Characterising Free-Range Layer Flocks Using Unsupervised Cluster Analysis
Abstract
:Simple Summary
Abstract
1. Introduction
2. Materials and Methods
2.1. Ethical Statement
2.2. Study Population and RFID Monitoring of Aviary and Range Usage
2.3. Primary Data Collection
2.4. Cluster Optimisation
2.5. Identifying Subpopulations Using K-Means and Agglomerative Clustering
2.6. Visualisation of the Clusters
2.7. Daily Feeder, Nest Box, and Range Usage
2.8. Coefficient of Variation
2.9. Bodyweight and Egg Follicle Score
3. Results
3.1. K-Means and Agglomerative Cluster Characteristics
3.2. The Agreement between the K-Means and Agglomerative Subpopulations
3.3. Visualisation of the Clusters
3.4. Daily Feeder Usage, Nest Box and Range Access during Different Laying Periods
3.5. Individual Variation in Daily Feeder Usage, Nest Box and Range Access
3.6. Bodyweight Distributions of Each Cluster
3.7. Egg Follicles
4. Discussion
5. Conclusions
Author Contributions
Funding
Acknowledgments
Conflicts of Interest
References
- Buijs, S.; Booth, F.; Richards, G.; McGaughey, L.; Nicol, C.; Edgar, J.; Tarlton, J. Behavioural and physiological responses of laying hens to automated monitoring equipment. Appl. Anim. Behav. Sci. 2018, 199, 17–23. [Google Scholar] [CrossRef] [PubMed]
- Siegford, J.; Berezowski, J.; Biswas, S.K.; Daigle, C.L.; Gebhardt-Henrich, S.G.; Hernandez, C.; Thurner, S.; Toscano, M.J. Assessing Activity and Location of Individual Laying Hens in Large Groups Using Modern Technology. Animals 2016, 6, 10. [Google Scholar] [CrossRef] [PubMed]
- Gebhardt-Henrich, S.G.; Toscano, M.J.; Fröhlich, E.K. Use of outdoor ranges by laying hens in different sized flocks. Appl. Anim. Behav. Sci. 2014, 155, 74–81. [Google Scholar] [CrossRef] [Green Version]
- Larsen, H.; Cronin, G.; Gebhardt-Henrich, S.G.; Smith, C.; Hemsworth, P.H.; Rault, J.-L. Individual Ranging Behaviour Patterns in Commercial Free-Range Layers as Observed through RFID Tracking. Animals 2017, 7, 21. [Google Scholar] [CrossRef] [PubMed]
- Zuidhof, M.; Fedorak, M.V.; Ouellette, C.A.; Wenger, I.I. Precision feeding: Innovative management of broiler breeder feed intake and flock uniformity. Poult. Sci. 2017, 96, 2254–2263. [Google Scholar] [CrossRef]
- Sibanda, T.Z.; Walkden-Brown, S.W.; Kolakshyapati, M.; Dawson, B.; Schneider, D.; Welch, M.; Iqbal, Z.; Cohen-Barnhouse, A.; Morgan, N.K.; Boshoff, J.; et al. Flock use of the range is associated with the use of different components of a multi-tier aviary system in commercial free-range laying hens. Br. Poult. Sci. 2019, 61, 97–106. [Google Scholar] [CrossRef]
- Feiyang, Z.; Yueming, H.; Liancheng, C.; Lihong, G.; Wenjie, D.; Lu, W. Monitoring behavior of poultry based on RFID radio frequency network. Int. J. Agric. Biol. Eng. 2016, 9, 139–147. [Google Scholar]
- Singh, M.; Cowieson, A.J. Range use and pasture consumption in free-range poultry production. Anim. Prod. Sci. 2013, 53, 1202–1208. [Google Scholar] [CrossRef]
- Wang, K.; Liu, K.; Xin, H.; Chai, L.; Wang, Y.; Fei, T.; Oliveira, J.; Pan, J.; Ying, Y. An RFID-Based Automated Individual Perching Monitoring System for Group-Housed Poultry. Trans. ASABE 2019, 62, 695–704. [Google Scholar] [CrossRef]
- Li, L.; Zhao, Y.; Oliveira, J.; Verhoijsen, W.; Liu, K.; Xin, H. A UHF RFID system for studying individual feeding and nesting behaviour of group-housed laying hens. ASABE 2017, 60, 1337–1347. [Google Scholar] [CrossRef] [Green Version]
- Han, J.; Jian, P.; Micheline, K. Data Mining: Concepts and Techniques; Elsevier: Amsterdam, The Netherlands, 2011; pp. 443–496. [Google Scholar]
- Barrett, J.; Rayner, A.C.; Gill, R.; Willings, T.H.; Bright, A. Smothering in UK free-range flocks. Part 1: Incidence, location, timing and management. Vet. Rec. 2014, 175, 19. [Google Scholar] [CrossRef] [PubMed]
- Australian Eggs: Annual-Report 2018/19. Available online: https://www.australianeggs.org.au/who-we-are/annual-reports/#item-1058 (accessed on 7 February 2020).
- Asher, L.; Collins, L.M.; Pfeiffer, D.U.; Nicol, C.J. Flocking for food or flock mates? Appl. Anim. Behav. Sci. 2013, 147, 94–103. [Google Scholar] [CrossRef]
- Rands, S.A.; Cowlishaw, G.; Pettifor, R.A.; Rowcliffe, J.M.; Johnstone, R.A. Spontaneous emergence of leaders and followers in foraging pairs. Nature 2003, 423, 432–434. [Google Scholar] [CrossRef] [PubMed]
- Conradt, L.; Krause, J.; Couzin, I.D.; Roper, T.J. “Leading According to Need” in Self-Organizing Groups. Am. Nat. 2009, 173, 304–312. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Harcourt, J.L.; Ang, T.Z.; Sweetman, G.; Johnstone, R.A.; Manica, A. Social Feedback and the Emergence of Leaders and Followers. Curr. Boil. 2009, 19, 248–252. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Sumpter, D.J.; Pratt, S.C. Quorum responses and consensus decision making. Philos. Trans. R. Soc. B Boil. Sci. 2008, 364, 743–753. [Google Scholar] [CrossRef]
- Caliński, T.; Harabasz, J. A dendrite method for cluster analysis. Commun. Stat. Theory Methods 1974, 3, 1–27. [Google Scholar] [CrossRef]
- Chikumbo, O.; Granville, V. Optimal Clustering and Cluster Identity in Understanding High-Dimensional Data Spaces with Tightly Distributed Points. Mach. Learn. Knowl. Extr. 2019, 1, 42. [Google Scholar] [CrossRef] [Green Version]
- Maimon, O.; Lior, R. (Eds.) Data Mining and Knowledge Discovery Handbook; Springer: Boston, MA, USA, 2005; pp. 297–432. [Google Scholar]
- Van der Maaten, L.J.P.; Hinton, G.E. Visualizing high-dimensional data using t-SNE. J. Mach. Learn. Res. 2008, 9, 2579–2605. [Google Scholar]
- Anonymous. The R Project for Statistical Computing. Available online: http://www.r-project.org/ (accessed on 13 February 2012).
- Kassambara, A. ’ggplot2’ Based Publication Ready Plots. Cran, 2020. Available online: https://rpkgs.datanovia.com/ggpubr/ (accessed on 14 May 2020).
