scholarly journals Is Seeing Still Believing? Leveraging Deepfake Technology for Livestock Farming

2021 ◽  
Vol 8 ◽  
Author(s):  
Suresh Neethirajan
Keyword(s):  
Digital Media ◽  
Data Augmentation ◽  
Animal Health ◽  
Real Data ◽  
Machine Learning Algorithms ◽  
Farm Animals ◽  
Generative Adversarial Networks ◽  
Farm Animal Welfare ◽  
Livestock Farming ◽  
Digital Twins

Deepfake technologies are known for the creation of forged celebrity pornography, face and voice swaps, and other fake media content. Despite the negative connotations the technology bears, the underlying machine learning algorithms have a huge potential that could be applied to not just digital media, but also to medicine, biology, affective science, and agriculture, just to name a few. Due to the ability to generate big datasets based on real data distributions, deepfake could also be used to positively impact non-human animals such as livestock. Generated data using Generative Adversarial Networks, one of the algorithms that deepfake is based on, could be used to train models to accurately identify and monitor animal health and emotions. Through data augmentation, using digital twins, and maybe even displaying digital conspecifics (digital avatars or metaverse) where social interactions are enhanced, deepfake technologies have the potential to increase animal health, emotionality, sociality, animal-human and animal-computer interactions and thereby productivity, and sustainability of the farming industry. The interactive 3D avatars and the digital twins of farm animals enabled by deepfake technology offers a timely and essential way in the digital transformation toward exploring the subtle nuances of animal behavior and cognition in enhancing farm animal welfare. Without offering conclusive remarks, the presented mini review is exploratory in nature due to the nascent stages of the deepfake technology.

scholarly journals Beyond Deepfake Technology Fear: On its Positive Uses for Livestock Farming

2021 ◽  
Author(s):  
Suresh Neethirajan
Keyword(s):  
Digital Media ◽  
Data Augmentation ◽  
Animal Health ◽  
Real Data ◽  
Machine Learning Algorithms ◽  
Generative Adversarial Networks ◽  
Livestock Farming ◽  
Affective Science ◽  
Digital Twins ◽  
Farming Industry

Deepfake technologies are known for the creation of forged celebrity pornography, face and voice swaps, and other fake media content. Despite the negative connotations the technology bears, the underlying machine learning algorithms have a huge potential that could be applied to not just digital media, but also to medicine, biology, affective science, and agriculture, just to name a few. Due to the ability to generate big datasets based on real data distributions, deepfake could also be used to positively impact non-human animals such as livestock. Generated data using Generative Adversarial Networks, one of the algorithms that deepfake is based on, could be used to train models to accurately identify and monitor animal health and emotions. Through data augmentation, using digital twins, and maybe even displaying digital conspecifics where social interactions are enhanced, deepfake technologies have the potential to increase animal health, emotionality, sociality, animal-human and animal-computer interactions and thereby animal welfare, productivity, and sustainability of the farming industry.

scholarly journals Precision Technologies to Address Dairy Cattle Welfare: Focus on Lameness, Mastitis and Body Condition

Animals ◽  
2021 ◽  
Vol 11 (8) ◽  
pp. 2253
Author(s):  
Severiano R. Silva ◽  
José P. Araujo ◽  
Cristina Guedes ◽  
Flávio Silva ◽  
Mariana Almeida ◽  
...  
Keyword(s):  
Animal Welfare ◽  
Body Condition ◽  
Farm Animals ◽  
Economic Sustainability ◽  
Farm Animal Welfare ◽  
Livestock Farming ◽  
Technological Support ◽  
Technological Tools ◽  
Cow Welfare ◽  
Time Assessment

Specific animal-based indicators that can be used to predict animal welfare have been the core of protocols for assessing the welfare of farm animals, such as those produced by the Welfare Quality project. At the same time, the contribution of technological tools for the accurate and real-time assessment of farm animal welfare is also evident. The solutions based on technological tools fit into the precision livestock farming (PLF) concept, which has improved productivity, economic sustainability, and animal welfare in dairy farms. PLF has been adopted recently; nevertheless, the need for technological support on farms is getting more and more attention and has translated into significant scientific contributions in various fields of the dairy industry, but with an emphasis on the health and welfare of the cows. This review aims to present the recent advances of PLF in dairy cow welfare, particularly in the assessment of lameness, mastitis, and body condition, which are among the most relevant animal-based indications for the welfare of cows. Finally, a discussion is presented on the possibility of integrating the information obtained by PLF into a welfare assessment framework.

