Automated identification of chicken distress vocalizations using deep learning models

Mao, Axiu; Giraudet, Claire S E; Liu, Kai; Nolasco, Ines; ZhiQin, Xie; ZhiXun, Xie; Gao, Yue; Theobald, James; Bhatta, Devaki; Stewart, Rebecca; McElligott, Alan G.

doi:10.1098/rsif.2021.0921

Cited by 17 publications

(6 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A large body of ML literature points out to the problem of class-unbalanced datasets and its solutions [68,69]. Recent studies and reviews have emphasised the use of data augmentation and balancing techniques to improve ML accuracy when handling acoustic data [70][71][72].…”

Section: Optimising Source Identificationmentioning

confidence: 99%

Optimising source identification from marmoset vocalisations with hierarchical machine learning classifiers

Phaniraj

Wierucka

Zürcher

et al. 2022

Preprint

View full text Add to dashboard Cite

Marmosets, with their highly social nature and complex vocal communication system, are important models for comparative studies of vocal communication and, eventually, language evolution. However, our knowledge about marmoset vocalisations predominantly originates from playback studies or vocal interactions between dyads, and there is a need to move towards studying group-level communication dynamics. Efficient source identification from marmoset vocalisations is essential for this challenge, and machine learning algorithms (MLAs) can aid it. Here we built a pipeline capable of plentiful feature extraction, meaningful feature selection, and supervised classification of vocalisations of up to 18 marmosets. We optimised the classifier by building a hierarchical MLA that first learned to determine the sex of the source, narrowed down the possible source individuals based on their sex, and then determined the source identity. We were able to correctly identify the source individual with high precisions (87.21% - 94.42%, depending on call type, and up to 97.79% after the removal of twins from the dataset). We also examine the robustness of identification across varying sample sizes. Our pipeline is a promising tool not only for source identification from marmoset vocalisations but also for analysing vocalisations and tracking vocal learning trajectories of other species.

show abstract

Section: Optimising Source Identificationmentioning

confidence: 99%

Optimising source identification from marmoset vocalisations with hierarchical machine learning classifiers

Phaniraj

Wierucka

Zürcher

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…To address the scarcity of multi-species vocal classification algorithms, Bishop et al proposed a multifunctional animal vocal algorithm using specific audio feature extraction techniques and machine learning models, which laid the foundation for the development of subsequent automatic animal vocal detection systems [ 149 ]. Mao et al developed a chicken call signal recognition device based on a convolutional neural network model, which effectively avoided the problem of inefficient reliance on manual recognition [ 150 ]. Changes in animal behavior are powerful indicators of health and welfare problems, and automatic identification of animal behavior can provide a powerful tool for improving farm management and ensuring animal welfare [ 151 , 152 ].…”

Section: Resultsmentioning

confidence: 99%

Precision Livestock Farming Research: A Global Scientometric Review

Jiang

Tang

Cui

et al. 2023

Animals

View full text Add to dashboard Cite

Precision livestock farming (PLF) utilises information technology to continuously monitor and manage livestock in real-time, which can improve individual animal health, welfare, productivity and the environmental impact of animal husbandry, contributing to the economic, social and environmental sustainability of livestock farming. PLF has emerged as a pivotal area of multidisciplinary interest. In order to clarify the knowledge evolution and hotspot replacement of PLF research, based on the relevant data from the Web of Science database from 1973 to 2023, this study analyzed the main characteristics, research cores and hot topics of PLF research via CiteSpace. The results point to a significant increase in studies on PLF, with countries having advanced livestock farming systems in Europe and America publishing frequently and collaborating closely across borders. Universities in various countries have been leading the research, with Daniel Berckmans serving as the academic leader. Research primarily focuses on animal science, veterinary science, computer science, agricultural engineering, and environmental science. Current research hotspots center around precision dairy and cattle technology, intelligent systems, and animal behavior, with deep learning, accelerometer, automatic milking systems, lameness, estrus detection, and electronic identification being the main research directions, and deep learning and machine learning represent the forefront of current research. Research hot topics mainly include social science in PLF, the environmental impact of PLF, information technology in PLF, and animal welfare in PLF. Future research in PLF should prioritize inter-institutional and inter-scholar communication and cooperation, integration of multidisciplinary and multimethod research approaches, and utilization of deep learning and machine learning. Furthermore, social science issues should be given due attention in PLF, and the integration of intelligent technologies in animal management should be strengthened, with a focus on animal welfare and the environmental impact of animal husbandry, to promote its sustainable development.

show abstract

“…If future research could identify specific acoustic cues that predict how humans rate arousal in chicken calls, these results could potentially be used in artificially intelligent based detection systems to monitor vocalizations in chickens. Furthermore, if such vocalization monitoring was reliable, it would provide a convenient and cost-effective way to enhance welfare assessment methods in the commercial chicken production industry [ 51 ].…”

Section: Discussionmentioning

confidence: 99%

Humans can identify reward-related call types of chickens

McGrath,

Phillips,

Burman

et al. 2024

R. Soc. open sci.

View full text Add to dashboard Cite

Humans can decode emotional information from vocalizations of animals. However, little is known if these interpretations relate to the ability of humans to identify if calls were made in a rewarded or non-rewarded context. We tested whether humans could identify calls made by chickens ( Gallus gallus ) in these contexts, and whether demographic factors or experience with chickens affected their correct identification context and the ratings of perceived positive and negative emotions (valence) and excitement (arousal) of chickens. Participants ( n = 194) listened to eight calls when chickens were anticipating a reward, and eight calls in non-rewarded contexts, and indicated whether the vocalizing chicken was experiencing pleasure/displeasure, and high/low excitement, using visual analogue scales. Sixty-nine per cent of participants correctly assigned reward and non-reward calls to their respective categories. Participants performed better at categorizing reward-related calls, with 71% of reward calls classified correctly, compared with 67% of non-reward calls. Older people were less accurate in context identification. Older people's ratings of the excitement or arousal levels of reward-related calls were higher than younger people's ratings, while older people rated non-reward calls as representing higher positive emotions or pleasure (higher valence) compared to ratings made by younger people. Our study strengthens evidence that humans perceive emotions across different taxa, and that specific acoustic cues may embody a homologous signalling system among vertebrates. Importantly, humans could identify reward-related calls, and this ability could enhance the management of farmed chickens to improve their welfare.

show abstract

Automated identification of chicken distress vocalizations using deep learning models

Cited by 17 publications

References 56 publications

Optimising source identification from marmoset vocalisations with hierarchical machine learning classifiers

Optimising source identification from marmoset vocalisations with hierarchical machine learning classifiers

Precision Livestock Farming Research: A Global Scientometric Review

Humans can identify reward-related call types of chickens

Contact Info

Product

Resources

About