- Sibanda, T.Z.; Kolakshyapati, M.; Walkden-Brown, S.W.; Vilela, J.; Courtice, J.M.; Ruhnke, I. Body weight sub-populations are associated with significant different welfare, health and egg production status in Australian commercial free-range laying hens in an aviary system. Eur. Poultry Sci. 2020, 84. [Google Scholar] [CrossRef]
- Sibanda, T.Z.; Kolakshyapati, M.; Welch, M.; Schneider, D.; Boshoff, J.; Ruhnke, I. Managing free-range laying hens—Part A: Frequent and non-frequent range users differ in laying performance but not egg quality. Animals 2020, (in press). [Google Scholar]
- Lewis, P.; Gous, R. Responses of poultry to ultraviolet radiation. Worlds Poult. Sci. J. 2009, 65, 499–510. [Google Scholar] [CrossRef]
- Stratmann, A.; Frohlich, E.K.F.; Gebhardt-Henrich, S.; Harlander-Matauschek, A.; Wurbel, H.; Toscano, M.J. Modification of aviary design reduces the incidence of falls, collisions and keel bone damage in laying hens. Appl. Anim. Behav. Sci. 2015, 165, 112–123. [Google Scholar] [CrossRef]
- Rufener, C.; Berezowski, J.; Sousa, F.M.; Abreu, Y.; Asher, L.; Toscano, M.J. Finding hens in a haystack: Consistency of movement patterns within and across individual laying hens maintained in large groups. Sci. Rep. 2018, 8, 12303. [Google Scholar] [CrossRef]
- Matthews, W.A.; Sumner, D.A. Effects of housing system on the costs of commercial egg production. Poult. Sci. 2015, 94, 552–557. [Google Scholar] [CrossRef]
- Michel, V.; Huonnic, D. Spring meeting of the WPSA French Branch. Br. Poult. Sci. 2003, 44, 775–776. [Google Scholar] [CrossRef]
- De Reu, K.; Messens, W.; Heyndrickx, M.; Rodenburg, T.; Uyttendaele, M.; Herman, L. Bacterial contamination of table eggs and the influence of housing systems. Worlds Poult. Sci. J. 2008, 64, 5–19. [Google Scholar] [CrossRef] [Green Version]
- Jones, D.R.; Cox, N.A.; Guard, J.; Fedorka-Cray, P.J.; Buhr, R.J.; Gast, R.; Abdo, Z.; Rigsby, L.L.; Plumblee, J.R.; Karcher, D.M.; et al. Microbiological impact of three commercial laying hen housing systems. Poult. Sci. 2015, 94, 544–551. [Google Scholar] [CrossRef]
- Ali, A.B.A.; Campbell, D.L.M.; Karcher, D.M.; Siegford, J. Influence of genetic strain and access to litter on spatial distribution of 4 strains of laying hens in an aviary system. Poult. Sci. 2016, 95, 2489–2502. [Google Scholar] [CrossRef]
- D’Eath, R.B.; Keeling, L.J. Social discrimination and aggression by laying hens in large groups: From peck orders to social tolerance. Appl. Anim. Behav. Sci. 2003, 84, 197–212. [Google Scholar] [CrossRef]
- Oden, K.; Keeling, L.; Algers, B. Behaviour of laying hens in two types of aviary systems on 25 commercial farms in Sweden. Br. Poult. Sci. 2002, 43, 169–181. [Google Scholar] [CrossRef] [PubMed]
- Banks, E.M.; Wood-Gush, D.G.; Hughes, B.O.; Mankovich, N.J. Social rank and priority of access to resources in domestic fowl. Behav. Process. 1979, 4, 197–209. [Google Scholar] [CrossRef]
