Perbandingan Kinerja Hybrid Classification SVM-RF dan SVM-NN Terhadap Faktor Risiko Anemia Ibu Hamil di Indonesia dengan Pendekatan Clustering K-Means
DOI:
https://doi.org/10.12962/limits.v22i3.8862Keywords:
Hybrid, Klasifikasi, SVM-RF, SVM-NN, AnemiaAbstract
Klasifikasi merupakan salah satu topik yang paling banyak diteliti oleh para peneliti dari bidang machine learning dan data mining. Metode machine learning yang sering digunakan antara lain Support Vector Machine (SVM), Random Forest (RF) dan Neural Network (NN). Namun, SVM tidak selalu memberikan nilai akurasi yang baik. Sebagai contoh, ketika diterapkan pada data yang sangat tidak seimbang, SVM akan mengalami tantangan. Selain itu, tidak terdapat satu metode terbaik yang bisa diterapkan untuk semua masalah klasifikasi. Saat ini, pendekatan metode hybrid untuk penggunaan data mining menjadi semakin populer seperti metode hybrid SVM-RF, SVM-NN dan KMeans-SVM. Pada penelitian ini, metode hybrid SVM-RF dan SVM-NN digunakan untuk mengklasifikasikan faktor risiko anemia pada ibu hamil di Indonesia dengan pendekatan K-Means untuk mengelompokkan data yang salah klasifikasi oleh SVM. Hasil penelitian menunjukkan bahwa metode hybrid dapat meningkatkan kinerja model SVM. Hybrid SVM-RF memberikan nilai metrik evaluasi yang lebih tinggi dibandingkan dengan SVM-NN. Empat metrik evaluasi yang digunakan, yaitu accuracy, balanced accuracy, sensitivity dan specificity pada SVM-RF masing-masing bernilai sebesar 0,989; 0,989; 0,988; dan 0,989. Peubah yang berkontribusi secara umum berdasarkan SHAP Global terhadap klasifikasi faktor risiko anemia pada ibu hamil secara berurutan adalah Usia, Tablet Fe, Status Bekerja, Pendidikan, Status Gizi dan ANC
References
[1] A. A. Soofi and A. Awan, “Classification Techniques in Machine Learning: Applications and Issues,” Journal of Basic & Applied Sciences, vol. 13, pp. 459–465, 2017.
[2] F. Y. Osisanwo, J. E. T. Akinsola, O. Awodele, J. O. Hinmikaiye, O. Olakanmi, and J. Akinjobi, “Supervised Machine Learning Algorithms: Classification and Comparison,” International Journal of Computer Trends and Technology, vol. 48, no. 3, pp. 128–138, 2017, doi: 10.14445/22312803/ijctt-v48p126.
[3] J. Dj Novakovi, A. Veljovi, S. S. Ili, ˇ Zeljko Papi, and M. Tomovi, “Evaluation of Classification Models in Machine Learning,” Theory and Applications of Mathematics & Computer Science, vol. 7, no. 1, pp. 39–46, 2017.
[4] S. Naeem, A. Ali, S. Anam, and M. M. Ahmed, “An Unsupervised Machine Learning Algorithms: Comprehensive Review,” International Journal of Computing and Digital Systems, vol. 13, no. 1, pp. 911–921, 2023, doi: 10.12785/ijcds/130172.
[5] B. Mahesh, “Machine Learning Algorithms - A Review,” International Journal of Science and Research (IJSR), vol. 9, no. 1, pp. 381–386, 2020, doi: 10.21275/ART20203995.
[6] M. Minghui and Z. Chuanfeng, “Application of Support Vector Machines to a Small-Sample Prediction,” Advances in Petroleum Exploration and Development, vol. 10, no. 2, pp. 72–75, 2015, doi: 10.3968/7830.
[7] B. Raj S., S. L. Gibson Moses, G. Chinnadurai, J. V. Anand, V. Janakiraman, and P. Anand, “Support Vector Machine for Image Classification,” Journal of the Asiatic Society of Mumbai, vol. 97, no. 4, pp. 1–10, 2023, [Online]. Available: https://www.researchgate.net/publication/371492398
[8] S. Annisa, A. Saefuddin, and Erfiani, “Blood Glucose Levels of Non Invasive Tool Using Support Vector Machine on Multi-Class Imbalanced Data,” Int J Sci Eng Res, vol. 9, no. 11, pp. 1649–1652, 2018.
[9] Y. D. Evitasari, W. J. Pranoto, and N. A. Verdikha, “Evaluasi Support Vector Machine Dengan Optimasi Metode Genetic Algorithm Pada Klasifikasi Banjir Kota Samarinda,” Jurnal Sains Komputer dan Teknologi Informasi, vol. 6, no. 1, pp. 49–53, 2023, doi: 10.33084/jsakti.v6i1.5462.
[10] S. Rezvani, F. Pourpanah, C. P. Lim, and Q. M. J. Wu, “Methods for class-imbalanced learning with support vector machines: a review and an empirical evaluation,” Soft comput, 2024, doi: 10.1007/s00500-024-09931-5.
[11] R. Guido, S. Ferrisi, D. Lofaro, and D. Conforti, “An Overview on the Advancements of Support Vector Machine Models in Healthcare Applications: A Review,” Information (Switzerland), vol. 15, no. 4, 2024, doi: 10.3390/info15040235.
