Browsing by Author "Mwanga, Gladness"

Now showing 1 - 2 of 2

How Information Communication Technology Can Enhance Evidence-Based Decisions and Farm-to-Fork Animal Traceability for Livestock Farmers
(Hindawi, 2020-12-17) Mwanga, Gladness; Mbega, Ernest; Yonah, Zaipuna; Chagunda, Gift
Due to changes in the livestock sector and the rise of consumer demand for comprehensive and integrated food security and safety, there has been a concern on the use of farm data in enhancing animal traceability and decision-making by farmers and other decision-makers in the livestock sector. To ensure high production through effective decision-making and auditable standards, producers are required to have better traceability and record systems. Therefore, this study aimed at (1) reviewing the current recording/data management and animal traceability systems used by small-scale farmers in developing countries and (2) analyzing how data management systems should be designed to enhance efficient decision-making and animal traceability from farm to fork. This study found that, still, a majority of small-scale farmers do not keep records leading to poor decision-making on the farm and policymaking. We also found that those who keep records do not store their data in electronic format, which again poses another challenge in data analysis. Moreover, this study found that the majority of traceability tools used by farmers in developing countries do not meet international standards based on tools they use for tracing animals; farmers were reported to use tools like branding and ear tagging, which provide very little information about the animal. Such tools lack the capability to keep track of useful information about an animal, e.g., information about feeding and animal health. In conclusion, this study recommended a better electronic system to be used at the farm level to facilitate data analysis, hence promoting informed decision-making and adherence to the international animal traceability standards. Otherwise, there is a need for researchers to conduct more studies in developing different analytical models for exploring on-farm data in order to improve the decision- making process by farmers and other stakeholders
Machine learning models for predicting the use of different animal breeding services in smallholder dairy farms in Sub-Saharan Africa.
(Springer Nature Switzerland AG., 2020-05-01) Mwanga, Gladness; Lockwood, Sarah; Mujibi, D F N; Yonah, Zaipuna; Chagunda, M G G
This study is concerned with developing predictive models using machine learning techniques to be used in identifying factors that influence farmers' decisions, predict farmers' decisions, and forecast farmers' demands relating to breeding service. The data used to develop the models comes from a survey of small-scale dairy farmers from Tanzania (n = 3500 farmers), Kenya (n = 6190 farmers), Ethiopia (n = 4920 farmers), and Uganda (n = 5390 farmers) and more than 120 variables were identified to influence breeding decisions. Feature engineering process was used to reduce the number of variables to a practical level and to identify the most influential ones. Three algorithms were used for feature selection, namely: logistic regression, random forest, and Boruta. Subsequently, six predictive models, using features selected by feature selection method, were tested for each country-neural network, logistic regression, K-nearest neighbor, decision tree, random forest, and Gaussian mixture model. A combination of decision tree and random forest algorithms was used to develop the final models. Each country model showed high predictive power (up to 93%) and are ready for practical use. The use of ML techniques assisted in identifying the key factors that influence the adoption of breeding method that can be taken and prioritized to improve the dairy sector among countries. Moreover, it provided various alternatives for policymakers to compare the consequences of different courses of action which can assist in determining which alternative at any particular choice point had a high probability to succeed, given the information and alternatives pertinent to the breeding decision. Also, through the use of ML, results to the identification of different clusters of farmers, who were classified based on their farm, and farmers' characteristics, i.e., farm location, feeding system, animal husbandry practices, etc. This information had significant value to decision-makers in finding the appropriate intervention for a particular cluster of farmers. In the future, such predictive models will assist decision-makers in planning and managing resources by allocating breeding services and capabilities where they would be most in demand.