Pregnancy Growth Data Analytics Using Correlated Antlion Optimized Tangent Approximated Extreme Gradient Learning

Pregnancy difficulties crucially influence women and give rise to inherent menaces to the child's health development. Early recognition of these difficulties is vitally important for life-saving interventions. Taking into consideration that was hinted at above, cardio toco grams (CTGs) are a straightforward and cost penetrable alternative to assess fetal health via pregnancy growth status data analytics permitting healthcare professionals to take preventive action with the objective of preventing child and maternal mortality. Here using the Extreme Gradient Machine Learning that works as gradient descent in function space aids in faster convergence and accordingly classification is made into either normal, suspect or pathological. Simulations will be performed to validate the proposed CAO-TAEGL method in Python language in precision, recall, f-measure, accuracy, training time using the fetal health classification dataset.