[12] L. A. Demidova, I. A. Klyueva, and A. N. Pylkin, “Hybrid approach to improving the results of the SVM classification using the random forest algorithm,” Procedia Comput Sci, vol. 150, pp. 455–461, 2019, doi: 10.1016/j.procs.2019.02.077.
[13] R. Li, H. N. Wang, H. He, Y. M. Cui, and Z. Le Du, “Support vector machine combined with K-nearest neighbors for solar flare forecasting,” Chinese Journal of Astronomy and Astrophysics, vol. 7, no. 3, pp. 441–447, 2007, doi: 10.1088/1009-9271/7/3/15.
[14] G. W. Cha, H. J. Moon, and Y. C. Kim, “Comparison of random forest and gradient boosting machine models for predicting demolition waste based on small datasets and categorical variables,” Int J Environ Res Public Health, vol. 18, no. 16, Aug. 2021, doi: 10.3390/ijerph18168530.
[15] P. Nanglia, S. Kumar, A. N. Mahajan, P. Singh, and D. Rathee, “A hybrid algorithm for lung cancer classification using SVM and Neural Networks,” ICT Express, vol. 7, no. 3, pp. 335–341, 2021, doi: 10.1016/j.icte.2020.06.007.
[16] C. Y. Ku, C. Y. Liu, Y. J. Chiu, and W. Da Chen, “Deep Neural Networks with Spacetime RBF for Solving Forward and Inverse Problems in the Diffusion Process,” Mathematics, vol. 12, no. 9, 2024, doi: 10.3390/math12091407.
[17] B. Debska and B. Guzowska-Świder, “Application of artificial neural network in food classification,” Anal Chim Acta, vol. 705, no. 1–2, pp. 283–291, 2011, doi: 10.1016/j.aca.2011.06.033.
[18] R. Kumar, G. Ganapathy, and J.-J. Kang, “A Hybrid Mod K-Means Clustering with Mod SVM Algorithm to Enhance the Cancer Prediction,” International Journal of Internet, Broadcasting and Communication, vol. 13, no. 2, pp. 231–243, 2021, [Online]. Available: http://dx.doi.org/10.7236/IJIBC.2021.13.2.231
[19] Y. P. Raykov, A. Boukouvalas, F. Baig, and M. A. Little, “What to do when K-means clustering fails: A simple yet principled alternative algorithm,” PLoS One, vol. 11, no. 9, pp. 1–28, 2016, doi: 10.1371/journal.pone.0162259.
[20] Kemenkes RI, Buku Saku Pencegahan Anemia Pada Ibu Hamil Dan Remaja Putri, vol. 5, no. 4. 2023. [Online]. Available: http://dx.doi.org/10.1016/j.snb.2010.05.051
[21] Kemenkes, Laporan Riskesdas 2018 Nasional.pdf. 2018.
[22] L. A. Demidova, “Two‐stage hybrid data classifiers based on svm and knn algorithms,” Symmetry (Basel), vol. 13, no. 4, 2021, doi: 10.3390/sym13040615.
[23] Y. Y. Colin Campbell, Learning with Support Vector Machines (Synthesis Lectures on Artificial Intelligence and Machine Learning). 2011.
[24] X. Wang and P. M. Pardalos, “A Survey of Support Vector Machines with Uncertainties,” Annals of Data Science, vol. 1, no. 3–4, pp. 293–309, 2014, doi: 10.1007/s40745-014-0022-8.
[25] B. Scholkopf and A. J. Smola, (book)Learning with Kernels, vol. 53, no. 9. London, England: The MIT Press, 2002.
[26] K. I. Sundus, B. H. Hammo, M. B. Al-Zoubi, and A. Al-Omari, “Solving the multicollinearity problem to improve the stability of machine learning algorithms applied to a fully annotated breast cancer dataset,” Inform Med Unlocked, vol. 33, no. September, p. 101088, 2022, doi: 10.1016/j.imu.2022.101088.
[27] F. Bolikulov, R. Nasimov, A. Rashidov, F. Akhmedov, and Y. I. Cho, “Effective Methods of Categorical Data Encoding for Artificial Intelligence Algorithms,” Mathematics, vol. 12, no. 16, 2024, doi: 10.3390/math12162553.
[28] G. K. Dewi, I. Istianah, and S. Septiani, “Analisis Risiko Anemia Pada Ibu Hamil,” Jurnal Ilmiah Kesehatan (JIKA), vol. 4, no. 1, pp. 67–80, 2022, doi: 10.36590/jika.v4i1.223.
[29] I. Tanziha, M. R. M. Damanik, L. J. Utama, and R. Rosmiati, “Faktor Risiko Anemia Ibu Hamil Di Indonesia,” Jurnal Gizi dan Pangan, vol. 11, no. 2, pp. 143–152, 2016, doi: 10.25182/jgp.2016.11.2.%p.
[30] G. S. Yulfani Putri, S. Sulistiawati, and M. A. Cahya Laksana, “Analisis faktor-faktor risiko anemia pada ibu hamil di Kabupaten Gresik tahun 2021,” Jurnal Riset Kebidanan Indonesia, vol. 6, no. 2, pp. 119–129, 2023, doi: 10.32536/jrki.v6i2.220.
