Találati lista | Tudóstér

001-es BibID:	BIBFORM121144
035-os BibID:	(Scopus)85192864723 (WoS)001242233500001
Első szerző:	Brassó Dóra Lili (állattenyésztő mérnök)
Cím:	Behaviour frequencies, spatial distribution and social network of Grimaud geese during the laying season / Lili Dóra Brassó, István Komlósi, Zoltán Barta
Dátum:	2024
ISSN:	0168-1591
Megjegyzések:	Most domestic goose breeds were domesticated from the Greylag goose. Even though domestication resulted in a change in the production and behaviour of birds compared to their ancestors, geese are relatively recently domesticated and less intensively selected for production compared to other species (i.e. chickens or dairy cattle). In this respect, we hypothesised that the territorial defence of ganders would be present during the laying season similar to the wild ones. The behaviour of birds was expected to differ by sex, the month of the laying season and the time of the day. We assumed that the hierarchy within a group would be affected by the influence of other groups. Altogether 150 birds in three fifty-bird groups were examined over five observation events indicating the onset (December), the peak (the start, the middle and the end of January) and the end (the end of February) of the laying season. Twenty behaviour elements classified into five categories (locomotion, static behaviours, feed intake, comfort behaviours and social behaviours) were examined regarding the three groups as replicates. The territorial defence of ganders was evaluated by spatial distribution analysis, and the relations within groups were investigated by social network analysis. Between sexes, only the frequency of social behaviours presented differences. Ganders showed social behaviour more frequently than geese (10.89% vs 1.49%, P= 0.000). The frequency of Journal Pre-proof static behaviours was the lowest at the onset of January and the highest in February (21.18% vs 38.03%, P= 0.000). The frequency of feed intake was the highest in December and the lowest in February (18.33% vs 4.83%, P= 0.000). Comfort behaviours showed the lowest frequency in December and the highest at the onset of January (36.65% vs 57.63%, P= 0.000). The social behaviours were unchanged in December and January but decreased in February (4.40-6.37% vs 1.16%, P=0.000). Only the frequency of social behaviours differed by the time of the day, indicating the highest frequency in the morning (55.60%, P=0.003). The results of the spatial distribution analysis did not strongly support the presence of territorial defence of ganders. The structure within a group was the most explicit in Group 1 having an adjacent large group and another small group by which it was likely to be influenced. It might be concluded that domestic geese ganders did not keep their territory-holding ability to a full extent during domestication and the behaviour (mainly social interactions) of domestic geese is influenced by sex, the month of the laying season and the time of the day. The structure within a group was somewhat influenced by the adjacent groups
Tárgyszavak:	Agrártudományok Állattenyésztési tudományok idegen nyelvű folyóiratközlemény külföldi lapban folyóiratcikk
Megjelenés:	Applied Animal Behaviour Science. - 275 (2024), p. 1-27. -
További szerzők:	Komlósi István (1960-) (agrármérnök) Barta Zoltán (1967-) (biológus, zoológus)
Pályázati támogatás:	EFOP-3.6.3-VEKOP-16-2017-00008 EFOP ÚNKP-20-3-I-DE-372 Egyéb TKP2021-NKTA-32 Egyéb
Internet cím:	Intézményi repozitóriumban (DEA) tárolt változat DOI
Borító:
Saját polcon:

001-es BibID:	BIBFORM115201
035-os BibID:	(WoS)001082301900001 (Scopus)85171791270
Első szerző:	Çakmakçı, Cihan
Cím:	Discovering the hidden personality of lambs : Harnessing the power of Deep Convolutional Neural Networks (DCNNs) to predict temperament from facial images / Cihan Çakmakçı, Danielle Rodrigues Magalhaes, Vitor Ramos Pacor, Douglas Henrique Silva de Almeida, Yusuf Çakmakçı, Selma Dalga, Csaba Szabo, Gustavo A. María, Cristiane Gonçalves Titto
Dátum:	2023
ISSN:	0168-1591
Megjegyzések:	The objective of this study was to define a more practical and reliable alternative to manual temperament classification methods that rely on the behavioral responses of animals individually subjected to various tests. Specifically, this study evaluated the correlation between facial image information and temperament based on deep convolutional neural networks (DCNNs) to predict the temperament of lambs based on their facial images. In the first phase, the lambs were categorized as to their temperament based on data acquired from a behavioral test to establish a ground truth for the temperament of the lambs. This enabled us to train (70%), validate (20%), and test (10%) deep-learning models in the second phase based on facial images and the corresponding temperament labels derived from the behavioral test. The performance of a custom deep convolutional neural network (C-DCNN) was compared to that of pre-trained VGG19 and Xception models for image classification. The Xception model achieved a training accuracy of 81%, which indicated that it learned well the underlying patterns in the data; however, lower validation (0.75) and test (0.58) accuracies indicate that it overfit the training data and did not generalize well to new samples. The VGG19 model, produced lower training (0.59), validation (0.46), and test (0.34) accuracies, which indicated that it did not learn the underlying patterns in the data as well as the Xception model. Furthermore, its precision (0.47), recall (0.42), and F1 score (0.41) indicated that the model performed poorly in identifying the classes correctly. The C-DCNN produced a moderate accuracy of 60%, which indicated that the model was able to predict the temperament traits of lambs with an accuracy of 60%, which was better than random guessing (33% accuracy), and demonstrated the potential of this approach in assessing temperament. The C-DCNN precision (0.69), recall (0.61) and F1 score (0.63) indicated that it had a moderate ability to correctly identify positive cases; however, the small size of the original dataset remains a limitation of the study because it might have caused the suboptimal performance of the models. To validate this approach, further research is needed based on a larger and more diverse dataset. We will continue to investigate the potential of deep learning and computer vision to predict animal personality traits from facial images based on large, diverse datasets, which might lead to more efficient and objective methods for assessing animal temperament and improving animal welfare.
Tárgyszavak:	Agrártudományok Állattenyésztési tudományok idegen nyelvű folyóiratközlemény külföldi lapban folyóiratcikk Computer vision Deep learning Facial images Lamb Temperament
Megjelenés:	Applied Animal Behaviour Science. - 267 (2023), p. 1-15. -
További szerzők:	Magalhaes, Danielle Rodrigues Pacor, Vitor Ramos Almeida, Douglas Henrique Silva de Çakmakçı, Yusuf Dalga, Selma Szabó Csaba (1968-) (agrármérnök) María, Gustavo A. Titto, Cristiane Gonçalves
Internet cím:	Szerző által megadott URL DOI Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Saját polcon: