Family planning gives the population a license to have control over its reproductive health and ultimately family size. A better understanding, therefore, of its determinants to its uptake is a necessity. The project embarked on determining these factors. It was observed that parity, marital status, age, residence, general health of an individual, education level, wealth status, and family planning awareness are significant factors that determine modern contraception. The number of children one has or is planning to have greatly impacted the use of the different modes of contraception. This research’s main objective was to formulate and implement a cross-validated RFE-NB classifier on modern contraceptive data and compare its performance to that of RFE-SVM. A recursive feature elimination technique trained on the data and important features responsible for modern contraception identified. The naive Bayes classifier was then used for classification. The data was also used to train an RBF kernel SVM classifier. A comparative analysis was then done on the two models. Considering the findings, we conclude that the RFE-NB model has a relatively high accuracy of 81%, which, however, is lower when compared to that of RFE-SVM. The high Kappa value further underscores its reliability in distinguishing between different classes. The RFE-NB exhibits strong accuracy, sensitivity, and specificity, making it a valuable tool for accurate prediction and classification tasks.
| Published in | American Journal of Nursing and Health Sciences (Volume 5, Issue 1) |
| DOI | 10.11648/j.ajnhs.20240501.11 |
| Page(s) | 1-8 |
| Creative Commons |
This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited. |
| Copyright |
Copyright © The Author(s), 2024. Published by Science Publishing Group |
Modern Contraception, Childbearing Women, Recursive Feature Elimination, Naïve Bayes, Support Vector Machine
| [1] | Cleland, J. G., Ndugwa, R. P., & Zulu, E. M. (2011). Family planning in subsaharan africa: Progress or stagnation? Bulletin of the World Health Organization, 89 (2), 137–143. |
| [2] | Darst, B. F., Malecki, K. C., & Engelman, C. D. (2018). Using recursive feature elimination in random forest to account for correlated variables in high dimensional data. BMC genetics, 19 (1), 1–6. |
| [3] | Davenport, T., & Kalakota, R. (2019). The potential for artificial intelligence in healthcare. Future healthcare journal, 6 (2), 94. |
| [4] | Leung, K. M., et al. (2007). Naive bayesian classifier. Polytechnic University Department of Computer Science/Finance and Risk Engineering, 2007, 123– 156. |
| [5] | Loucks, J., Davenport, T., & Schatsky, D. (2018). State of ai in the enterprise. Deloitte Insights Report. |
| [6] | Marston, L. (2010). Introductory statistics for health and nursing using spss. Sage Publications. |
| [7] | Nasien, D., Yuhaniz, S. S., & Haron, H. (2010). Statistical learning theory and support vector machines. 2010 Second International Conference on Computer Research and Development, 760–764. |
| [8] | Negash, W. D., Eshetu, H. B., & Asmamaw, D. B. (2022). Predictors of modern contraceptive use among reproductive age women in high fertility countries in sub-saharan africa: Evidence from demographic and health surveys. BMC Women’s Health, 22 (1), 1–10. |
| [9] | Qteat, H., & Awad, M. (2021). Using hybrid model of particle swarm optimization and multi-layer perceptron neural networks for classification of diabete. Int. J. Intell. Eng. Syst, 14 (3), 11–22. |
| [10] | Rish, I., et al. (2001). An empirical study of the naive bayes classifier. IJCAI 2001 workshop on empirical methods in artificial intelligence, 3 (22), 41–46. |
| [11] | Webb, G. I., Keogh, E., & Miikkulainen, R. (2010). Naıve bayes. Encyclopedia of machine learning, 15, 713–714. |
APA Style
Bor, L. K., Wanjoya, A., Mwalili, S., Kirui, D. (2024). Recursive Feature Elimination with Naive Bayes Classification of Modern Contraception in Reproductive-Aged Women in Kenya. American Journal of Nursing and Health Sciences, 5(1), 1-8. https://doi.org/10.11648/j.ajnhs.20240501.11
ACS Style
Bor, L. K.; Wanjoya, A.; Mwalili, S.; Kirui, D. Recursive Feature Elimination with Naive Bayes Classification of Modern Contraception in Reproductive-Aged Women in Kenya. Am. J. Nurs. Health Sci. 2024, 5(1), 1-8. doi: 10.11648/j.ajnhs.20240501.11
AMA Style
Bor LK, Wanjoya A, Mwalili S, Kirui D. Recursive Feature Elimination with Naive Bayes Classification of Modern Contraception in Reproductive-Aged Women in Kenya. Am J Nurs Health Sci. 2024;5(1):1-8. doi: 10.11648/j.ajnhs.20240501.11
Share This Article
Twitter
Linked In
Facebook
Copy
