Scopus Indexed Paper

Paper Details


Title
Classification on BDHS data analysis: Hybrid approach for predicting pregnancy termination
Abstract
Pregnancy termination is a trivial anomaly for third world countries like Bangladesh. The greater aspiration of this research is to downturn the rate of pregnancy termination. This research finds out the attributes that contribute to pregnancy termination and leads to propose a hybrid of supervised machine learning approach for predicting “Pregnancy Termination” in Bangladesh. The Bangladesh Demographic and Health Survey (BDHS), 2014 dataset has been used to perform analysis containing two or more variables. This dataset is further reduced by analyzing attributes that exhibit information of interest to explore the current reasons for pregnancy termination. After extracting out the features of interest with the help of Weka provided feature ranking attribute evaluator, hybridization of supervised machine learning classifiers are done concerning the negatively biasedness of the dataset with respect to pregnancy termination. On this investigation, we've developed a hybrid approach with 67.2% accuracy considering the biasedness of the dataset which is relatively better than other classifiers in terms of performance metrics.
Keywords
Machine learning, Pregnancy, Bayes methods, Training, Feature extraction, Hafnium, Logistics
Authors
Faisal Ahmed, Md. Montasir Bin Shams, Pintu Chandra Shill, Majidur Rahman
Phone
Journal or Conference Name
2nd International Conference on Electrical, Computer and Communication Engineering, ECCE 2019
Publish Year
2019
Indexing
Scopus