Farm animal welfare: the future.

2020 ◽  
pp. 173-190
Author(s):  
Alistair Stott ◽  
Bouda Vosough Ahmadi
Keyword(s):  
Animal Welfare ◽  
Production Systems ◽  
Animal Health ◽  
Livestock Production ◽  
Farm Animal ◽  
Management Approach ◽  
Farm Animal Welfare ◽  
Livestock Farming ◽  
The Future ◽  
Animal Welfare Science

Abstract Science can help us understand what animals want and economics can provide the understanding of human motivation needed to deliver such wants. In our view, what needs further development in future is for economics and information/communication science and technology to channel awareness into appropriate action. This chapter elaborates on this idea by providing some illustrative examples. Focusing on animal health and welfare, it argues that there is much scope for improvement in profit and welfare on commercial farms simply by adopting the best disease management approach available. We also emphasize the importance of systems modelling and operations research (OR) in the future to ensure that animal welfare taps into the growing opportunities that developments in these methods are likely to bring. The chapter also argues that OR can provide a bridge between animal welfare science, economics and business to deliver improvements in animal welfare through food markets. The importance of big data and precision livestock farming in livestock production/reproduction, animal health and welfare, and the environmental impact of livestock production are also discussed. New genetic approaches to optimize livestock resilience and efficiency are highlighted. We argue that tackling difficult problems, such as sustainability (that encompasses animal welfare alongside environment and climate change), efficiency and resilience in farm animal production systems, is and will remain a vital focus of research in the agri-food sector. Research methods and governance still need to change to properly reflect this. It is envisaged that animal welfare will be affected by these developments and should, wherever appropriate, be explicitly considered.

scholarly journals The three pillars of applied farm animal welfare

2021 ◽  
pp. 14-14
Author(s):  
Miroslav Kjosevski ◽  
Martin Nikolovski ◽  
Ksenija Ilievska ◽  
Lazo Pendovski ◽  
Vlatko Ilieski
Keyword(s):  
Animal Welfare ◽  
Animal Health ◽  
Economic Value ◽  
Added Value ◽  
Farm Animals ◽  
The European Union ◽  
Farm Animal Welfare ◽  
Product Price ◽  
Implementation Level ◽  
The Impact

There is an evident difference in the implementation level of animal welfare (AW) across the societies and countries worldwide. Although multiple factors contribute to these differences, we can summarize them into a three pillar concept, the three aspects of applied farm AW. The objective of this review is to analyse applied AW on farms from the ethical, economic and animal health aspects. Modern ethics emphasizes biocentrism against anthropocentrism, the modern ethical concept of bioethics. Additionally, beside the differences among the major ethical concepts, there is a consensus that AW deserves a respectful place. An animal?s economic value is not only limited by its material value determined by the inputs and outputs. Thus, rather than being simply considered as a ?stock-good? machine, animals are valued as a sentient beings with ?added value?, which has an impact on the final product price. Animal health and welfare are interconnected and are based on the impact of AW on health and vice versa. The implementation of higher welfare standards to farm animals is only possible if AW is accepted as part of the health of the animal. The applicability of this concept is presented through the European Union AW legislation, which is based on public opinion, economy and animal health. As a conclusion, applied AW is possible only at the level at which the three pillars are equally balanced, and the initiatives in this field should work and be focused on ethics, economics and health.

scholarly journals ADD: Attention-Based DeepFake Detection Approach

2021 ◽  
Vol 5 (4) ◽  
pp. 49
Author(s):  
Aminollah Khormali ◽  
Jiann-Shiun Yuan
Keyword(s):  
Digital Media ◽  
Network Architecture ◽  
Data Augmentation ◽  
Input Image ◽  
Detection Methods ◽  
Generative Adversarial Networks ◽  
Fine Grained ◽  
Detection Model ◽  
Benchmark Datasets ◽  
Main Components

Recent advancements of Generative Adversarial Networks (GANs) pose emerging yet serious privacy risks threatening digital media’s integrity and trustworthiness, specifically digital video, through synthesizing hyper-realistic images and videos, i.e., DeepFakes. The need for ascertaining the trustworthiness of digital media calls for automatic yet accurate DeepFake detection algorithms. This paper presents an attention-based DeepFake detection (ADD) method that exploits the fine-grained and spatial locality attributes of artificially synthesized videos for enhanced detection. ADD framework is composed of two main components including face close-up and face shut-off data augmentation methods and is applicable to any classifier based on convolutional neural network architecture. ADD first locates potentially manipulated areas of the input image to extract representative features. Second, the detection model is forced to pay more attention to these forgery regions in the decision-making process through a particular focus on interpreting the sample in the learning phase. ADD’s performance is evaluated against two challenging datasets of DeepFake forensics, i.e., Celeb-DF (V2) and WildDeepFake. We demonstrated the generalization of ADD by evaluating four popular classifiers, namely VGGNet, ResNet, Xception, and MobileNet. The obtained results demonstrate that ADD can boost the detection performance of all four baseline classifiers significantly on both benchmark datasets. Particularly, ADD with ResNet backbone detects DeepFakes with more than 98.3% on Celeb-DF (V2), outperforming state-of-the-art DeepFake detection methods.

scholarly journals Creating artificial human genomes using generative neural networks

PLoS Genetics ◽  
2021 ◽  
Vol 17 (2) ◽  
pp. e1009303
Author(s):  
Burak Yelmen ◽  
Aurélien Decelle ◽  
Linda Ongaro ◽  
Davide Marnetto ◽  
Corentin Tallec ◽  
...  
Keyword(s):  
Data Augmentation ◽  
Wide Spectrum ◽  
Generative Models ◽  
Machine Learning Algorithms ◽  
Easy Access ◽  
Generative Adversarial Networks ◽  
Compact Representation ◽  
Restricted Boltzmann Machines ◽  
High Quality ◽  
Genetic Studies

Generative models have shown breakthroughs in a wide spectrum of domains due to recent advancements in machine learning algorithms and increased computational power. Despite these impressive achievements, the ability of generative models to create realistic synthetic data is still under-exploited in genetics and absent from population genetics. Yet a known limitation in the field is the reduced access to many genetic databases due to concerns about violations of individual privacy, although they would provide a rich resource for data mining and integration towards advancing genetic studies. In this study, we demonstrated that deep generative adversarial networks (GANs) and restricted Boltzmann machines (RBMs) can be trained to learn the complex distributions of real genomic datasets and generate novel high-quality artificial genomes (AGs) with none to little privacy loss. We show that our generated AGs replicate characteristics of the source dataset such as allele frequencies, linkage disequilibrium, pairwise haplotype distances and population structure. Moreover, they can also inherit complex features such as signals of selection. To illustrate the promising outcomes of our method, we showed that imputation quality for low frequency alleles can be improved by data augmentation to reference panels with AGs and that the RBM latent space provides a relevant encoding of the data, hence allowing further exploration of the reference dataset and features for solving supervised tasks. Generative models and AGs have the potential to become valuable assets in genetic studies by providing a rich yet compact representation of existing genomes and high-quality, easy-access and anonymous alternatives for private databases.

scholarly journals 7 ASAS-EAAP Exchange Speaker Talk: Increasing animal welfare and efficiency on-farm with the use of precision technology tools: technology development, application, and use

2019 ◽  
Vol 97 (Supplement_3) ◽  
pp. 12-13
Author(s):  
Jasmeet Kaler
Keyword(s):  
Machine Learning ◽  
Animal Welfare ◽  
Technological Development ◽  
Window Size ◽  
Machine Learning Algorithms ◽  
Farm Animals ◽  
Drinking Behaviour ◽  
Learning Approaches ◽  
Livestock Farming ◽  
Adoption Of Technology

Abstract Recent advances in bio-telemetry technology have made it possible to generate lot of data through sensors, which could be used to monitor welfare and classify behavioural activities in many different farm animals. However, little has been done with regards to evaluating predictive ability and comparing various machine learning approaches for ‘big data’ and also evaluating how this changes depending on sampling frequencies and position of sensors. In this talk, I will discuss technological development covering range of sensor technologies utilising state-of-the-art computation and transmission protocols we have co- developed as part of our research and on how we used these technologies to build machine learning algorithms for lameness in, and drinking behaviour in cows, with an ultimate aim to improve animal welfare. Algorithms could classify behaviours with overall accuracy above 95%; however, the accuracy varied by number of features used, choice of algorithm and window size used for feature generation. The talk will focus on challenges and approaches to build smart systems that are not only technologically advanced, have good accuracy, algorithms that continue to learn and versatile but also energy efficient and practical. While precision livestock farming has been a growing area for the past decade and has huge potential to improve livestock health and welfare, technology adoption has not occurred at the same pace. We need to understand farmers’ perceptions and understanding around technology, its use on farms and in farming. Results from our research with farmers suggest few key areas are important for embedding and adoption of technology on farms: first, utility of the technology, lack of validation and its ability to fit with existing structures and practices and the beliefs held by farmers that the use of the device may result in a loss of skill in future—that of the farmer knowing his animals.