Download@article{10.11648/j.ajnhs.20240501.11,
author = {Levi Kiplang’at Bor and Anthony Wanjoya and Samuel Mwalili and Dennis Kirui},
title = {Recursive Feature Elimination with Naive Bayes Classification of Modern Contraception in Reproductive-Aged Women in Kenya},
journal = {American Journal of Nursing and Health Sciences},
volume = {5},
number = {1},
pages = {1-8},
doi = {10.11648/j.ajnhs.20240501.11},
url = {https://doi.org/10.11648/j.ajnhs.20240501.11},
eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajnhs.20240501.11},
abstract = {Family planning gives the population a license to have control over its reproductive health and ultimately family size. A better understanding, therefore, of its determinants to its uptake is a necessity. The project embarked on determining these factors. It was observed that parity, marital status, age, residence, general health of an individual, education level, wealth status, and family planning awareness are significant factors that determine modern contraception. The number of children one has or is planning to have greatly impacted the use of the different modes of contraception. This research’s main objective was to formulate and implement a cross-validated RFE-NB classifier on modern contraceptive data and compare its performance to that of RFE-SVM. A recursive feature elimination technique trained on the data and important features responsible for modern contraception identified. The naive Bayes classifier was then used for classification. The data was also used to train an RBF kernel SVM classifier. A comparative analysis was then done on the two models. Considering the findings, we conclude that the RFE-NB model has a relatively high accuracy of 81%, which, however, is lower when compared to that of RFE-SVM. The high Kappa value further underscores its reliability in distinguishing between different classes. The RFE-NB exhibits strong accuracy, sensitivity, and specificity, making it a valuable tool for accurate prediction and classification tasks.},
year = {2024}
}
TY - JOUR T1 - Recursive Feature Elimination with Naive Bayes Classification of Modern Contraception in Reproductive-Aged Women in Kenya AU - Levi Kiplang’at Bor AU - Anthony Wanjoya AU - Samuel Mwalili AU - Dennis Kirui Y1 - 2024/01/08 PY - 2024 N1 - https://doi.org/10.11648/j.ajnhs.20240501.11 DO - 10.11648/j.ajnhs.20240501.11 T2 - American Journal of Nursing and Health Sciences JF - American Journal of Nursing and Health Sciences JO - American Journal of Nursing and Health Sciences SP - 1 EP - 8 PB - Science Publishing Group SN - 2994-7227 UR - https://doi.org/10.11648/j.ajnhs.20240501.11 AB - Family planning gives the population a license to have control over its reproductive health and ultimately family size. A better understanding, therefore, of its determinants to its uptake is a necessity. The project embarked on determining these factors. It was observed that parity, marital status, age, residence, general health of an individual, education level, wealth status, and family planning awareness are significant factors that determine modern contraception. The number of children one has or is planning to have greatly impacted the use of the different modes of contraception. This research’s main objective was to formulate and implement a cross-validated RFE-NB classifier on modern contraceptive data and compare its performance to that of RFE-SVM. A recursive feature elimination technique trained on the data and important features responsible for modern contraception identified. The naive Bayes classifier was then used for classification. The data was also used to train an RBF kernel SVM classifier. A comparative analysis was then done on the two models. Considering the findings, we conclude that the RFE-NB model has a relatively high accuracy of 81%, which, however, is lower when compared to that of RFE-SVM. The high Kappa value further underscores its reliability in distinguishing between different classes. The RFE-NB exhibits strong accuracy, sensitivity, and specificity, making it a valuable tool for accurate prediction and classification tasks. VL - 5 IS - 1 ER -
Department of Statistics and Actuarial Science, Jomo Kenyatta University of Agriculture and Technology (JKUAT), Nairobi, Kenya
Department of Statistics and Actuarial Science, Jomo Kenyatta University of Agriculture and Technology (JKUAT), Nairobi, Kenya
Department of Statistics and Actuarial Science, Jomo Kenyatta University of Agriculture and Technology (JKUAT), Nairobi, Kenya
Department of Statistics and Actuarial Science, Jomo Kenyatta University of Agriculture and Technology (JKUAT), Nairobi, Kenya
Information