- Cooper, J.; Albentosa, M.J. Behavioural Priorities of Laying Hens. Avian Poult. Boil. Rev. 2003, 14, 127–149. [Google Scholar] [CrossRef]
- Rufener, C.; Abreu, Y.; Asher, L.; Berezowski, J.; Sousa, F.M.; Stratmann, A.; Toscano, M.J. Keel bone fractures are associated with individual mobility of laying hens in an aviary system. Appl. Anim. Behav. Sci. 2019, 217, 48–56. [Google Scholar] [CrossRef]
- Hartcher, K.M.; Hickey, K.A.; Hemsworth, P.H.; Cronin, G.M.; Wilkinson, S.J.; Singh, M. Relationships between range access as monitored by radio frequency identification technology, fearfulness, and plumage damage in free-range laying hens. Animals 2015, 10, 847–853. [Google Scholar] [CrossRef] [Green Version]
- Li, N.; Ren, Z.; Li, D.; Zeng, L. Review: Automated techniques for monitoring the behaviour and welfare of broilers and laying hens: Towards the goal of precision livestock farming. Animals 2019, 14, 617–625. [Google Scholar] [CrossRef] [Green Version]
Summary Statistics | Average Lower Feeder Time (Min/Hen/Day) | Average Upper Feeder Time (Min/Hen/Day) | Average Nest Box Time (Min/Hen/Day) | Average Range Use Time (Min/Hen/Day) | |||||
---|---|---|---|---|---|---|---|---|---|
K-Means | Agglomerative | K-Means | Agglomerative | K-Means | Agglomerative | K-Means | Agglomerative | ||
Cluster 1 | Mean ± SEM | 108.7 ± 2.28 | 88.9 ± 2.45 | 498.0 ± 4.16 | 571.8 ± 4.60 | 71.9 ± 1.37 | 68.2 ± 1.58 | 6.18 ± 0.32 | 4.80 ± 0.36 |
SD | 87.4 | 76.7 | 159.7 | 144.1 | 52.5 | 49.3 | 12.1 | 11.4 | |
Skewness | 0.85 | 0.99 | 0.89 | 0.87 | 1.41 | 0.79 | 3.07 | 3.88 | |
CV | 80.3 | 0.48 | 32.1 | 0.14 | 73.0 | 0.44 | 196.2 | 19.4 | |
Median | 89.7 | 65.3 | 458.3 | 539.6 | 63.1 | 60.5 | 0.01 | 0.00 | |
N | 1470 | 979 | 1470 | 979 | 1470 | 979 | 1470 | 979 | |
Cluster 2 | Mean ± SEM | 302.4 ± 1.80 | 264.1 ± 1.88 | 143.8 ± 1.57 | 178.7 ± 1.94 | 78.1 ± 1.16 | 72.88 ± 0.89 | 30.0 ± 0.45 | 26.59 ± 0.43 |
SD | 106.2 | 109.9 | 92.7 | 114.6 | 68.4 | 52.6 | 26.6 | 25.4 | |
Skewness | −0.31 | −0.17 | 0.42 | 0.32 | 3.54 | 2.64 | 1.02 | 1.10 | |
Kurtosis | −0.66 | −0.436 | −0.55 | −0.865 | 18.70 | 12.2 | 1.19 | 1.39 | |
Median | 312.1 | 273.5 | 132.2 | 164.9 | 61.2 | 61.1 | 26.1 | 22.4 | |
N | 3473 | 3501 | 3473 | 3501 | 3473 | 3501 | 3473 | 3501 | |
Cluster 3 | Mean ± SEM | 648.5 ± 2.50 | 611.7 ± 2.61 | 46.3 ± 1.17 | 55.3 ± 1.11 | 59.0 ± 1.05 | 69.1 ± 1.38 | 26.8 ± 1.20 | 27.9 ± 0.57 |
SD | 119.8 | 137.2 | 56.2 | 58.5 | 50.2 | 72.4 | 29.6 | 30.1 | |
Skewness | 0.70 | 0.47 | 1.80 | 1.03 | 2.61 | 3.57 | 1.20 | 1.17 | |
Kurtosis | 0.32 | 0.001 | 4.89 | 0.178 | 11.9 | 18.5 | 0.94 | 0.866 | |
Median | 635.1 | 602.1 | 26.1 | 37.0 | 48.0 | 51.4 | 16.9 | 18.8 | |
N | 2301 | 2764 | 2301 | 2764 | 2301 | 2764 | 2301 | 2764 |
Clustering Algorigthm | Agglomerative Clustering | Total N | |||
---|---|---|---|---|---|
Cluster 1 N (%) | Cluster 2 N (%) | Cluster 3 N (%) | |||
