Abstract
Predicting the pregnancy termination and controlling the child mortality rate has always been a great challenge for third world country. This research targets to extract out best subset of features to predict pregnancy termination more accurately relative to previous researches. To facilitate this noble purpose, we have carried out an extensive research on Bangladesh Demographic and Health Survey (BDHS) 2014, that find out the most contributing attributes of pregnancy termination in Bangladesh. Bivariate and multivariate analyses on this data shows interesting details to find out the recent causes for pregnancy termination. However, for finding out the intended features first demographically feature selection performed with Weka provided visualization tools and secondly Weka provided feature ranking attribute evaluators such as Correlation, Gain Ratio, One R, Symmetrical Uncertainty, Information Gain, Relief are used. After minimizing the subset of features, we apply three traditional machine learning classifiers (Naïve Byes, Bayesian Network, Decision Stump) along with the hybrid method which shows better performance in terms of performance metrics. This research improved accuracy 10.238% for Naïve Byes, 8.2657% for Bayesian Network, 3.5853% for Decision Stump and 9.03% for Hybrid.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ahmed, F., Shams, M.M.B., Shill, P.C., Rahman, M.: Classification on BDHS data analysis: hybrid approach for predicting pregnancy termination. In: 2nd International Conference on Electrical, Computer and Communication Engineering (ECCE), pp. 1–6. IEEE, Cox’s Bazar, Bangladesh (2019). https://doi.org/10.1109/ecace.2019.8679302
Lawn, J.E., Cousens, S., Zupan, J.: 4 Million neonatal deaths: When? Where? Why? Lancet 365(9462), 891–900 (2005)
Kerber, K.J., de Graft-Johnson, J.E., Bhutta, Z.A., Okong, P., Starrs, A., Lawn, J.E.: Continuum of care for maternal, newborn, and child birth: from slogan to service delivery. Lancet 370, 1358–1369 (2007)
Boetticher, G., Menzies, T., Ostrand, T.: Promise repository of empirical software engineering data. West Virginia University, Department of Computer Science (2007). http://promisedata.org/repository
Cameron, A.C., Trivedi, P.K.: Regression analysis of count data. 2nd edn, Econometric Society Monograph No. 53, Cambridge University Press, NY, USA (1998)
Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. J. Mach. Learn. Res. 3, 1157–1182 (2003)
Ghosh, P., Hasan, M.Z., Jabiullah, M.I.: A comparative study of machine learning approaches on dataset to predicting cancer outcome. J. Bangladesh Electron. Soc. 18(1–2), 81–86 (2018)
Liu, H., Yu, L.: Toward integrating feature selection algorithms for classification and clustering. IEEE Trans. Knowl. Data Eng. 17(4), 491–502 (2005). https://doi.org/10.1109/TKDE.2005.66
Hall, M.A., Holmes, G.: Benchmarking attribute selection techniques for discrete class data mining. IEEE Trans. Knowl. Data Eng. 15(6), 1437–1447 (2003). https://doi.org/10.1109/TKDE.2003.1245283
Jong, K., Marchiori, E., Sebag, M., van der Vaart, A.: Feature selection in proteomic pattern data with support vector machines. In: Proceedings of the 2004 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, pp. 41–48. IEEE, La Jolla, CA, USA (2004). https://doi.org/10.1109/cibcb.2004.1393930
Ilczuk, G., Mlynarski, R., Kargul, W., Wakulicz-Deja, A.: New feature selection methods for qualification of the patients for cardiac pacemaker implantation. In: Computers in Cardiology, vol. 200, pp. 423–426, IEEE, Durham, NC, USA (2007)
de Souza, J.T., Japkowicz, N., Matwin, S.: STochFS: a framework for combining feature selection outcomes through a stochastic process. In: 9th European Conference on Principles and Practice of Knowledge Discovery in Databases on Proceedings, Porto, Portugal, Oct 3–7, 2005, pp. 667–674
Islam, A.Z., Mondol, M.N.I., Islam, M.R.: Prevalence and determinants of contraceptive use among employed and unemployed women in Bangladesh. Int. J. MCH AIDS 5(2), 92–102 (2016). https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5187648/
Kamal, S.M.M.: Domestic violence, unwanted pregnancy and pregnancy termination among Urban women of Bangladesh. J. Fam. Reprod. Health 7(1), 11–22 (2013)
Cherkassky, V., Mulier, F.M.: Learning from Data: Concepts, Theory, and Methods. 2nd edn, Wiley—IEEE Press (2007)
Wozniak, M.: Hybrid Classifiers: Methods of Data, Knowledge, and Classifier Combination. Studies in Computational Intelligence, vol. 519. Springer (2014)
Brazdil, P., Giraud-Carrier, C., Soares, C., Vilalta, R.: Metalearning: Applications to Data Mining. Springer (2009)
Rajaraman, A., Leskovec, J., Ullman, J.D.: Mining of Massive Datasets, 1st edn. Cambridge University Press, NY, USA (2011)
Fayyad, U.M., Irani, K.B.: Multi-interval discretization of continuous valued attributes for classification learning. In: 13th International Join Conference on Artificial Intelligence, Vol. 2, pp. 1022–1027, Morgan Kaufmann, Chambe’ry, France (1993)
Roobaert,D., Karakoulas, G., Chawla, N.V.: Information gain, correlation and support vector machines. In: Guyon I., Nikravesh M., Gunn S., Zadeh L.A. (eds.) Feature Extraction. Studies in Fuzziness and Soft Computing, vol. 207. Springer, Berlin, Heidelberg (2006). https://doi.org/10.1007/978-3-540-35488-8_23
Rajaraman, A., Leskovec, J., Ullman, J.D.: Mining of Massive Datasets. Cambridge University Press (2011)
Iba, W.F., Langley, P.: Induction of one-level decision trees. In: Sleeman, D., Edwards, P. (eds.) Proceedings of the Ninth International Conference on Machine Learning, San Mateo, CA: Morgan Kaufmann, pp. 233–240 (1992)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Ahmed, F., Shultana, S., Yasmin, A., Prome, J.F. (2021). Minimizing the Subset of Features on BDHS Dataset to Improve Prediction on Pregnancy Termination. In: Sharma, H., Saraswat, M., Yadav, A., Kim, J.H., Bansal, J.C. (eds) Congress on Intelligent Systems. CIS 2020. Advances in Intelligent Systems and Computing, vol 1335. Springer, Singapore. https://doi.org/10.1007/978-981-33-6984-9_6
Download citation
DOI: https://doi.org/10.1007/978-981-33-6984-9_6
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-33-6983-2
Online ISBN: 978-981-33-6984-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)