Preterm Birth Prediction using Hybrid Ant Colony-Genetic Optimization Algorithm in Data Mining
M. Varusai Mohamed1, P. Mayilvahanan2
1M. Varusai Mohamed, Research Scholar, School of Computing Science, VISTAS ( Vels University),Chennai, India.
2Dr. P. Mayilvahanan, Research Supervisor, Department of Computer Application, VISTAS (Vels University), Chennai, India.
Manuscript received on December 14, 2019. | Revised Manuscript received on December 22, 2019. | Manuscript published on January 10, 2020. | PP: 3157-3160 | Volume-9 Issue-3, January 2020. | Retrieval Number: C8832019320/2020©BEIESP | DOI: 10.35940/ijitee.C8832.019320
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Many data mining (DM) methods are used to explore the risk factors of Preterm birth (PTB) and to predict preterm birth. High rates of infant mortality, preterm births and maternal mobility and continuous variation in pregnancy outcomes are an important public health issue in India and worldwide. In this paper, aims to develop and evaluate prevent factors of preterm birth using hybrid algorithm which is optimized the model with genetic algorithm and ant bee colony algorithm based also analysis of risk factor of preterm birth prediction. It is identified that variables which were highly influenced to forecast less weight child birth are Mother’s weight (pounds) before pregnant, age of Mother, during first three months the number of physician meet, number of early premature labors. The results of this work have improved prediction accuracy when compared with other optimization techniques. Maximum accuracy of 0.9629 is produced in proposed method.
Keywords: Preterm Birth, Optimization, Classification, Accuracy, Iteration
Scope of the Article: Classification