Analisis Kombinasi Bagging dan Gradient Boosting pada Klasifikasi Diagnosis Kanker Payudara
DOI:
https://doi.org/10.36350/jbs.v16i2.346Keywords:
Machiene Learning, Gradient Boosting, Klasifikasi Kanker Payudara, Ensemble Learning, AUCAbstract
Penelitian ini bertujuan untuk menganalisis kinerja metode Gradient Boosting dalam meningkatkan performa beberapa algoritma klasifikasi machine learning pada diagnosis kanker payudara. Dataset yang digunakan adalah Breast Cancer Wisconsin (Diagnostic) yang terdiri dari 569 data dengan 30 atribut numerik yang merepresentasikan karakteristik sel jaringan payudara serta dua kelas diagnosis yaitu malignant dan benign. Proses eksperimen dilakukan melalui beberapa tahap, dimulai dari pelatihan model klasifikasi dasar menggunakan lima algoritma yaitu Support Vector Machine (SVM), Neural Network (NN), Logistic Regression (LR), Decision Tree (DT), dan K-Nearest Neighbors (KNN). Selanjutnya model tersebut dioptimasi menggunakan teknik Gradient Boosting untuk melihat pengaruhnya terhadap peningkatan performa model. Dataset dibagi menjadi 70% data training dan 30% data testing untuk memastikan evaluasi yang objektif. Evaluasi kinerja model dilakukan menggunakan confusion matrix, kurva Receiver Operating Characteristic (ROC), dan Area Under Curve (AUC). Hasil penelitian menunjukkan bahwa optimasi menggunakan teknik boosting mampu meningkatkan kemampuan klasifikasi pada beberapa algoritma machine learning. Neural Network memperoleh akurasi dasar tertinggi sebesar 98,2%, sedangkan Logistic Regression menunjukkan performa paling stabil dengan nilai AUC tertinggi sebesar 99,7%. Hasil ini menunjukkan bahwa metode Gradient Boosting dapat meningkatkan kemampuan prediksi model machine learning pada tugas klasifikasi medis khususnya diagnosis kanker payudara.
Downloads
References
[1] H. J. Yoon et al., “Accelerated training of bootstrap aggregation-based deep information extraction systems from cancer pathology reports,” J. Biomed. Inform., vol. 110, Oct. 2020, doi: 10.1016/j.jbi.2020.103564.
[2] A. H. Yunial, “Optimization Analysis of Support Vector Machine Classification Algorithms, Decision Trees, and Neural Networks Using Adaboost and Bagging,” J. Inform. Univ. Pamulang, vol. 5, no. 3, p. 247, Sep. 2020, doi: 10.32493/informatika.v5i3.6609.
[3] A. Kurniawan and A. Prihandono, “Application Of Bagging Techniques To Improve Classification Accuracy In The Naive Bayes Algorithm In Determining Professional Bloggers,” 2020.
[4] G. Arther Sandag, “A Prediction Model Of Company Health Using Bagging Classifier,” vol. 6, no. 1, 2020, doi: 10.33480/jitk.v6i1.1390.
[5] M. Dianati-nasab and K. Salimifard, “Machine learning algorithms to uncover risk factors of breast cancer: insights from a large case-control study,” no. February, pp. 1–13, 2024, doi: 10.3389/fonc.2023.1276232.
[6] H. Jafarzadeh, F. M. M. M. Eric Gill, and S. Homayouni, “Bagging and Boosting Ensemble Classifiers for Classification of Comparative Evaluation,” Remote sensing, MDPI, 2021.
[7] M. Dutta, K. M. Hasan, A. Akter, and H. Rahman, “An interpretable machine learning-based breast cancer classification using XGBoost , SHAP , and LIME,” vol. 13, no. 6, pp. 4306–4315, 2024, doi: 10.11591/eei.v13i6.7866.
[8] R. du Plooy and P. J. Venter, “A Comparison of Artificial Neural Networks and Bootstrap Aggregating Ensembles in a Modern Financial Derivative Pricing Framework,” J. Risk Financ. Manag., vol. 14, no. 6, p. 254, Jun. 2021, doi: 10.3390/jrfm14060254.
[9] V. I. Yani, A. Aradea, and H. Mubarok, “Optimasi Prakiraan Cuaca Menggunakan Metode Ensemble pada Naïve Bayes dan C4.5,” J. Tek. Inform. dan Sist. Inf., vol. 8, no. 3, pp. 607–619, 2022, doi: 10.28932/jutisi.v8i3.5455.
[10] L. M. Cendani and A. Wibowo, “Perbandingan Metode Ensemble Learning pada Klasifikasi Penyakit Diabetes,” J. Masy. Inform., vol. 13, no. 1, pp. 33–44, 2022, doi: 10.14710/jmasif.13.1.42912.
[11] R. Pramudita, S. Muis, N. Safitri, and F. Shafirawati, “Optimasi Algoritma Machine Learning Menggunakan Teknik Bagging Pada Klasifikasi Diagnosis Kanker Payudara,” Tematik, vol. 11, no. 1, pp. 128–134, 2024, doi: 10.38204/tematik.v11i1.1928.
[12] S. Al-Dahidi, P. Baraldi, E. Zio, and M. Lorenzo, “Bootstrapped ensemble of artificial neural networks technique for quantifying uncertainty in prediction of wind energy production,” Sustain., vol. 13, no. 11, Jun. 2021, doi: 10.3390/su13116417.
[13] C. O. Siti Fatihah et al., “The effect of aggregating bootstrap on the accuracy of neural network system for islamic investment prediction,” Univers. J. Account. Financ., vol. 9, no. 4, pp. 604–612, Aug. 2021, doi: 10.13189/ujaf.2021.090408.
[14] R. Pramudita, Solikin, and N. Safitri, “Optimization Analysis of Neural Network Algorithms Using Bagging Techniques on Classification of Date Fruit Types,” in Seventh International Conference on Informatics and Computing (ICIC), Denpasar: IEEE, 2022. [Online]. Available: https://ieeexplore.ieee.org/document/10006986
[15] R. Ali and A. Shabri, “Comparative analysis of hybrid models for prediction of tourist arrivals,” in AIP Conference Proceedings, S. A., E. A.F., H. S.P., R. H.A., A. M.A.K., and S. S., Eds., American Institute of Physics Inc., 2023. doi: 10.1063/5.0114935.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 TeknoIS : Jurnal Ilmiah Teknologi Informasi dan Sains
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Register 
Focus and Scope
Editorial Team
Author Gudielines
Reviewer
Author Fees (APC)
Publication Ethics
Peer Review Process
Templates