K-means | Cluster 1 | 979 (66.6) | 491 (33.4) | 0 (0) | 1470 |
Cluster 2 | 0 (0) | 2992 (86.2) | 481 (13.9) | 3473 | |
Cluster 3 | 0 (0) | 18 (0.78) | 2283 (99.2) | 2301 | |
Total | 979 | 3501 | 2764 | 7244 | |
Kappa coefficient | Kappa | SEM | Lower 95% | Upper 95% | |
0.7794 | 0.0065 | 0.7667 | 0.7922 |
Cluster | Summary Statistics | CV of Mean Lower Feeder Duration (%) | CV of Mean Upper Feeder Duration (%) | CV of Mean Nest Box Duration (%) | CV of Mean Range Use Duration (%) |
---|---|---|---|---|---|
Cluster 1 (n = 979) | Mean ± SEM | 72.2 ± 0.74 | 132 ± 1.28 | 115 ± 0.77 | 164 ± 1.35 |
SD | 42.2 | 73.4 | 44.2 | 77.2 | |
Maximum | 360 | 499 | 461 | 500 | |
Minimum | 21.0 | 31.5 | 32.4 | 55.3 | |
Median | 55.4 | 113 | 105 | 147 | |
Cluster 2 (n = 3501) | Mean ± SEM | 101 ± 1.59 | 113 ± 1.85 | 114 ± 1.44 | 196 ± 2.64 |
SD | 55.3 | 64.6 | 50.2 | 92 | |
Maximum | 452 | 496 | 471 | 500 | |
Minimum | 23.8 | 26.1 | 38.5 | 59.6 | |
Median | 84.9 | 98.7 | 103 | 175 | |
Cluster 3 (n = 2764) | Mean ± SEM | 70.7 ± 1.03 | 175 ± 2.20 | 120 ± 1.02 | 185 ± 1.85 |
SD | 43.0 | 91.9 | 42.8 | 77.4 | |
Maximum | 416 | 497 | 432 | 500 | |
Minimum | 21.0 | 44.3 | 43.9 | 65.0 | |
Median | 53.6 | 155 | 113 | 167 | |
Pooled (n = 7244) | Mean ± SEM | 77.5 ± 0.59 | 140 ± 1.02 | 116 ± 0.57 | 176 ± 1.03 |
SD | 46.8 | 80.8 | 45.11 | 81.4 | |
Maximum | 452 | 499 | 471 | 500 | |
Minimum | 21.0 | 26.1 | 32.4 | 55.4 | |
Median | 60.7 | 123 | 107 | 158 |
Sub-Population | Egg Follicle Observation; N (%) | |||
---|---|---|---|---|
No Follicles | Late Regression | Early Regression | Full Egg Production | |
Cluster 1 | 55 (1.58) | 43 (1.24) | 107 (3.08) | 3266 (94.1) |
Cluster 2 | 35 (2.38) | 19 (1.29) | 50 (3.40) | 1366 (92.9) |
Cluster 3 | 44 (1.92) | 34 (1.48) | 75 (3.27) | 2144 (93.3) |
Pooled | 134 (1.85) | 96 (1.33) | 232 (3.21) | 6776 (93.6) |
p-value Cluster | 0.4133 | |||
p-value Flock | 0.0092 | |||
p-value Flock × Cluster | 0.7167 |
© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Sibanda, T.Z.; Welch, M.; Schneider, D.; Kolakshyapati, M.; Ruhnke, I. Characterising Free-Range Layer Flocks Using Unsupervised Cluster Analysis. Animals 2020, 10, 855. https://doi.org/10.3390/ani10050855
Sibanda TZ, Welch M, Schneider D, Kolakshyapati M, Ruhnke I. Characterising Free-Range Layer Flocks Using Unsupervised Cluster Analysis. Animals. 2020; 10(5):855. https://doi.org/10.3390/ani10050855
Chicago/Turabian StyleSibanda, Terence Zimazile, Mitchell Welch, Derek Schneider, Manisha Kolakshyapati, and Isabelle Ruhnke. 2020. "Characterising Free-Range Layer Flocks Using Unsupervised Cluster Analysis" Animals 10, no. 5: 855. https://doi.org/10.3390/ani10050855
APA StyleSibanda, T. Z., Welch, M., Schneider, D., Kolakshyapati, M., & Ruhnke, I. (2020). Characterising Free-Range Layer Flocks Using Unsupervised Cluster Analysis. Animals, 10(5), 855. https://doi.org/10.3390/ani10050855