Birth weight prediction of new born baby with application of machine learning techniques on features of mother. Issue 6 (17th August 2020)

• Record Type: Journal Article
• Authors: Hussain, Zakir; Borah, Malaya Dutta
• Is Part Of: Journal of statistics & management systems. Volume 23:Issue 6(2020)
• Page Start: 1079
• Page End: 1091
• Publication Date: 2020-08-17
• Subjects: 68Q32; Birth weight prediction -- Gaussian naïve bayes -- Random forest -- Features of mother -- Malnutrition -- Under-nutrition -- Nutritional status; Statistics -- Periodicals; Mathematical models -- Periodicals; Mathematical models; Statistics; Periodicals; 519.5
• DOI: 10.1080/09720510.2020.1814499
• Languages: English
• ISSNs: 0972-0510

Abstract

Abstract: The degree of malnutrition is very high in India. Early detection of the possibility for a child to be affected by malnutrition can combat the situation to some extent. Birth weight prediction of new born baby is necessary as parent and doctors can prepare themselves for precautionary and curative measures for the development of physical and mental health. In this study, birth weight prediction of new born baby has been carried out using two machine learning techniques called Gaussian Naïve Bayes and Random Forest. These two models have been trained and tested on a self-created dataset containing 445 instances with eighteen numbers of features of mother. The dataset contains a label with two classes: low-weight and normal-weight. We got 86% accuracy for Gaussian Naïve Bayes and 100% accuracy for Random Forest. Both the techniques have shown significant improvement compared to existing studies.