scholarly journals Digital Twins in Livestock Farming

2021 ◽  
Author(s):  
Suresh Neethirajan ◽  
Bas Kemp
Keyword(s):  
Large Scale ◽  
Well Being ◽  
Farm Animals ◽  
Emotional States ◽  
Space Technology ◽  
Livestock Farming ◽  
Digital Twin ◽  
Technological Advances ◽  
Digital Twins ◽  
Cost And Benefit Analysis

Digital twin technology is already improving efficiencies and reducing costs across multiple industries and sectors. As the earliest adopters, space technology and manufacturing sectors have made the most sophisticated gains with automobile and natural resource extraction industries following close behind with recent investments in digital twin technology. The application of digital twins within the livestock farming sector is the next frontier. The possibilities that this technology may fuel are nearly endless as digital twins can be used to improve large-scale precision livestock farming practices, machinery and equipment usage, and the health and well-being of a wide variety of farm animals. Currently, many pioneers of digital twins in livestock farming are already applying sophisticated AI technology to monitor both animals and environment around the clock, which leads to a better understanding of animal behavior and distress, disease control and prevention, and smarter business decisions for the farmer. Mental and emotional states of animals can be monitored using recognition technology that examines facial features such as ear postures and eye white regions. Used with modeling, simulation and augmented reality technologies, digital twins can help farmers build more energy-efficient housing structures, predict heat cycles for breeding, discourage negative behaviors of livestock, and potentially much more. As with all disruptive technological advances, the implementation of digital twin technology will demand a thorough cost and benefit analysis by individual farms. Digital twin application will need to overcome challenges and accept limitations that arise. However, regardless of these issues, the potential of digital twins promises to revolutionize livestock farming in the future.

scholarly journals Satellite Imagery Noising With Generative Adversarial Networks

2021 ◽  
Vol 15 (1) ◽  
pp. 16-25
Author(s):  
Mohamed Akram Zaytar ◽  
Chaker El Amrani
Keyword(s):  
Remote Sensing ◽  
Satellite Imagery ◽  
Data Augmentation ◽  
Remote Sensing Data ◽  
Machine Learning Algorithms ◽  
Supervised Machine Learning ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Sensing Data ◽  
Adversarial Network

Using satellite imagery and remote sensing data for supervised and self-supervised learning problems can be quite challenging when parts of the underlying datasets are missing due to natural phenomena (clouds, fog, haze, mist, etc.). Solving this problem will improve remote sensing data augmentation and make use of it in a world where satellite imagery represents a great resource to exploit in any big data pipeline setup. In this paper, the authors present a generative adversarial network (GANs) model that can generate natural atmospheric noise that serves as a data augmentation preprocessing tool to produce input to supervised machine learning algorithms.

scholarly journals Farmers’ Preferences Regarding the Design of Animal Welfare Programs: Insights from a Choice-Based Conjoint Study in Germany

Animals ◽  
2021 ◽  
Vol 11 (3) ◽  
pp. 704
Author(s):  
Iris Schröter ◽  
Marcus Mergenthaler
Keyword(s):  
Animal Welfare ◽  
Animal Health ◽  
Well Being ◽  
Farm Animal ◽  
Farm Animal Welfare ◽  
Welfare Programs ◽  
Livestock Farming ◽  
Commitment Period ◽  
Decisive Importance ◽  
Compensation Level

As more animal welfare is required in livestock farming, several approaches have been developed to improve the well-being of farmed animals on a voluntary basis. Since farmers’ acceptance is important for the success of these approaches, their preferences should be considered when developing farm animal welfare programs. We used choice based conjoint analysis to investigate the preferences of 242 German livestock farmers (147 cattle farmers; 95 pig farmers) regarding the design of farm animal welfare programs. The conditional logit regression models show that the measures serving as basis for remuneration and the compensation level were of decisive importance for the farmers’ choices. The most preferred measure for assessing animal welfare, and thus as the basis for remuneration, was animal health. As expected, a higher compensation level led to greater acceptance of an animal welfare approach. The commitment period was only of subordinate importance with the longer commitment period being preferred. Our study outlines aspects of farm animal welfare programs that might encourage farmers to participate in these programs. Future programs could consider our findings by emphasising health parameters and by creating planning security through longer commitment periods and sufficiently high compensations for farmers’ efforts to improve animal welfare.

Sign in / Sign up

Export Citation Format

Share Document