Fetal health monitoring is essential as it leads to increased mortality rates in fetuses. Cardiotocography is a medical technique used by obstetricians to monitor fetal health during labor, particularly in cases involving complications. Though various works have been carried out in the classification of CTG data there seems to be a need for improvement in achieving significant accuracy levels. In this work, first, we implemented the Smote Tomek sampling technique to create a balanced dataset. Then, the balanced data is employed for classification in the Random Forest ensemble with a bagging classifier. Our technique's performance is assessed using metrics including accuracy, precision, recall, and F1-score. Experimental findings reveal our method achieves an accuracy of 98.5%, outperforming not only other classifiers examined in the study but also surpassing deep learning algorithms. Hence, thefindings of our study highlight the effectiveness of our approach in classifying Cardiotocography data, suggesting the potential for enhancing fetal health monitoring during labor and for improved obstetric care.