![]() ![]() In other words, we must evaluate the cognitive challenges presented by enrichment phenomena and to know whether it is eliciting the intended cognitive skills, as well as any emotional or behavioral affect it is having upon the animals involved ( 16). Cognitive enrichment requires us to simultaneously measure how the animal is performing cognitively (i.e., their learning, memory, problem-solving skills), and their welfare state (i.e., if their wellbeing is positively affected by the enrichment). For the focus of this paper, however, we are interested in the use of technology to automatically log an animal's response to a cognitive enrichment device, foremost to save researcher time and effort, but also to prevent human observation from influencing animal behavior. Technology also creates opportunities for instant feedback and to automate processes such as food reward presentation ( 13– 15). Digital interfaces can augment how cognitive challenges are provided to animals in their enclosure (e.g., the contrast between a tangible and digital maze, for example), and furthermore, provide more novel and repeatable experiences across time ( 13). We believe there is great potential to embed technology within cognitive enrichment and there are several possible avenues for realizing this. Previous research has identified cognitive enrichment as being particularly applicable to great apes under human care following decades of study into their cognitive abilities as compared to humans, and their swift adaptation to novel phenomena ( 12). Animals may also directly experience technological feedback systems in the form of lights, tones or vibrations ( 9, 10).Ĭognitive enrichment is a form of enrichment that aims to challenge the evolved cognitive skills of animals to enhance their welfare, yet it remains under-provisioned in many zoo settings ( 11). ![]() Contemporary animal-computer interaction (ACI) usually involves animals directly interacting with components such as touchscreens ( 4, 6), buttons or joysticks ( 7, 8), and therefore animals need to be trained to use the technology. However, the concept of zoo animals interacting with technology for the purposes of enrichment has experienced a renaissance over the past two decades ( 3– 5). The use of technology in zoos can be traced back to the research of Hal Markowitz beginning in the late 1970s and the birth of “behavioral engineering” ( 1, 2). To end, we describe a future system that combines machine learning and sensor technology which could automate the collection of data in real-time for use by researchers and animal care staff.Īnimal technologies in zoos have a long history they reflect society's changing perceptions of animal intelligence and welfare, and technological advancements and fashions. This highlights the need for additional technology, such as infrared sensors, to fully automate cognitive enrichment evaluation. ![]() ![]() Additionally, researcher input was still required to visually identify which maze modules were being used by gorillas and how. Therefore, we suggest a system like this is only appropriate for long-term projects. However, its development was a heavy investment, requiring specialized hardware and interdisciplinary expertise. The facial recognition system was very effective at identifying individual gorillas (97% mean average precision) and could automate specific downstream tasks (for example, duration of engagement). Concurrent traditional video recording and behavioral coding by eye was undertaken for comparison. We explored whether machine learning could automatically identify individual gorillas through facial recognition, and automate the collection of device-use data including the order, frequency and duration of use by the troop. In this paper, we describe how a facial recognition system, developed using machine learning, was embedded within a cognitive enrichment device (a vertical, modular finger maze) for a troop of seven Western lowland gorillas ( Gorilla gorilla gorilla) at Bristol Zoo Gardens, UK. However, despite its various positive applications to wildlife in recent years, there has been little uptake of machine learning in zoo animal care. The use of computer technology within zoos is becoming increasingly popular to help achieve high animal welfare standards. 5Bristol Vet School, Faculty of Life Sciences, University of Bristol, Bristol, United Kingdom.4School of Life Sciences, Faculty of Science and Engineering, Anglia Ruskin University, Cambridge, United Kingdom.3School of Psychological Science, Faculty of Life Sciences, University of Bristol, Bristol, United Kingdom.2Centre for Entrepreneurship, Faculty of Engineering, University of Bristol, Bristol, United Kingdom.1Department of Computer Science, Faculty of Engineering, University of Bristol, Bristol, United Kingdom.Clark 3,4 Elisabeth Roberts 5 Tilo Burghardt 1 Otto Brookes 1 * Stuart Gray 2 Peter Bennett 1 Katy V. ![]()
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |