Browsing by Author "Emsen, Ebru"

Now showing 1 - 4 of 4

Citation Count: 1
Machine Learning Algorithms for Lamb Survival
(ELSEVIER SCI LTD, 2021-03) Emsen, Ebru; Aydın, Man Nuri; Ödevci, Bahadır
Lamb survival is influenced by the culmination of a sequence of often interrelated events including genetics, physiology, behaviour and nutrition, with the environment providing an overarching complication. Machine learning algorithms offer great flexibility with regard to problems of complex interactions among variables. The objective of this study was to use machine learning algorithms to identify factors affecting the lamb survival in high altitudes and cold climates. Lambing records were obtained from three native breed of sheep (Awassi = 50, Morkaraman = 50, Tuj = 50) managed in semi intensive systems. The data set included 193 spring born lambs out of which 106 lambs were sired by indigenous rams (n = 10), and 87 lambs were sired by Romanov Rams (n = 10). Factors included were dam body weight at lambing, age of dam, litter size at birth, maternal and lamb be-haviors, and lamb sex. Individual and cohort data were combined into an original dataset containing 1351 event records from 193 individual lambs and 750 event records from 150 individual ewes. Classification algorithms applied for lamb survival were Bayesian Methods, Artificial Neural Networks, Support Vector Machine and Decision Trees. Variables were categorized for lamb survival, lamb behavior, and mothering ability. Random-Forest performed very well in their classification of the mothering ability while SMO was found best in predicting lamb behavior. REPtree tree visualization showed that grooming behavior is the first determinant for mothering ability. Classification Trees performed best in lamb survival. Our results showed that Classification Trees clearly outperform others in all traits included in this study.
Citation Count: 0
Machine Learning Model for Maternal Quality in Sheep
(Organising Committee of the 9th European Conference on Precision Livestock Farming (ECPLF), Teagasc, Animal and Grassland Research and Innovation Centre, 2019) Ödevci, Bahadır; Emsen, Ebru
This paper aims to identify determinant traits of ewes by measuring their impact on lamb survival. For that, we devised a machine learning model that correlates ewe traits to lamb survival, and figured out as to which ewe traits explain the correlation and hence help us to identify the better mother. In this study, we kept pregnant ewes under 24 h observation by two researchers starting approximately three days before expected parturition dates. We conducted the study using native and crossbreed lambs produced in high altitude and cold climate region. It is critical to note that parturation took place with minimum interruption unless there is a birth difficulty. Independent variables used in the machine learning model pertain to mother's behaviours during parturation, however, we also took into consideration factors like dam breed, dam body weight at lambing, age of dam, litter size at birth, lamb breed and sex. Lamb survival is a nominal output variable, hence we tried out several classification algorithms like Bayesian Methods, Artificial Neural Networks, Support Vector Machine and Tree Based Algorithms. Classification algorithms applied for lamb survival were Bayesian Methods, Artificial Neural Networks, Support Vector Machine and Trees. RandomForest algorithm was found best performer among tree algorithms. We were able to present tree visualisation for mothering ability with 80% accuracy rate and 0.43 Kappa Statistics. The result of the study shows that grooming behaviour is the first determinant mothering ability. If the grooming duration is longer than 15 minutes, then it is a good mother.
Citation Count: 0
Mobile Precision Flock Management Tool for Intensively Managed Meat Sheep
(Organising Committee of the 9th European Conference on Precision Livestock Farming (ECPLF), Teagasc, Animal and Grassland Research and Innovation Centre, 2019) Emsen, Ebru; Ödevci, Bahadır
A Mobile Sheep Manager Software (M-SMS) was developed for commercial lamb production model using cloud architecture that collects and utilises farm data and responds to the farm management with respect to insights on the operational and financial aspects of the farm. Metadata used in the software is composed of ewe reproductive performance, overall productivity, lamb growing rate, survival rate of newborns, and health status of flock. The system detects alerts occurring in the farm and suggests for troubleshooting. M-SMS was combined with Cloud Services compounded with Predictive Analytics Services for helping fine-tune flock management and improve operational excellence. Mobile Sheep Manager Software is aimed at sheep farmers who need an easy to use “point and click” solution to keep legislative records, to attain operational guidance and build flock performance data. The product supports for purchase, cull or breed decisions are based on targets of flock performance.
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.