May 27, 2024 Thesis Open Access

Asmamaw Mekure Ingdayehu

Citation Style Language JSON Export

{
  "DOI": "10.20372/nadre:10417", 
  "author": [
    {
      "family": "Asmamaw Mekure Ingdayehu"
    }
  ], 
  "issued": {
    "date-parts": [
      [
        2024, 
        5, 
        27
      ]
    ]
  }, 
  "abstract": "<p>This thesis(paper) explores the prediction of breastfeeding practices in Ethiopia using ensemble machine learning algorithms. Exclusive breastfeeding (EBF) is crucial for(to) infant health and well-being, and understanding the factors influencing breastfeeding behaviors is vital for public health interventions. The novelty of the study lies in its use of ensemble machine learning algorithms, its focus on the Ethiopian context, and its potential policy implications for healthcare professionals and policymakers. Ensemble learning is a machine learning technique that enhances accuracy and resilience in forecasting by merging predictions from multiple models. The main idea of Ensemble learning is to combine the results of different models to produce more accurate predictions. By analyzing data from the Ethiopian Demographic and Health Survey, preprocessing, and utilizing techniques like the Bagging Meta-Estimator Algorithm, Random Forest Algorithm, Gradient Boosting Algorithm, AdaBoost Algorithm, KNeighbors Classifier Algorithm, Logistic Regression Algorithm, and CatBoost Algorithm., the study aims to enhance prediction accuracy. Evaluation metrics include accuracy, precision, recall, and F1-score and this study used a crossvalidation technique is k-fold cross-validation, where the data is divided into k equally sized folds. The model is trained on k-1 folds and evaluated on the remaining fold, and this process is repeated k times, with each fold serving as the evaluation set once. the feature importance for a machine learning model, likely the Random Forest Classifier mentioned in this study. The feature importances represent the relative contribution of each feature to the model&#39;s predictive performance. This study used k-fold cross-validation, the given data is divided into k equally sized folds. The model is trained on k-1 folds and evaluated on the remaining fold, and this process is repeated k times, with each fold serving as the evaluation set once. The user interface is also implemented to provide a user-friendly way to access the model&#39;s predictions without requiring deep technical knowledge. the study also recommends targeted interventions to improve breastfeeding rates in Ethiopia and enhance infant health. This thesis contributes to the existing body of knowledge and sets the stage for future research and interventions in breastfeeding practices.<br>\n&nbsp;</p>", 
  "title": "Predicting and Analyzing Factors Influencing Breastfeeding Practices in Ethiopia Using Ensemble Machine Learning Algorithms", 
  "type": "thesis", 
  "id": "10417"
}