Special Issue "Automation, Big Data, and New Technologies in Animal Research"

A special issue of Animals (ISSN 2076-2615). This special issue belongs to the section "Animal System and Management".

Deadline for manuscript submissions: 30 September 2021.

Special Issue Editors

Dr. Nuno Franco
E-Mail Website
Guest Editor
i3S—Institute of Health Research and Innovation, University of Porto, 4169-007 Porto, Portugal
Interests: animal welfare; animal ethics; laboratory animal science; experimental design
Dr. Paulin Jirkof
E-Mail Website
Guest Editor
Department of Animals welfare, Zurich University, CH-8057 Zurich, Switzerland
Interests: animal welfare; 3Rs; animal behavior; pain assessment; severity assessment; analgesia; laboratory animals
Special Issues and Collections in MDPI journals
Dr. Katharina Hohlbaum
E-Mail Website
Guest Editor
Institute of Animal Welfare, Animal Behavior, and Laboratory Animal Science, Department of Veterinary Medicine, Freie Universität Berlin, 14163 Berlin, Germany
Interests: animal welfare; animal behavior; laboratory animals; refinement; severity assessment; facial expression analysis; intelligence

Special Issue Information

Automation technology offers a wide range of possibilities for data collection in research on animals. One of its most important advantages is the possibility of continuous, round-the-clock data collection with minimal disturbance of the animals, with applications that go from biomedical research to precision livestock farming and wildlife research. The automated collection and/or analysis of large datasets gathered from sensors or cameras can offer a comprehensive picture of animal behaviour and physiology, and its interactions with the environment, while avoiding current caveats of operator-based methods, which are typically more labour-demanding, time-consuming, cost-inefficient, and bias-prone. Moreover, automated analysis allows identifying more details that would otherwise remain uncovered.

This Special Issue is interested in both reviews and original research papers on new technological approaches in research on animals, with particular emphasis on automation technology, artificial intelligence, and big data. We invite reports on the development or application of these technologies in laboratory, farm, companion, and wild animals. Examples include the application of new technological approaches to identify behavioural and physiological indicators of positive and negative welfare, as well as monitoring and early signalling of health problems to allow prompt intervention (from timely treatment of common diseases in livestock species to implementation of humane endpoints in animal models of disease).

Dr. Paulin Jirkof
Dr. Nuno Franco
Dr. Katharina Hohlbaum
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Animals is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • animal research
  • automation
  • technology
  • big data
  • precision livestock farming

Published Papers (2 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Review

Article
Determination of Body Parts in Holstein Friesian Cows Comparing Neural Networks and k Nearest Neighbour Classification
Animals 2021, 11(1), 50; https://doi.org/10.3390/ani11010050 - 29 Dec 2020
Viewed by 648
Abstract
Machine learning methods have become increasingly important in animal science, and the success of an automated application using machine learning often depends on the right choice of method for the respective problem and data set. The recognition of objects in 3D data is [...] Read more.
Machine learning methods have become increasingly important in animal science, and the success of an automated application using machine learning often depends on the right choice of method for the respective problem and data set. The recognition of objects in 3D data is still a widely studied topic and especially challenging when it comes to the partition of objects into predefined segments. In this study, two machine learning approaches were utilized for the recognition of body parts of dairy cows from 3D point clouds, i.e., sets of data points in space. The low cost off-the-shelf depth sensor Microsoft Kinect V1 has been used in various studies related to dairy cows. The 3D data were gathered from a multi-Kinect recording unit which was designed to record Holstein Friesian cows from both sides in free walking from three different camera positions. For the determination of the body parts head, rump, back, legs and udder, five properties of the pixels in the depth maps (row index, column index, depth value, variance, mean curvature) were used as features in the training data set. For each camera positions, a k nearest neighbour classifier and a neural network were trained and compared afterwards. Both methods showed small Hamming losses (between 0.007 and 0.027 for k nearest neighbour (kNN) classification and between 0.045 and 0.079 for neural networks) and could be considered successful regarding the classification of pixel to body parts. However, the kNN classifier was superior, reaching overall accuracies 0.888 to 0.976 varying with the camera position. Precision and recall values associated with individual body parts ranged from 0.84 to 1 and from 0.83 to 1, respectively. Once trained, kNN classification is at runtime prone to higher costs in terms of computational time and memory compared to the neural networks. The cost vs. accuracy ratio for each methodology needs to be taken into account in the decision of which method should be implemented in the application. Full article
(This article belongs to the Special Issue Automation, Big Data, and New Technologies in Animal Research)
Show Figures

Figure 1

Review

Jump to: Research

Review
Infrared Thermography in the Study of Animals’ Emotional Responses: A Critical Review
Animals 2021, 11(9), 2510; https://doi.org/10.3390/ani11092510 - 26 Aug 2021
Viewed by 270
Abstract
Whether animals have emotions was historically a long-lasting question but, today, nobody disputes that they do. However, how to assess them and how to guarantee animals their welfare have become important research topics in the last 20 years. Infrared thermography (IRT) is a [...] Read more.
Whether animals have emotions was historically a long-lasting question but, today, nobody disputes that they do. However, how to assess them and how to guarantee animals their welfare have become important research topics in the last 20 years. Infrared thermography (IRT) is a method to record the electromagnetic radiation emitted by bodies. It can indirectly assess sympathetic and parasympathetic activity via the modification of temperature of different body areas, caused by different phenomena such as stress-induced hyperthermia or variation in blood flow. Compared to other emotional activation assessment methods, IRT has the advantage of being noninvasive, allowing use without the risk of influencing animals’ behavior or physiological responses. This review describes general principles of IRT functioning, as well as its applications in studies regarding emotional reactions of domestic animals, with a brief section dedicated to the experiments on wildlife; it analyzes potentialities and possible flaws, confronting the results obtained in different taxa, and discusses further opportunities for IRT in studies about animal emotions. Full article
(This article belongs to the Special Issue Automation, Big Data, and New Technologies in Animal Research)
Back to TopTop