The Future of Artificial Intelligence in Monitoring Animal Identification, Health, and Behaviour

Application of Machine Learning for Automating Behavioral Tracking of Captive Bornean Orangutans (Pongo Pygmaeus)

This article applies object detection to CCTV video material to investigate the potential of using machine learning to automate behavior tracking. This study includes video tapings of two captive Bornean orangutans and their behavior. From a 2 min training video containing the selected behaviors, 334 images were extracted and labeled using Rectlabel. The labeled training material was used to construct an object detection model using Create ML. The use of object detection was shown to have potential for automating tracking, especially of locomotion, whilst filtering out false positives. Potential improvements regarding this tool are addressed, and future implementation should take these into consideration. These improvements include using adequately diverse training material and limiting iterations to avoid overfitting the model.

Human-animal interactions and machine-animal interactions in animals under human care: A summary of stakeholder and researcher perceptions and future directions

Animals under human care are exposed to a potentially large range of both familiar and unfamiliar humans. Human-animal interactions vary across settings, and individuals, with the nature of the interaction being affected by a suite of different intrinsic and extrinsic factors. These interactions can be described as positive, negative or neutral. Across some industries, there has been a move towards the development of technologies to support or replace human interactions with animals. Whilst this has many benefits, there can also be challenges associated with increased technology use. A day-long Animal Welfare Research Network workshop was hosted at Harper Adams University, UK, with the aim of bringing together stakeholders and researchers (n = 38) from the companion, farm and zoo animal fields, to discuss benefits, challenges and limitations of human-animal interactions and machine-animal interactions for animals under human care and create a list of future research priorities. The workshop consisted of four talks from experts within these areas, followed by break-out room discussions. This work is the outcome of that workshop. The key recommendations are that approaches to advancing the scientific discipline of machine-animal interactions in animals under human care should focus on: (1) interdisciplinary collaboration; (2) development of validated methods; (3) incorporation of an animal-centred perspective; (4) a focus on promotion of positive animal welfare states (not just avoidance of negative states); and (5) an exploration of ways that machines can support a reduction in the exposure of animals to negative human-animal interactions to reduce negative, and increase positive, experiences for animals.

Health Status Classification for Cows Using Machine Learning and Data Management on AWS Cloud

The health and welfare of livestock are significant for ensuring the sustainability and profitability of the agricultural industry. Addressing efficient ways to monitor and report the health status of individual cows is critical to prevent outbreaks and maintain herd productivity. The purpose of the study is to develop a machine learning (ML) model to classify the health status of milk cows into three categories. In this research, data are collected from existing non-invasive IoT devices and tools in a dairy farm, monitoring the micro- and macroenvironment of the cow in combination with particular information on age, days in milk, lactation, and more. A workflow of various data-processing methods is systematized and presented to create a complete, efficient, and reusable roadmap for data processing, modeling, and real-world integration. Following the proposed workflow, the data were treated, and five different ML algorithms were trained and tested to select the most descriptive one to monitor the health status of individual cows. The highest result for health status assessment is obtained by random forest classifier (RFC) with an accuracy of 0.959, recall of 0.954, and precision of 0.97. To increase the security, speed, and reliability of the work process, a cloud architecture of services is presented to integrate the trained model as an additional functionality in the Amazon Web Services (AWS) environment. The classification results of the ML model are visualized in a newly created interface in the client application.