Doktora Tezleri

Permanent URI for this collectionhttps://hdl.handle.net/20.500.12469/7776

Browse

Browsing Doktora Tezleri by Subject "Agriculture"

Filter results by typing the first few letters
Now showing 1 - 1 of 1
  • Thumbnail Image
    Doctoral Thesis
    Proposing a Model for Precision Management Supervised With Machine Learning in Livestock Management
    (Kadir Has Üniversitesi, 2021) Ödevci, Bahadır Baran; Emsen, Ebru; Aydın, Mehmet Nafiz
    The global demand for meat is predicted to rise by 40% in the next 15 years, owing to an increase in the number of people adopting protein-richer diets, and technology solutions in agricultural and livestock production systems are likely to play a vital role in addressing this issue. On the other hand, while expanding meat output, it will be critical to discover ways to reduce livestock farming's environmental footprint and assure high levels of animal care and health. In this thesis, we aim to propose a model and approach along with a number of steps to follow for a livestock farm to adapt an information management system to attain optimum production efficiency. We are seeking answers to respond to the following research question: How can a livestock farm utilize information management systems for optimum efficiency? In order to expand the research on a specific livestock case study, we focus on intensively managed sheep for lamb production. However, the model and approach proposed in this thesis can be applicable to any livestock farming that aims to utilize information systems for precision management of farm operations. First, we reviewed scientific research related to long-standing, novel-technology, and data sensors with emphasis on data-information-knowledge-wisdom and decision-making processes and for intensively managed sheep for lamb production. Secondly, we addressed what data elements exist in the context of a livestock farm and how data elements in the context of livestock farms are associated. Special attention was given to the data model of the farm context for managerial precision livestock farming (PLF) systems. Thirdly, we proposed the decision-making points supervised by machine learning models in a PLF management information system for intensively managed sheep for lamb production. At this point, we developed and adapted a Mobile Sheep Manager Software (M-SMS) for a commercial lamb production model using an appropriate cloud architecture that collects and utilizes farm data and responds to the farm management with respect to insights into the operational and financial aspects of the farm. The technology identifies real-time alarms pertaining to animal welfare, health, environmental effects, and production on the farm and provides troubleshooting recommendations. We also looked at its suitability for user experience as well as its impact on farm profitability and sustainability. This research has shown that M-SMS combined with cloud services compounded with Predictive Analytics Services can fine-tune flock management and significantly improve operational excellence. According to the usability results, intensive sheep farmers had access to "point and click" solutions to keep legislative records, attain operational guidance and build flock performance data. Finally, we propose a model and steps to follow to adapt the information management system to any livestock management system in order to attain optimum efficiency. It was concluded that the architecture of this application can be easily adapted to other intensively managed livestock if the steps in this study are followed precisely.