recognition of laying hens in an aviary system
Long-term monitoring of animal behaviours requires energy-aware features and classifiers to support onboard classification. However, limited studies have been conducted on the behaviour recognition of laying hens, especially in aviary systems. The objective of this study was to configure key paramet...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Animal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1751731124003148 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832595375898230784 |
|---|---|
| author | X. Yang Q. Hu L. Nie C. Wang |
| author_facet | X. Yang Q. Hu L. Nie C. Wang |
| author_sort | X. Yang |
| collection | DOAJ |
| description | Long-term monitoring of animal behaviours requires energy-aware features and classifiers to support onboard classification. However, limited studies have been conducted on the behaviour recognition of laying hens, especially in aviary systems. The objective of this study was to configure key parameters for developing onboard behaviour monitoring techniques of aviary laying hens, including proper sliding window length, energy-aware feature, and lightweight classifier. A total of 19 Jingfen No.6 laying hens were reared in an aviary system from day 30 to day 70. Six light-weight accelerometers were attached to the back of birds for behaviour monitoring with a sampling frequency of 20 Hz. Laying hen behaviours were categorised into four groups, including static behaviour (resting and standing), ingestive behaviour (feeding and drinking), walking, and jumping. Two different window lengths (0.5 and 1 s) were tested. The SD of each axial acceleration was considered the only classification feature. The results indicated that performing denoise procedure before feature extraction can improve the classification accuracy by 10–20%. The 1-s window length yielded better accuracy than the 0.5-s window, especially for ingestive and walking behaviours. Classification models based on X-axis accelerations were better than those of Y- and Z-axis with the recognition accuracies of static, ingestive, walking, and jumping behaviours being 97.4, 89.6, 95.7, and 98.5%, respectively. The study might provide insights into developing onboard behaviour recognition algorithms for laying hens. |
| format | Article |
| id | doaj-art-13a0744800d240b49f9a1800c33e4468 |
| institution | Kabale University |
| issn | 1751-7311 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Animal |
| spelling | doaj-art-13a0744800d240b49f9a1800c33e44682025-01-19T06:24:47ZengElsevierAnimal1751-73112025-01-01191101377Energy-aware feature and classifier for behaviour recognition of laying hens in an aviary systemX. Yang0Q. Hu1L. Nie2C. Wang3College of Water Resources and Civil Engineering, China Agricultural University, Beijing 100083, China; Key Laboratory of Agricultural Engineering in Structure and Environment, Ministry of Agriculture and Rural Affairs, Beijing 100083, ChinaCollege of Water Resources and Civil Engineering, China Agricultural University, Beijing 100083, China; Key Laboratory of Agricultural Engineering in Structure and Environment, Ministry of Agriculture and Rural Affairs, Beijing 100083, ChinaCollege of Animal Science, Ningxia University, Yinchuan 750021, ChinaCollege of Water Resources and Civil Engineering, China Agricultural University, Beijing 100083, China; Key Laboratory of Agricultural Engineering in Structure and Environment, Ministry of Agriculture and Rural Affairs, Beijing 100083, China; Corresponding author.Long-term monitoring of animal behaviours requires energy-aware features and classifiers to support onboard classification. However, limited studies have been conducted on the behaviour recognition of laying hens, especially in aviary systems. The objective of this study was to configure key parameters for developing onboard behaviour monitoring techniques of aviary laying hens, including proper sliding window length, energy-aware feature, and lightweight classifier. A total of 19 Jingfen No.6 laying hens were reared in an aviary system from day 30 to day 70. Six light-weight accelerometers were attached to the back of birds for behaviour monitoring with a sampling frequency of 20 Hz. Laying hen behaviours were categorised into four groups, including static behaviour (resting and standing), ingestive behaviour (feeding and drinking), walking, and jumping. Two different window lengths (0.5 and 1 s) were tested. The SD of each axial acceleration was considered the only classification feature. The results indicated that performing denoise procedure before feature extraction can improve the classification accuracy by 10–20%. The 1-s window length yielded better accuracy than the 0.5-s window, especially for ingestive and walking behaviours. Classification models based on X-axis accelerations were better than those of Y- and Z-axis with the recognition accuracies of static, ingestive, walking, and jumping behaviours being 97.4, 89.6, 95.7, and 98.5%, respectively. The study might provide insights into developing onboard behaviour recognition algorithms for laying hens.http://www.sciencedirect.com/science/article/pii/S1751731124003148AccelerometerCage-freeMachine learningPoultrySpatial behaviour |
| spellingShingle | X. Yang Q. Hu L. Nie C. Wang Energy-aware feature and classifier for behaviour recognition of laying hens in an aviary system Animal Accelerometer Cage-free Machine learning Poultry Spatial behaviour |
| title | Energy-aware feature and classifier for behaviour recognition of laying hens in an aviary system |
| title_full | Energy-aware feature and classifier for behaviour recognition of laying hens in an aviary system |
| title_fullStr | Energy-aware feature and classifier for behaviour recognition of laying hens in an aviary system |
| title_full_unstemmed | Energy-aware feature and classifier for behaviour recognition of laying hens in an aviary system |
| title_short | Energy-aware feature and classifier for behaviour recognition of laying hens in an aviary system |
| title_sort | energy aware feature and classifier for behaviour recognition of laying hens in an aviary system |
| topic | Accelerometer Cage-free Machine learning Poultry Spatial behaviour |
| url | http://www.sciencedirect.com/science/article/pii/S1751731124003148 |
| work_keys_str_mv | AT xyang energyawarefeatureandclassifierforbehaviourrecognitionoflayinghensinanaviarysystem AT qhu energyawarefeatureandclassifierforbehaviourrecognitionoflayinghensinanaviarysystem AT lnie energyawarefeatureandclassifierforbehaviourrecognitionoflayinghensinanaviarysystem AT cwang energyawarefeatureandclassifierforbehaviourrecognitionoflayinghensinanaviarysystem |